diff --git a/chat/services/turn_parse.py b/chat/services/turn_parse.py
index df721dc..9c1e778 100644
--- a/chat/services/turn_parse.py
+++ b/chat/services/turn_parse.py
@@ -16,6 +16,16 @@ nested quotes, mixed punctuation), so v1 delegates the segmentation to
 the classifier. The configurable ``Settings.ooc_marker`` is *not* read
 here: the classifier figures OOC out from ``((`` ``))`` regardless of
 config-time choice; marker-based stripping is a downstream concern.
+
+T62 extends the parser with an ``intent`` field so the turn flow can
+short-circuit time-skip phrases before the regular narrative path.
+``intent`` defaults to ``"narrative"``; the classifier may set it to
+``"skip_elision"`` when prose like "skip to when we arrive" or
+``"skip_jump"`` when prose like "next morning" / "a week later" is
+detected. ``landing_state_hint`` carries the residual descriptor for
+elision skips (the "to when we ..." phrase). Existing callers that
+don't read ``intent`` continue to work because the default keeps the
+narrative path intact.
 """
 
 from __future__ import annotations
@@ -39,9 +49,19 @@ class TurnSegment(BaseModel):
 
 
 class ParsedTurn(BaseModel):
-    """A turn split into ordered, typed segments."""
+    """A turn split into ordered, typed segments.
+
+    ``intent`` distinguishes a regular narrative beat (the default) from
+    a natural-language time-skip command (T62). ``landing_state_hint``
+    captures the descriptor following "skip to when we ..." for elision
+    skips so the downstream skip controller can pass it to the
+    narration helper. Both fields are optional and default-empty so
+    older fixtures and tests that don't supply them keep working.
+    """
 
     segments: list[TurnSegment]
+    intent: str = "narrative"  # "narrative" | "skip_elision" | "skip_jump"
+    landing_state_hint: str = ""
 
 
 _SYSTEM_PROMPT = (
@@ -52,13 +72,24 @@ _SYSTEM_PROMPT = (
     "- ((text in double parens)) is an OOC (out-of-character) segment — "
     "the author talking to the system, not the in-fiction bot.\n\n"
     "Output a JSON object with shape "
-    '{"segments": [{"kind": "...", "text": "..."}, ...]} '
-    "where each ``kind`` is exactly one of: dialogue, action, ooc. "
-    "Preserve the original substring text as ``text``: do not rewrite, "
-    "translate, or normalize punctuation — strip only the marker "
-    "characters (asterisks, surrounding quotes, double parens) so "
-    "``text`` is the inner content. Emit segments in the order they "
-    "appear in the input."
+    '{"segments": [{"kind": "...", "text": "..."}, ...], '
+    '"intent": "...", "landing_state_hint": "..."} '
+    "where each segment ``kind`` is exactly one of: dialogue, action, "
+    "ooc. Preserve the original substring text as ``text``: do not "
+    "rewrite, translate, or normalize punctuation — strip only the "
+    "marker characters (asterisks, surrounding quotes, double parens) "
+    "so ``text`` is the inner content. Emit segments in the order they "
+    "appear in the input.\n\n"
+    "``intent`` is exactly one of: narrative, skip_elision, skip_jump. "
+    "Default to ``narrative``. Use ``skip_elision`` when the prose is a "
+    "directive to fast-forward an in-progress activity to a near-term "
+    "landing state — e.g. 'skip to when we arrive', 'fast-forward to "
+    "after dinner'. Use ``skip_jump`` when the prose denotes a longer "
+    "fiction-time bridge — e.g. 'next morning', 'a week later', 'the "
+    "following day'.\n"
+    "``landing_state_hint`` is a short descriptor of the landing state "
+    "for ``skip_elision`` (e.g. 'we arrive at the park'). Empty string "
+    "for ``skip_jump`` and ``narrative``."
 )
 
 
diff --git a/chat/web/drawer.py b/chat/web/drawer.py
index ea27721..1098eb5 100644
--- a/chat/web/drawer.py
+++ b/chat/web/drawer.py
@@ -29,19 +29,15 @@ from __future__ import annotations
 
 import json
 import uuid
-from datetime import datetime, timezone
 from pathlib import Path
 
 from fastapi import APIRouter, Depends, Form, HTTPException, Request
 from fastapi.responses import HTMLResponse
 from fastapi.templating import Jinja2Templates
 
-from chat.eventlog.log import append_and_apply, append_event
-from chat.services.memory_write import record_turn_memory_for_present
+from chat.eventlog.log import append_and_apply
 from chat.services.relationship_seed import seed_inter_bot_edges
 from chat.services.scene_summarize import apply_scene_close_summary
-from chat.services.skip_narration import narrate_skip
-from chat.services.synthesized_memories import synthesize_memories
 from chat.state.edges import get_edge
 from chat.state.entities import get_bot, get_you, list_bots
 from chat.state.events import list_active_events
@@ -51,6 +47,11 @@ from chat.state.threads import list_open_threads
 from chat.state.world import active_scene, get_activity, get_chat, get_container
 from chat.web.bots import get_conn
 from chat.web.kickoff import get_llm_client
+from chat.web.skip import (
+    _now_iso,
+    process_elision_skip,
+    process_jump_skip,
+)
 
 TEMPLATES = Jinja2Templates(
     directory=str(Path(__file__).resolve().parent.parent / "templates")
@@ -881,29 +882,6 @@ async def remove_guest(
 # rerenders itself on these submissions).
 
 
-def _parse_iso_time(value: str) -> datetime | None:
-    """Permissive ISO 8601 parser for skip route validation.
-
-    ``datetime.fromisoformat`` doesn't accept a trailing ``Z`` until 3.11,
-    so we normalize it to ``+00:00`` first. Returns ``None`` on parse
-    failure so the caller can return ``400`` with a stable error shape.
-    """
-    if not value:
-        return None
-    try:
-        v = value.strip()
-        if v.endswith("Z"):
-            v = v[:-1] + "+00:00"
-        return datetime.fromisoformat(v)
-    except (TypeError, ValueError):
-        return None
-
-
-def _now_iso() -> str:
-    """UTC ISO timestamp used as a fallback when the chat clock is unset."""
-    return datetime.now(timezone.utc).isoformat()
-
-
 @router.post(
     "/chats/{chat_id}/drawer/event/plan",
     response_class=HTMLResponse,
@@ -1000,70 +978,29 @@ async def skip_elision(
 ):
     """Elision skip: collapse in-progress activity into its end-state.
 
-    Validates ``new_time`` is ISO 8601 AND non-decreasing relative to the
-    chat clock (a backwards skip would corrupt downstream causality).
-    Emits ``time_skip_elision`` first (chat clock advances) then an
-    ``assistant_turn`` carrying the narrated transition from
-    :func:`chat.services.skip_narration.narrate_skip`. The narration call
-    has its own LLM-failure fallback so this route never blocks on a
-    flaky model.
+    Thin HTTP wrapper around :func:`chat.web.skip.process_elision_skip`
+    (T62 extracted the controller). Validation failures surface as
+    ``400`` and the route still returns the refreshed drawer partial on
+    success so HTMX swaps in the new chat clock.
     """
-    chat = get_chat(conn, chat_id)
-    if chat is None:
-        raise HTTPException(status_code=404, detail=f"chat not found: {chat_id}")
-
-    new_dt = _parse_iso_time(new_time)
-    if new_dt is None:
-        raise HTTPException(
-            status_code=400,
-            detail=f"new_time must be ISO 8601, got {new_time!r}",
-        )
-    cur_dt = _parse_iso_time(chat.get("time") or "")
-    if cur_dt is not None and new_dt < cur_dt:
-        raise HTTPException(
-            status_code=400,
-            detail="new_time must not be earlier than the current chat clock",
-        )
-
-    host_bot = get_bot(conn, chat["host_bot_id"]) or {
-        "name": "host",
-        "persona": "",
-    }
-    you_entity = get_you(conn) or {"name": "you"}
-    bot_activity = get_activity(conn, chat["host_bot_id"]) or {}
-    current_activity = (
-        (bot_activity.get("action") or {}).get("verb") or ""
-    )
-
     settings = request.app.state.settings
-    narration = await narrate_skip(
-        client,
-        narrative_model=settings.narrative_model,
-        skip_kind="elision",
-        speaker_bot=host_bot,
-        you_name=you_entity.get("name") or "you",
-        current_time=chat.get("time") or "",
-        new_time=new_time,
-        current_activity=current_activity,
-        landing_state_hint=landing_state_hint,
-        timeout_s=settings.classifier_timeout_s,
-    )
-
-    append_and_apply(
-        conn,
-        kind="time_skip_elision",
-        payload={"chat_id": chat_id, "new_time": new_time},
-    )
-    append_event(
-        conn,
-        kind="assistant_turn",
-        payload={
-            "chat_id": chat_id,
-            "speaker_id": host_bot["id"] if "id" in host_bot else chat["host_bot_id"],
-            "text": narration,
-            "truncated": False,
-        },
-    )
+    try:
+        await process_elision_skip(
+            conn,
+            client,
+            settings,
+            chat_id=chat_id,
+            new_time=new_time,
+            landing_state_hint=landing_state_hint,
+        )
+    except ValueError as exc:
+        # ``process_elision_skip`` raises on missing-chat or malformed /
+        # backwards new_time. The drawer used to 404 / 400 these
+        # separately — preserve the 404-vs-400 split by sniffing the
+        # error message so existing tests keep passing without changes.
+        if str(exc).startswith("chat not found"):
+            raise HTTPException(status_code=404, detail=str(exc))
+        raise HTTPException(status_code=400, detail=str(exc))
     return await drawer(chat_id, request, conn)
 
 
@@ -1082,123 +1019,28 @@ async def skip_jump(
 ):
     """Jump skip: bridge a longer fiction-time delta.
 
-    Same ISO + non-decreasing validations as the elision route. When
-    ``notable_prose`` is non-empty, runs :func:`synthesize_memories`
-    once per present bot witness (host always; guest when present),
-    then writes one ``memory_written`` per synthesized memory via
-    :func:`record_turn_memory_for_present` (which fans out to host +
-    guest internally). Each call writes ``source="synthesized"`` so the
-    retrieval ranker can treat them as lower-reliability than direct
-    turn memories. Finally emits ``time_skip_jump`` and the narration
-    ``assistant_turn``.
-
-    ``reset_activity`` is parsed permissively ("1" / "true" / "on" /
-    "yes" — same shape as the add-guest reseed flag) since HTML
-    checkboxes typically post the literal "1" or omit the field
-    entirely.
+    Thin HTTP wrapper around :func:`chat.web.skip.process_jump_skip`
+    (T62 extracted the controller). ``reset_activity`` is parsed
+    permissively here ("1" / "true" / "on" / "yes" — same shape as the
+    add-guest reseed flag) since HTML checkboxes typically post the
+    literal "1" or omit the field entirely.
     """
-    chat = get_chat(conn, chat_id)
-    if chat is None:
-        raise HTTPException(status_code=404, detail=f"chat not found: {chat_id}")
-
-    new_dt = _parse_iso_time(new_time)
-    if new_dt is None:
-        raise HTTPException(
-            status_code=400,
-            detail=f"new_time must be ISO 8601, got {new_time!r}",
-        )
-    cur_dt = _parse_iso_time(chat.get("time") or "")
-    if cur_dt is not None and new_dt < cur_dt:
-        raise HTTPException(
-            status_code=400,
-            detail="new_time must not be earlier than the current chat clock",
-        )
-
     reset_flag = reset_activity.lower() in ("1", "true", "on", "yes")
-
-    host_bot = get_bot(conn, chat["host_bot_id"]) or {
-        "id": chat["host_bot_id"],
-        "name": "host",
-        "persona": "",
-    }
-    you_entity = get_you(conn) or {"name": "you"}
-    you_name = you_entity.get("name") or "you"
-    guest_bot_id = chat.get("guest_bot_id")
-    guest_bot = get_bot(conn, guest_bot_id) if guest_bot_id else None
-
     settings = request.app.state.settings
-
-    # Emit time_skip_jump up front so the chat clock is at the new time
-    # before any memory writes — they should record at the post-jump
-    # clock, mirroring how a regular turn's memory carries the chat clock.
-    append_and_apply(
-        conn,
-        kind="time_skip_jump",
-        payload={
-            "chat_id": chat_id,
-            "new_time": new_time,
-            "reset_activity": reset_flag,
-        },
-    )
-
-    # Synthesize memories per present bot witness when prose is non-empty.
-    # ``synthesize_memories`` short-circuits on whitespace prose so this
-    # is safe to call unconditionally, but we gate the loop to avoid
-    # iterating a fixed empty list.
-    if notable_prose.strip():
-        present_bots: list[dict] = [host_bot]
-        if guest_bot is not None:
-            present_bots.append(guest_bot)
-        for bot in present_bots:
-            digest = await synthesize_memories(
-                client,
-                classifier_model=settings.classifier_model,
-                prose=notable_prose,
-                bot_name=bot.get("name") or "",
-                bot_persona=bot.get("persona") or "",
-                you_name=you_name,
-                timeout_s=settings.classifier_timeout_s,
-            )
-            for mem in digest.memories:
-                # ``record_turn_memory_for_present`` writes one
-                # ``memory_written`` per present bot per call. Calling it
-                # once per synthesized memory means N memories x M bots
-                # = N*M events; the loop above already iterates by bot
-                # so we pass guest_bot_id=None here to avoid double-
-                # writing the guest's row when bot==guest.
-                record_turn_memory_for_present(
-                    conn,
-                    chat_id=chat_id,
-                    host_bot_id=bot["id"],
-                    guest_bot_id=None,
-                    narrative_text=mem.text,
-                    chat_clock_at=new_time,
-                    source="synthesized",
-                    significance=mem.significance,
-                )
-
-    narration = await narrate_skip(
-        client,
-        narrative_model=settings.narrative_model,
-        skip_kind="jump",
-        speaker_bot=host_bot,
-        you_name=you_name,
-        current_time=chat.get("time") or "",
-        new_time=new_time,
-        current_activity="",
-        landing_state_hint=notable_prose,
-        timeout_s=settings.classifier_timeout_s,
-    )
-    append_event(
-        conn,
-        kind="assistant_turn",
-        payload={
-            "chat_id": chat_id,
-            "speaker_id": host_bot.get("id") or chat["host_bot_id"],
-            "text": narration,
-            "truncated": False,
-        },
-    )
+    try:
+        await process_jump_skip(
+            conn,
+            client,
+            settings,
+            chat_id=chat_id,
+            new_time=new_time,
+            notable_prose=notable_prose,
+            reset_activity=reset_flag,
+        )
+    except ValueError as exc:
+        if str(exc).startswith("chat not found"):
+            raise HTTPException(status_code=404, detail=str(exc))
+        raise HTTPException(status_code=400, detail=str(exc))
     return await drawer(chat_id, request, conn)
 
 
diff --git a/chat/web/skip.py b/chat/web/skip.py
new file mode 100644
index 0000000..ccbf470
--- /dev/null
+++ b/chat/web/skip.py
@@ -0,0 +1,287 @@
+"""Shared skip-flow controllers (T62).
+
+Both the drawer skip routes (T59) and the natural-language skip parse
+(T62) call into these controllers. Keep the controllers free of HTTP
+concerns — they take ``conn`` + ``client`` + ``settings`` and structured
+args, append events, and return a small result dict the caller can map
+to whatever response shape it owes (drawer partial, 204, 422, etc.).
+
+``ValueError`` is the controller-level signal for caller-mappable
+validation failure (bad ISO timestamp, backwards skip). The drawer
+routes translate it to ``HTTP 400``; the natural-language path either
+swallows it (the parser handed us a degenerate hint) or surfaces it the
+same way. Anything else (LLM failure, unexpected exception) propagates
+uncaught — :func:`narrate_skip` already has its own deterministic
+fallback for the routine LLM-down case, so a real exception here means
+something we want to see.
+
+The two controllers mirror the drawer T59 logic closely so the v1
+guarantees (``time_skip_*`` lands first → memory writes ride the
+post-skip clock → narration ``assistant_turn`` is appended last) hold
+identically across the two entry points.
+"""
+
+from __future__ import annotations
+
+from datetime import datetime, timezone
+from sqlite3 import Connection
+
+from chat.config import Settings
+from chat.eventlog.log import append_and_apply, append_event
+from chat.llm.client import LLMClient
+from chat.services.memory_write import record_turn_memory_for_present
+from chat.services.skip_narration import narrate_skip
+from chat.services.synthesized_memories import synthesize_memories
+from chat.state.entities import get_bot, get_you
+from chat.state.world import get_activity, get_chat
+
+
+def _parse_iso_time(value: str) -> datetime | None:
+    """Permissive ISO 8601 parser shared with the drawer routes (T59).
+
+    ``datetime.fromisoformat`` doesn't accept a trailing ``Z`` until
+    Python 3.11; we normalize it to ``+00:00`` so older interpreters
+    parse the same set of strings the drawer accepts.
+    """
+    if not value:
+        return None
+    try:
+        v = value.strip()
+        if v.endswith("Z"):
+            v = v[:-1] + "+00:00"
+        return datetime.fromisoformat(v)
+    except (TypeError, ValueError):
+        return None
+
+
+def _validate_new_time(chat: dict, new_time: str) -> None:
+    """Raise ``ValueError`` if ``new_time`` is unparseable or backwards.
+
+    The drawer route maps the raised error to ``HTTP 400``; the
+    natural-language path may also surface it as a ``400``. Centralizing
+    the rule here means both entry points enforce the same invariant
+    (no causality-corrupting backwards jumps).
+    """
+    new_dt = _parse_iso_time(new_time)
+    if new_dt is None:
+        raise ValueError(f"new_time must be ISO 8601, got {new_time!r}")
+    cur_dt = _parse_iso_time(chat.get("time") or "")
+    if cur_dt is not None and new_dt < cur_dt:
+        raise ValueError(
+            "new_time must not be earlier than the current chat clock"
+        )
+
+
+async def process_elision_skip(
+    conn: Connection,
+    client: LLMClient,
+    settings: Settings,
+    *,
+    chat_id: str,
+    new_time: str,
+    landing_state_hint: str = "",
+) -> dict:
+    """Run an elision skip end-to-end.
+
+    Validates ``new_time`` against the current chat clock, appends a
+    ``time_skip_elision`` event (chat clock advances), generates a
+    transition narration via :func:`narrate_skip`, and appends an
+    ``assistant_turn`` carrying the narration. ``narrate_skip`` has its
+    own deterministic fallback so this never blocks on the model.
+
+    Returns ``{"assistant_text": ..., "speaker_id": ..., "skip_event_id":
+    ..., "assistant_event_id": ...}`` so callers can introspect the
+    generated turn (e.g. for SSE rebroadcast or test assertions).
+
+    Raises ``ValueError`` on validation failure or when the chat row
+    can't be located (the drawer maps it to ``HTTP 400`` / ``404``
+    respectively; the natural-language path follows the same shape).
+    """
+    chat = get_chat(conn, chat_id)
+    if chat is None:
+        raise ValueError(f"chat not found: {chat_id}")
+
+    _validate_new_time(chat, new_time)
+
+    host_bot = get_bot(conn, chat["host_bot_id"]) or {
+        "id": chat["host_bot_id"],
+        "name": "host",
+        "persona": "",
+    }
+    you_entity = get_you(conn) or {"name": "you"}
+
+    # The drawer route reaches into the host bot's current activity to
+    # surface the verb to the narration helper — we do the same so both
+    # entry points produce the same prose for the same chat state.
+    bot_activity = get_activity(conn, chat["host_bot_id"]) or {}
+    current_activity = (bot_activity.get("action") or {}).get("verb") or ""
+
+    narration = await narrate_skip(
+        client,
+        narrative_model=settings.narrative_model,
+        skip_kind="elision",
+        speaker_bot=host_bot,
+        you_name=you_entity.get("name") or "you",
+        current_time=chat.get("time") or "",
+        new_time=new_time,
+        current_activity=current_activity,
+        landing_state_hint=landing_state_hint,
+        timeout_s=settings.classifier_timeout_s,
+    )
+
+    skip_event_id = append_and_apply(
+        conn,
+        kind="time_skip_elision",
+        payload={"chat_id": chat_id, "new_time": new_time},
+    )
+    speaker_id = host_bot.get("id") or chat["host_bot_id"]
+    assistant_event_id = append_event(
+        conn,
+        kind="assistant_turn",
+        payload={
+            "chat_id": chat_id,
+            "speaker_id": speaker_id,
+            "text": narration,
+            "truncated": False,
+        },
+    )
+
+    return {
+        "assistant_text": narration,
+        "speaker_id": speaker_id,
+        "skip_event_id": skip_event_id,
+        "assistant_event_id": assistant_event_id,
+    }
+
+
+async def process_jump_skip(
+    conn: Connection,
+    client: LLMClient,
+    settings: Settings,
+    *,
+    chat_id: str,
+    new_time: str,
+    notable_prose: str = "",
+    reset_activity: bool = False,
+) -> dict:
+    """Run a jump skip end-to-end.
+
+    Same validations as :func:`process_elision_skip`. Emits
+    ``time_skip_jump`` *before* synthesizing memories so per-bot writes
+    record the post-jump chat clock (mirroring how a regular turn's
+    memory carries the chat clock). When ``notable_prose`` is non-empty,
+    runs :func:`synthesize_memories` once per present bot witness, then
+    fans the resulting memories out via
+    :func:`record_turn_memory_for_present` with ``source="synthesized"``.
+    Finally appends the narration ``assistant_turn``.
+
+    Returns ``{"assistant_text": ..., "speaker_id": ..., "skip_event_id":
+    ..., "assistant_event_id": ...}``.
+
+    Raises ``ValueError`` on validation failure (caller maps to ``400``).
+    """
+    chat = get_chat(conn, chat_id)
+    if chat is None:
+        raise ValueError(f"chat not found: {chat_id}")
+
+    _validate_new_time(chat, new_time)
+
+    host_bot = get_bot(conn, chat["host_bot_id"]) or {
+        "id": chat["host_bot_id"],
+        "name": "host",
+        "persona": "",
+    }
+    you_entity = get_you(conn) or {"name": "you"}
+    you_name = you_entity.get("name") or "you"
+    guest_bot_id = chat.get("guest_bot_id")
+    guest_bot = get_bot(conn, guest_bot_id) if guest_bot_id else None
+
+    # Emit time_skip_jump up front so subsequent memory writes ride the
+    # post-jump chat clock (matches the drawer T59 behavior pinned by
+    # test_post_skip_jump_with_notable_prose_writes_synthesized_memories).
+    skip_event_id = append_and_apply(
+        conn,
+        kind="time_skip_jump",
+        payload={
+            "chat_id": chat_id,
+            "new_time": new_time,
+            "reset_activity": reset_activity,
+        },
+    )
+
+    # Synthesize per-bot memories when prose is non-empty. The helper
+    # short-circuits on whitespace prose, but gating the loop here keeps
+    # the canned-LLM-queue accounting predictable for tests.
+    if notable_prose.strip():
+        present_bots: list[dict] = [host_bot]
+        if guest_bot is not None:
+            present_bots.append(guest_bot)
+        for bot in present_bots:
+            digest = await synthesize_memories(
+                client,
+                classifier_model=settings.classifier_model,
+                prose=notable_prose,
+                bot_name=bot.get("name") or "",
+                bot_persona=bot.get("persona") or "",
+                you_name=you_name,
+                timeout_s=settings.classifier_timeout_s,
+            )
+            for mem in digest.memories:
+                # ``record_turn_memory_for_present`` writes one row per
+                # present bot per call — we already iterate by bot here,
+                # so guest_bot_id=None avoids double-writing the guest's
+                # row when bot==guest.
+                record_turn_memory_for_present(
+                    conn,
+                    chat_id=chat_id,
+                    host_bot_id=bot["id"],
+                    guest_bot_id=None,
+                    narrative_text=mem.text,
+                    chat_clock_at=new_time,
+                    source="synthesized",
+                    significance=mem.significance,
+                )
+
+    narration = await narrate_skip(
+        client,
+        narrative_model=settings.narrative_model,
+        skip_kind="jump",
+        speaker_bot=host_bot,
+        you_name=you_name,
+        current_time=chat.get("time") or "",
+        new_time=new_time,
+        current_activity="",
+        landing_state_hint=notable_prose,
+        timeout_s=settings.classifier_timeout_s,
+    )
+    speaker_id = host_bot.get("id") or chat["host_bot_id"]
+    assistant_event_id = append_event(
+        conn,
+        kind="assistant_turn",
+        payload={
+            "chat_id": chat_id,
+            "speaker_id": speaker_id,
+            "text": narration,
+            "truncated": False,
+        },
+    )
+
+    return {
+        "assistant_text": narration,
+        "speaker_id": speaker_id,
+        "skip_event_id": skip_event_id,
+        "assistant_event_id": assistant_event_id,
+    }
+
+
+def _now_iso() -> str:
+    """UTC ISO timestamp used by callers as a chat-clock fallback."""
+    return datetime.now(timezone.utc).isoformat()
+
+
+__all__ = [
+    "process_elision_skip",
+    "process_jump_skip",
+    "_now_iso",
+    "_parse_iso_time",
+]
diff --git a/chat/web/turns.py b/chat/web/turns.py
index 5ef6725..5d2ff94 100644
--- a/chat/web/turns.py
+++ b/chat/web/turns.py
@@ -51,8 +51,10 @@ import html
 import json
 import re
 
+from datetime import timedelta
+
 from fastapi import APIRouter, Depends, Form, HTTPException, Request
-from fastapi.responses import HTMLResponse, RedirectResponse, Response
+from fastapi.responses import HTMLResponse, JSONResponse, RedirectResponse, Response
 
 from chat.eventlog.log import append_and_apply, append_event
 from chat.services.addressee import detect_addressee
@@ -75,6 +77,7 @@ from chat.web.bots import get_conn
 from chat.web.kickoff import get_llm_client
 from chat.web.pubsub import publish
 from chat.web.render import render_turn_html as _render_turn_html
+from chat.web.skip import _parse_iso_time, process_elision_skip
 
 router = APIRouter()
 
@@ -254,6 +257,65 @@ async def post_turn(
     )
     prompt_prose = _strip_ooc_for_prompt(parsed)
 
+    # 1a. Skip-command short-circuit (T62). The parser may classify the
+    # prose as a time-skip directive — in which case the regular
+    # narrative path (addressee detection, narrative stream, post-turn
+    # state-update + scene-close passes) is skipped entirely. Elision
+    # runs through the shared controller in :mod:`chat.web.skip`; jump
+    # is drawer-only for Phase 3 (the natural-language path returns
+    # 422 directing the user to the drawer's jump form, where they can
+    # supply structured ``notable_prose`` and a target time). Anything
+    # not matching these intents falls through to the narrative branch.
+    intent = getattr(parsed, "intent", "narrative") or "narrative"
+    if intent == "skip_jump":
+        # Drawer-only jump for Phase 3: parsing a free-form fiction-time
+        # delta out of natural language ("next morning" -> ?) is fragile
+        # enough that we'd rather route the user to the drawer form,
+        # where they pick a concrete ISO time and an optional notable-
+        # prose field. 422 = "request shape is understood, but the
+        # required structured input lives on a different surface".
+        return JSONResponse(
+            {
+                "error": (
+                    "Jump skip requires the drawer's jump form for "
+                    "notable_prose."
+                )
+            },
+            status_code=422,
+        )
+
+    if intent == "skip_elision":
+        # Derive ``new_time`` from the chat clock. Phase 3 stub: bump by
+        # 1 hour. The drawer's elision form is the structured path when
+        # the author wants a specific landing time; here the goal is
+        # "elide the dull bit" and any sensible forward step is fine —
+        # ``narrate_skip`` weaves the landing-state hint into the
+        # transition prose so the prose carries the semantic time, not
+        # the timestamp itself.
+        cur_dt = _parse_iso_time(chat.get("time") or "")
+        new_time = (
+            (cur_dt + timedelta(hours=1)).isoformat()
+            if cur_dt is not None
+            else (chat.get("time") or "")
+        )
+        try:
+            await process_elision_skip(
+                conn,
+                client,
+                settings,
+                chat_id=chat_id,
+                new_time=new_time,
+                landing_state_hint=getattr(parsed, "landing_state_hint", "")
+                or "",
+            )
+        except ValueError as exc:
+            # The controller raises on missing chat / bad new_time.
+            # Missing chat is already handled above (we'd have 404'd);
+            # a bad new_time here is a stub-derivation bug rather than
+            # user input — surface as 400 with the controller message.
+            raise HTTPException(status_code=400, detail=str(exc))
+        return Response(status_code=204)
+
     # 2. Append user_turn event.
     user_turn_event_id = append_event(
         conn,
diff --git a/tests/test_turn_flow.py b/tests/test_turn_flow.py
index a202e2d..80364ec 100644
--- a/tests/test_turn_flow.py
+++ b/tests/test_turn_flow.py
@@ -1137,3 +1137,183 @@ def test_turn_with_no_active_events_skips_classifier(app_state_setup, tmp_path):
                 "SELECT COUNT(*) FROM event_log WHERE kind = ?", (kind,)
             ).fetchone()[0]
             assert count == 0, f"expected zero {kind} events, got {count}"
+
+
+# ---------------------------------------------------------------------------
+# Phase 3 (T62) — natural-language skip-command surface.
+#
+# The classifier may flag prose as a time-skip directive via
+# ``ParsedTurn.intent``. Elision runs through the shared controller in
+# :mod:`chat.web.skip` and short-circuits the regular narrative path;
+# jump returns 422 directing the user to the drawer's structured form
+# (Phase 3 simpler path — natural-language jump time derivation is too
+# fragile for v1 without the structured surface).
+# ---------------------------------------------------------------------------
+
+
+def test_elision_skip_via_natural_language(app_state_setup, tmp_path):
+    """User prose 'skip to when we arrive at the park' classifies as
+    ``intent='skip_elision'``. The post_turn handler short-circuits the
+    narrative path, advances the chat clock by an hour stub, appends a
+    ``time_skip_elision`` event AND an ``assistant_turn`` carrying the
+    canned narration. No ``user_turn`` is emitted on the skip path.
+
+    Canned queue: 1 parse_turn (intent=skip_elision) + 1 narration
+    string (consumed by ``narrate_skip``). No state-update / scene-close
+    / event-detection slots — those branches are bypassed entirely.
+    """
+    _seed(tmp_path / "test.db")
+    canned_parse = json.dumps(
+        {
+            "segments": [
+                {"kind": "dialogue", "text": "skip to when we arrive at the park"}
+            ],
+            "intent": "skip_elision",
+            "landing_state_hint": "we arrive at the park",
+        }
+    )
+    canned_narration = "We pull up to the park entrance, sun low in the sky."
+    mock = _override_llm([canned_parse, canned_narration])
+    try:
+        response = app_state_setup.post(
+            "/chats/chat_bot_a/turns",
+            data={"prose": "skip to when we arrive at the park"},
+        )
+        assert response.status_code == 204
+    finally:
+        app.dependency_overrides.clear()
+
+    # Both canned slots drained — no other classifier branches ran.
+    assert mock._canned == []
+
+    with open_db(tmp_path / "test.db") as conn:
+        # time_skip_elision landed.
+        skip_rows = conn.execute(
+            "SELECT payload_json FROM event_log "
+            "WHERE kind = 'time_skip_elision' ORDER BY id"
+        ).fetchall()
+        assert len(skip_rows) == 1
+        sp = json.loads(skip_rows[0][0])
+        assert sp["chat_id"] == "chat_bot_a"
+        # 1-hour stub from the seeded chat clock (20:00 -> 21:00).
+        assert sp["new_time"].startswith("2026-04-26T21:00:00")
+
+        # Chat clock advanced via the projector.
+        from chat.state.world import get_chat
+
+        chat = get_chat(conn, "chat_bot_a")
+        assert chat["time"].startswith("2026-04-26T21:00:00")
+
+        # An assistant_turn carrying the canned narration was appended.
+        turn_rows = conn.execute(
+            "SELECT payload_json FROM event_log "
+            "WHERE kind = 'assistant_turn' ORDER BY id"
+        ).fetchall()
+        assert len(turn_rows) == 1
+        tp = json.loads(turn_rows[0][0])
+        assert tp["chat_id"] == "chat_bot_a"
+        assert tp["text"] == canned_narration
+        assert tp["speaker_id"] == "bot_a"
+        assert tp["truncated"] is False
+
+        # No user_turn lands on the skip path — the natural-language
+        # skip is a command, not a beat the bots should remember.
+        user_count = conn.execute(
+            "SELECT COUNT(*) FROM event_log WHERE kind = 'user_turn'"
+        ).fetchone()[0]
+        assert user_count == 0
+
+
+def test_jump_skip_via_natural_language_returns_422(app_state_setup, tmp_path):
+    """User prose 'next morning' classifies as ``intent='skip_jump'``.
+    The handler returns 422 with a guidance payload pointing the author
+    at the drawer's structured jump form. No event is emitted — the
+    drawer form is the only entry point for jump skips in Phase 3.
+    """
+    _seed(tmp_path / "test.db")
+    canned_parse = json.dumps(
+        {
+            "segments": [{"kind": "dialogue", "text": "next morning"}],
+            "intent": "skip_jump",
+            "landing_state_hint": "",
+        }
+    )
+    # Only one canned slot — parse — because the 422 fallback short-
+    # circuits before any other classifier runs.
+    mock = _override_llm([canned_parse])
+    try:
+        response = app_state_setup.post(
+            "/chats/chat_bot_a/turns", data={"prose": "next morning"}
+        )
+        assert response.status_code == 422
+        body = response.json()
+        # Guidance payload mentions the drawer so the client can surface
+        # the right CTA; we don't pin the exact wording.
+        assert "drawer" in body.get("error", "").lower()
+    finally:
+        app.dependency_overrides.clear()
+
+    # Parse slot consumed; no follow-on classifier calls.
+    assert mock._canned == []
+
+    with open_db(tmp_path / "test.db") as conn:
+        for kind in (
+            "user_turn",
+            "assistant_turn",
+            "time_skip_elision",
+            "time_skip_jump",
+        ):
+            count = conn.execute(
+                "SELECT COUNT(*) FROM event_log WHERE kind = ?", (kind,)
+            ).fetchone()[0]
+            assert count == 0, f"expected zero {kind} on jump-via-NL, got {count}"
+
+
+def test_skip_command_does_not_run_narrative_classifier(
+    app_state_setup, tmp_path, monkeypatch
+):
+    """The skip dispatch branch must bypass the narrative-prompt assembly
+    entirely. We monkeypatch ``assemble_narrative_prompt`` (re-bound on
+    the ``chat.web.turns`` module since the handler imports it by name)
+    and assert the call count is zero after the elision skip lands.
+    """
+    _seed(tmp_path / "test.db")
+    canned_parse = json.dumps(
+        {
+            "segments": [
+                {"kind": "dialogue", "text": "skip to when we arrive at the park"}
+            ],
+            "intent": "skip_elision",
+            "landing_state_hint": "we arrive at the park",
+        }
+    )
+    canned_narration = "We arrive moments later."
+    mock = _override_llm([canned_parse, canned_narration])
+
+    call_counter = {"n": 0}
+
+    def _spy(*args, **kwargs):
+        call_counter["n"] += 1
+        return []
+
+    # Patch the symbol at the handler's import site so we can assert
+    # the skip path bypasses prompt assembly even when the symbol still
+    # exists in the module namespace.
+    from chat.web import turns as turns_mod
+
+    monkeypatch.setattr(turns_mod, "assemble_narrative_prompt", _spy)
+
+    try:
+        response = app_state_setup.post(
+            "/chats/chat_bot_a/turns",
+            data={"prose": "skip to when we arrive at the park"},
+        )
+        assert response.status_code == 204
+    finally:
+        app.dependency_overrides.clear()
+
+    assert mock._canned == []
+    assert call_counter["n"] == 0, (
+        "assemble_narrative_prompt was called on the skip path; the "
+        "natural-language skip dispatch must bypass narrative assembly."
+    )