From neurodock
Close the currently open chronometric session, optionally attaching a verbatim summary. Triggers the auto-summary side effect used by weekly_rollup.
How this skill is triggered — by the user, by Claude, or both
Slash command
/neurodock:chronometric-mark-endThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Quick wrapper for `mark_session_end` on the local NeuroDock chronometric
Quick wrapper for mark_session_end on the local NeuroDock chronometric
server (neurodock-chronometric). Closes the most-recent open session and
returns its final metadata.
Authoritative schema $id:
https://schemas.neurodock.org/mcp-chronometric/v0.1.0/mark_session_end.schema.json
(source).
Calls mcp__neurodock-chronometric__mark_session_end with an optional
summary. The server:
session_id
argument — by design, per ADR 0001).ended_at (ISO 8601 with offset).duration as an ISO 8601 duration string.intent.session_id, started_at, ended_at, duration, intent,
summary.The verbatim intent + summary pair is the unit consumed by the
cognitive graph's weekly_rollup tool. Sessions ended without a summary
are still included but contribute less signal. Encourage the user to write
a one-line summary even when nothing "finished" — "got distracted into refactor; did not finish the planned migration ADR" is more useful than
no summary at all.
Minimal:
{}
With summary:
{
"summary": "shipped the RFC reply, parked two follow-ups in inbox"
}
Constraints:
summary is optional, 1–1000 chars, plain language.session_id field — the server picks the most recent open session.Example response:
{
"session_id": "6f9f4f5e-3b1c-4e2a-9f7d-2b3c4d5e6f70",
"started_at": "2026-05-23T09:14:22+01:00",
"ended_at": "2026-05-23T10:42:18+01:00",
"duration": "PT1H27M56S",
"intent": "finish draft RFC reply",
"summary": "shipped the RFC reply, parked two follow-ups in inbox"
}
NO_OPEN_SESSION — caller thought a session was open; it was not.
Distinct from silent success so the caller can tell "I forgot to
start one" from "this worked".SUMMARY_TOO_LONG — over 1000 chars. Trim and retry.Read the duration back plainly. Do not editorialise ("wow, an hour!" — no). Just the numbers and the user's own words. The summary is theirs, not something to reformulate.
Provides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub tlennon-ie/neurodock --plugin neurodock