End-of-session closure. Records what changed into the project's own handoff and log files, separating verified from attempted work, and reports what is uncommitted. Use when wrapping up a session. Twin of sitrep.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
Write down what the next session would otherwise have to rediscover. The record is only useful if it is honest: a log that reports intentions as accomplishments costs more than no log, because the next session trusts it.
Glob for .codex/prompts/*finish*.md, .codex/prompts/*wrap*.md, and the same patterns under .claude/commands/ — they catch variants such as finished.md or wrap-up.md. If one matches, Read it, follow its instructions instead of the steps below, and say which file you used. Otherwise continue here.
Read AGENTS.md and CLAUDE.md for the stated handoff or logging convention, then locate the artifacts the project actually keeps: HANDOFF.md, CODEX_HANDOFF.md, STATUS.md, SESSION_LOG.md, NOTES.md, or a dated logs/ directory. Match the structure already in the file. Updating these existing files is the job and needs no approval. If the project keeps none, summarize in the reply and offer once to start a durable file, since that sets a convention for the repository.
git status --short
git log --oneline <session-start>..HEAD
git diff --stat
Ground every claim in one of these outputs. For each item, classify it:
If the user asked for a commit or push, run it and record the resulting hash in both the handoff file and the log entry. Otherwise leave the tree alone and report what is uncommitted — closing a session is not authorization to publish it.
List the files updated, with paths, anything left uncommitted or unresolved, and any work that is done but unverified.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Consult an independent, read-only GPT-6 Astra advisor before committing to a substantive interpretation, approach, or final result. Not for routine work, implementation, or file edits. Uses gpt-6-astra at an effort matched to the question.
The English summary is being prepared. Showing the original description.
Consults Fable as an independent, read-only reviewer at an effort the caller matches to the question. The calling session (usually Opus, or Haiku) holds the task and escalates one decision point. Use before committing to an interpretation or a substantial piece of writing or analysis, when stuck or not converging, when changing approach, or as a final check on a finished task. Fallback for when the native advisor tool is unavailable. Not for a session already running Fable.
The English summary is being prepared. Showing the original description.
House rules and craft for LaTeX Beamer slide decks (lectures, seminars, talks), drawn from the author's own Overleaf edits and published slide-design guidance. Covers storyboarding, frame titles, slide prose, word and frame budgets, layout without overfull boxes, XeLaTeX fonts and Korean (xeCJK), color, figures and screenshots, Overleaf source hygiene, speaker notes, and a build-and-QA loop with a contact sheet. Use when writing, editing, reviewing, or building a Beamer deck, theme, or storyboard. A course skill supplies course facts and the frame skeleton; this skill supplies the craft. Not for HTML or PowerPoint decks, posters, or papers.
The English summary is being prepared. Showing the original description.
House rules and craft for LaTeX Beamer decks (storyboarding, slide prose, frame budgets, layout, XeLaTeX and Korean fonts, color, figures, Overleaf hygiene, build QA). Use to write, edit, review, or build a Beamer deck.
The English summary is being prepared. Showing the original description.
Audit a manuscript's citations for fabricated sources, DOIs that resolve to the wrong work, in-text and reference-list mismatches, style, and claim support, verified against Crossref and OpenAlex. Use to check citations, references, a .bib file, or DOIs.
The English summary is being prepared. Showing the original description.
Audits a manuscript's citations for fabricated or nonexistent sources, DOIs that resolve to a different work, mismatches between in-text citations and the reference list, APA 7 or journal style, and whether each source supports the claim it is attached to. Checks entries against Crossref, OpenAlex, and DataCite and labels anything it could not verify NOT CHECKED. Use to check citations, references, a .bib file, or DOIs, or when a source may be AI-invented. Figures and tables go to figure-table-audit.
The English summary is being prepared. Showing the original description.