Skip to content
cccskills
FreePublished on GitHub

sitrep

Start-of-session report on where a repository stands. Reads the project's own handoff and log files, checks live git state, and reports objective, verified baseline, open tasks, blockers, and next actions. Use when resuming work. Twin of finished.

The English summary is being prepared. Showing the original description.

See how to install

Files included (2)

  • SKILL.md2.9 KB
  • agents/openai.yaml246 B

SKILL.md (original)

Review the instructions the agent will receive before you install.

Situational report

Answer one question: where does this project actually stand right now? The value is in the gap between what the project's own documents claim and what the repository shows. Report the gap; never launder a stale document into a current fact.

0. Defer to the repository first

Glob for .codex/prompts/*sitrep*.md, .codex/prompts/*status*.md, and the same patterns under .claude/commands/ — they catch variants such as project-sitrep.md. If one matches, Read it, follow its instructions instead of the steps below, and say which file you used. If several match, pick the closest name and say which. Otherwise continue here.

1. Learn the project's conventions

Read AGENTS.md and CLAUDE.md if present; they usually state the handoff or logging convention. Fall back to README.md for orientation. Then find the project's own memory: HANDOFF.md, CODEX_HANDOFF.md, STATUS.md, SESSION_LOG.md, NOTES.md, or a logs/ directory with dated entries.

Use what the project has. If it keeps none, say so rather than inventing a format.

2. Check live state

git status --short
git log --oneline -n 8
git branch --show-current
git status -sb | head -1

Two failure modes are worth the extra commands. A detached or behind branch: if git status -sb shows divergence from the upstream, run git fetch and report the true position — a local branch can be many commits behind while the working tree looks clean. Working-tree drift: if the project syncs files outside git (Syncthing, Dropbox, a shared mount), a large uncommitted diff may be someone else's committed work that this clone's .git has not seen. Check before treating it as local change.

3. Confirm load-bearing artifacts, only if the project names them

If AGENTS.md or README.md names specific data files, build outputs, or directories as load-bearing, spot-check that they exist.

4. Report

Order by priority, not by discovery order. Cite concrete paths and commands.

  • Current objective — from the handoff document if one exists, otherwise inferred from recent commits and README.md. Say which.
  • Completed baseline — what is done and verified. Distinguish "committed" from "verified"; they are not the same claim.
  • Open tasks — what is queued, with the file or command each would start from.
  • Risks and blockers — anything stale, missing, half-finished, or contradicted by what the repository shows. When a handoff names commits, branches, artifacts, or versions the repository no longer matches, say so and propose the exact fix.
  • Immediate next actions — a short numbered list the user can approve in one line.

Reviews

No reviews yet. Tell others what you thought.

Comments

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.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

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.

scdenney/open-science-skills69Updated Oct 20, 2026

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.

scdenney/open-science-skills69Updated Oct 20, 2026

beamer

Free

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.

scdenney/open-science-skills69Updated Oct 20, 2026

beamer

Free

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.

scdenney/open-science-skills69Updated Oct 20, 2026

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.

scdenney/open-science-skills69Updated Oct 20, 2026

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.

scdenney/open-science-skills69Updated Oct 20, 2026

See all skills by scdenney

Report a problem with this skill