recap
Skill1 starsChanged 18 days agoApache-2.0View on GitHub
Render the session's end-of-work summary in the fixed recap format — what shipped, what surfaced along the way, which signals deserve a GitHub issue, and the immediate next steps. Use when the user says "recap", "recap the session", "recap the day", "summarize what we did", "summarize the session", "what did we get done", "wrap up the session", "debrief", or asks for a summary of the work just finished. Read-only: it reports and recommends; it never files issues or mutates anything.
44 other projects use a version of this.
Adopted by
Most recently taken up by
- mel0nyrame/skillstheir own version, first seen Nov 8, 2026
- delorenj/skillstheir own version, first seen Nov 7, 2026
- Integralist/agent-skillstheir own version, first seen Nov 6, 2026
- acegalaxy-co/ace_commons-ccswitch-clitheir own version, first seen Nov 1, 2026
- kanalias/ace_commons-ccswitch-clitheir own version, first seen Nov 1, 2026
- AcKeskin/contexturetheir own version, first seen Nov 1, 2026
Used with
Projects with it also use glossary, orchestrate and 7 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
Microsoft AzureSkillglossary
Short glossary of domain terms used by the team.
Also in 3 projects that use this
varun29ankuSSkillorchestrate
This skill should be used when the user asks to 'orchestrate a task', 'break down work into parallel agents', 'coordinate subtasks', 'run agents in parallel', or mentions 'multi-agent'. Decomposes complex tasks into tracked subtasks, dispatches parallel subagents, and coordinates until completion.
Also in 4 projects that use this
sunnyclinches44Skillexplain
Explains code using real-world analogies and ASCII diagrams
Also in 3 projects that use this
Microsoft AzureSkillbuild
Build the TypeSpec Rust emitter from source. Run this after cloning the repo, after pulling changes, or when TypeScript source files have been modified.
Also in 3 projects that use this
nicolasestremSkillbrainstorm
Structured idea generation and solution exploration with systematic analysis.
Also in 3 projects that use this
BlockSkillplan
Draft a TDD, PRD, or lightweight plan in the conversation without committing it.
Also in 3 projects that use this
Other versions44 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 44
- first-fluke/fullstack-starter★ 226same name
- backnotprop/bro★ 176same name
- benoror/obsidianos_work★ 166same name
- Soul-Brews-Studio/arra-oracle-skills-cli★ 121same name
- mbwsims/claude-universe★ 71same name
- TakaGoto/rag-learning-academy★ 24same name
- Integralist/agent-skills★ 23same name
- delorenj/skills★ 17same name
- ivklgn/ai-kit★ 12same name
- ivklgn/bag-of-skills★ 12same name
34 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository24 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- assess-itSkill
- dispatch-readySkill
- github-issuesSkill
- github-secretsSkill
- groom-backlogSkill
- pr-shepherdSkill
- repo-cleanupSkill
- repo-healthSkill
- send-itSkill
- sentry-triageSkill
- setup-configSkill
- setup-depsSkill
- setup-hooksSkill
- setup-repoSkill
- survey-workSkill
- take-itSkill
- testflightSkill
- tidy-repoSkill
- whats-behindSkill
- whats-on-fireSkill
- work-fire-watchSkill
- work-recommendationsSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 38 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 74
Every next step leads with the short bold action phrase.
“Common” is measured: kept by at least 6 in 10 of the 38 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Recap
One retrospective report of the session just worked: what happened, what it revealed, and what to do next — the same shape every time, so the user can scan it instead of re-reading the session.
Acting principle: a recap is evidence, not memory. Report only what was actually observed in
this session; anything uncertain renders as uncertain, never inferred — a confident summary built
on unverified claims reads exactly like a real one. Before asserting a terminal state ("merged",
"closed", "landed"), re-check it with a quick read (gh pr view, gh issue view) if the session's
last observation of it is stale.
1. Gather
Walk the session once and sort every event into exactly one bucket:
- Work completed — things that changed state and finished: merged PRs, pushed commits, config or infrastructure mutations, external actions (routine/trigger updates, secrets set). Each item keeps its evidence: PR number, commit SHA, run or session id, or link.
- What surfaced — findings the session produced that required no action yet: gotchas hit, diagnoses made, signals noticed (a flaky test, a coverage gap, a doc mismatch). One line each on why it matters.
- Issues we should file — the subset of surfaced signals with NO tracking issue anywhere. Each
gets a proposed title, suggested labels, and a one-line rationale — enough that filing it later
is mechanical. Check
gh issue list --searchbefore proposing; a signal that is already tracked belongs under "what surfaced" with its issue number instead. - Immediate next steps — actions, not states. "PR #13 awaiting merge" is a state; "Merge PR
#13 — green and waiting on a human press" is a step. Order by priority; when the step is a
one-liner, include the literal command (
take #99,gh pr merge 13 --auto).
In-flight work that is still running (a watcher, an unfinished agent, an unmerged PR) is a next step, never "completed".
2. Render
Output exactly this shape, inline as markdown:
# Recap (YYYY-MM-DD)
## ✅ Work completed
- **<short bold action phrase>** — outcome, with evidence (PR #N · commit · link)
## 🔍 What surfaced
- **<finding>** — one line on why it matters (issue #N if already tracked)
## 📋 Issues we should file
- **<proposed title>** — `label`, `label` — one-line rationale
## 👉 Immediate next steps
1. **<short bold action phrase>** — one-line detail · `command` when it is a one-linerFormat rules:
- Sections in exactly this order; next steps LAST.
- An empty section is DROPPED entirely — except
## ✅ Work completedand## 👉 Immediate next steps, which always render. An empty completed section says so honestly ("Nothing shipped this session"); an empty next-steps section is almost always a gather failure, not a clean slate. - Every next step leads with the short bold action phrase; detail after the em-dash.
- Prose is complete sentences with evidence inline — fixed section names only, never a per-run taxonomy.
3. Read-only contract
This skill never files issues, never edits issues, and never mutates anything — in any repo, under
any invocation. "Issues we should file" is a recommendation list; when the user approves filing,
route it through sassy-dog:github-issues (its file-or-link-issue.sh dedupe-then-file path),
never file directly from here.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

