retro
Close a session by routing ONE finding to the strongest rung it reaches - a gate or test, else a hook, else prose, else dropped.
Skill by vancourse
Chalk Labs
Need help deploying retro?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/vancourse-retro
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: testing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/retro
What's inside
- Skill name
retro- Description
- Close a session by routing ONE finding to the strongest rung it reaches - a gate or test, else a hook, else prose, else dropped.
- License
- MIT
- Instructions
- 15 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# The retro loop
1. **One finding, with a number.** What went wrong this session that a mechanism could have
caught? Use your own turn history, never a parse of transcript files.
2. **Route it to the strongest rung:**
- a **gate or test** (`rails/gates.toml` row with cites, a planted defect, an FP count measured on
the real tree, and `required_by`);
- else a **hook** (plugin `hooks/gates.toml` row; 7 days in shadow before it refuses);
- else **prose**, only under `## Judgment` or with `-> enforced by: <path>`;
- else **drop it**. Dropping is the common case and not a failure.
3. **Write it where it lives** before the session ends: the PR body, an issue (one per session), or
the registry. A lesson only in chat is gone next session.
4. **Delete one thing** if the metrics say a mechanism earned nothing (`rails metrics`).From vancourse/apex, MIT.
More from vancourse/apex
- 0.587score
rails
vancourse
The rails loop and its commands - claim, intent, rails check, push, rails ship, walk, used.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
adversarial-pair
vancourse
Run a review as two isolated voices, cooperative and adversarial, then reconcile.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
typescript-review
vancourse
TypeScript/React review rules (types, hooks, state, tests, errors).
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
python-review
vancourse
Python review rules (types, SQL, async, tests, errors, security).
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
postgres-review
vancourse
Postgres schema, RLS, indexing and SQL review rules.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
security-review
vancourse
Pre-PR security pass for auth, data access, external input, secrets and dependencies.
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
fix
vancourse
Fix something broken - a defect, a red check, a wrong behaviour.
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
release
vancourse
Start or close a release (a milestone whose done is the operator using it).
SkillAFreshness: A★ 1Claude Code +9 - 0.318score
design-review
vancourse
No description from the publisher yet.
SkillAFreshness: A★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 1
- Open issues
- 9
- Last commit (this folder)
- Oct 6, 2026 (24 days ago)
- Last release
- Aug 13, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/vancourse/apex
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from vancourse
- 0.587score
rails
vancourse
The rails loop and its commands - claim, intent, rails check, push, rails ship, walk, used.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
adversarial-pair
vancourse
Run a review as two isolated voices, cooperative and adversarial, then reconcile.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
typescript-review
vancourse
TypeScript/React review rules (types, hooks, state, tests, errors).
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
python-review
vancourse
Python review rules (types, SQL, async, tests, errors, security).
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
postgres-review
vancourse
Postgres schema, RLS, indexing and SQL review rules.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
security-review
vancourse
Pre-PR security pass for auth, data access, external input, secrets and dependencies.
SkillAFreshness: A★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get retro running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
retro skill. Agent Mart. https://agentmart.dev/skills/vancourse-retro (last updated 2026-10-24)