retro

Use when running the retrospective on a piece of work that has just finished — the retro, normally the step straight after `prep-pr` opens the pull request — to write and commit the session-metrics card for the branch, read what the session actually cost against the difficulty declared before it started, and turn that into concrete changes to the skills, `AGENTS.md`, the wiki, the tests or the brief. Also the owner of the card — nothing else writes one carrying the pull request's identity.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

92%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An exceptionally actionable, well-sequenced procedural skill with executable commands, validation checkpoints, degradation paths for every failed prerequisite, and a properly signaled one-level-deep reference. Its only cost is length: some repeated conditionals and rationale asides could be tightened without losing information.

Dimension	Reasoning	Score
Conciseness	No concept tutorials and every rule is project-specific, but the body repeats conditionals (the "transcripts: no" handling appears in the pre-step and again in Step 1 as "as above" territory) and carries justificatory asides that could be trimmed. Not 5: there is measurable repetition; not 3: nothing explains what Claude already knows and the bulk earns its tokens.	4 / 5
Actionability	Copy-paste-ready commands throughout — the three-answer probe block, `bun run --cwd tools/pr-metrics card -- --resolve-issue`, the slug-transformed single-file `git add`, the `grep -c '^<details><summary>Session metrics'` guard — plus a filing table naming repos, labels and issue types, a `RETRO.md` template, and explicit fallbacks for no-gh/no-transcripts/no-network. Not 4: even failure paths are executable.	5 / 5
Workflow Clarity	Seven sequenced steps behind an explicit environment probe, with real validation checkpoints: read the card before forming any opinion, verify the block is not already on the PR body before appending, read the existing body rather than recomposing it, and carry on with a named record when a step cannot run. Not 4: the checkpoints and recovery loops are explicit, not implicit.	5 / 5
Progressive Disclosure	The single bundle reference, `references/card-signals.md`, is clearly signaled with its purpose and read-point ("Read it before Step 3"), is one level deep, and exists — it carries the per-field signal detail that keeps Step 2's table a summary. Not 4: the split between procedure (body) and signal reference (file) is clean and easy to navigate.	5 / 5
	Total	19 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A highly specific, well-triggered description that states concrete actions, an explicit "Use when" clause with timing context, and a distinct ownership niche. The only weakness is modest synonym coverage for the trigger terms.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — "write and commit the session-metrics card for the branch", "read what the session actually cost against the difficulty declared before it started", "turn that into concrete changes to the skills, `AGENTS.md`, the wiki, the tests or the brief" — covering the retro's outputs comprehensively. Not 4: coverage has no minor gaps; every output class (card, comparison, findings) is named with its target.	5 / 5
Completeness	Explicitly answers both: "Use when running the retrospective on a piece of work that has just finished — … normally the step straight after `prep-pr` opens the pull request" (when) and the card/cost-comparison/findings action list (what). Not 4: the trigger clause is explicit and concrete rather than improvable.	5 / 5
Trigger Term Quality	Includes natural terms a user would actually say — "retrospective", "the retro", "piece of work that has just finished", "prep-pr", "pull request" — but misses common variations such as "postmortem" or "session review". Not 3: keyword coverage is good, not merely "some relevant keywords"; not 5: synonym breadth is incomplete.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — the post-`prep-pr` retro and card ownership ("nothing else writes one carrying the pull request's identity") — so it is unlikely to fire for a sibling pipeline skill. Not 4: the ownership claim and pipeline position leave only minimal overlap risk.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: englishstreetventures/osn
Path: .claude/skills/retro/SKILL.md
Commit: c63f0ed

Reviewed: 13 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.