CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

retro-v2

Use when a branch has finished and the session-metrics card is all that is wanted — writes and commits the card, normally just before `prep-pr`'s first push, puts its block on the pull-request body, and stops. The card-only half of `retro`, for sessions running close to their token budget. Where there is room to think, run `retro` instead — this one deliberately produces no findings and changes nothing.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

88%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.

A tightly engineered procedural skill: executable commands with variables defined, explicit validation and recovery for every risky operation (identity checks, duplicate-block check, failure branches), and dense repo-specific rationale rather than padding. Weaknesses are stylistic verbosity and a monolithic structure with no progressive-disclosure layer.

DimensionReasoningScore

Conciseness

Nearly all content is repo-specific constraint knowledge Claude cannot infer ("a tracker number on a card is a disclosure", "Stage the one card, never the directory") rather than explanations of known concepts, but the ornate prose style ("That reading is the point of the exercise, and this skill throws it away") and sections restating the description could be tightened — efficient with minor trimmable passages, not the lean-every-token-earns-its-place of anchor 5.

4 / 5

Actionability

Fully executable, copy-paste-ready bash throughout: the pre-flight probe block, the BRANCH/SLUG/PR/BASE setup, both `bun run --cwd tools/pr-metrics card` invocations, the commit and `gh pr edit --body-file` sequence, and specific recovery flags (`--pr <n>`, `--resolve-issue`) for each failure mode.

5 / 5

Workflow Clarity

Clear pre-flight → Step 1 → Step 2 → Finish sequence with explicit validation checkpoints and feedback loops: "Check the issue the card names... run both commands again with `--issue <n>` added", the duplicate-block grep (with the reason tag-matching fails), and the "When a step here cannot run" error-recovery branches. The commit/push/body-edit operations are all guarded, so no validation cap applies.

5 / 5

Progressive Disclosure

Well-organized sections (pre-flight, two steps, finish) with appropriate deferral of edge cases to `retro` Step 1 ("a tracker-only branch, a branch closing several issues and a reused branch name do instead"); however it is a single ~220-line file with no reference split — the five rules block is dense enough that it could live one level deep — so it stops short of the well-signaled reference structure of anchor 5.

4 / 5

Total

18

/

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 strong description: concrete third-person actions, an explicit "Use when" trigger with a budget-based condition, and deliberate self-differentiation from the sibling `retro` skill. The only gap is modest synonym coverage of trigger terms.

DimensionReasoningScore

Specificity

"writes and commits the card", "puts its block on the pull-request body, and stops", "deliberately produces no findings and changes nothing" — multiple concrete actions covering the skill's full scope, in third person throughout.

5 / 5

Completeness

Explicitly answers both: what ("writes and commits the card... puts its block on the pull-request body, and stops") and when ("Use when a branch has finished and the session-metrics card is all that is wanted", "for sessions running close to their token budget"), with concrete trigger phrases and an explicit when-not-to-use clause.

5 / 5

Trigger Term Quality

"a branch has finished", "session-metrics card is all that is wanted", "close to their token budget" are the natural phrases a user of this workflow would say; a few variations (e.g. "out of context", "just the metrics") are missing, so it sits above anchor 3 but short of comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

"The card-only half of `retro`" and "Where there is room to think, run `retro` instead" carve out a clear niche and explicitly disambiguate against the only plausible competing skill; minimal conflict risk.

5 / 5

Total

19

/

20

Passed

Validation

100%

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-v2/SKILL.md

Reviewed

Table of Contents

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.