contributor-onboarding

Help a new contributor get productive on this checkout - inspect sync state against main, build, run the repository's exact verification gate, and produce a local what's-new digest. Never fetches, pulls, or modifies a dirty tree on its own. Explicit-only.

Quality

85%

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

93%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 written, fully executable onboarding workflow with clear sequencing and explicit safety boundaries; the only meaningful gap is a missing validate→fix→re-run feedback loop at the gate, which bounds workflow_clarity at 4.

Suggestions

Add an explicit gate feedback loop: on a clippy/fmt/test failure, state 'fix the reported issue and re-run the exact gate command before reporting pass/fail' rather than only 'do not claim a gate passed you did not run'.

Promote the known flake into a concrete retry/confirm step (e.g. 're-run the failing test in isolation; if it passes, attribute to the known flake') so recovery is actionable rather than asserted.

Make the changelog-cap rule a small checklist item so truncation behavior is mechanically verifiable during the run.

Dimension	Reasoning	Score
Conciseness	Lean and purposeful: every section is a concrete step with verbatim commands and a brief rule, no padding or explanation of concepts Claude already knows; assumes competence throughout, so it matches the 'lean and efficient' anchor rather than the trimmed-explanation 4.	5 / 5
Actionability	Fully executable — exact git and cargo commands are given copy-paste ready for each phase, with the exact CI lints and caps (20 commits / 40 lines) specified; covers the common cases concretely, matching the 5 anchor.	5 / 5
Workflow Clarity	Clear six-phase sequence with explicit checkpoints ('A build failure ends the run', gate must pass before dogfood) and an error-recovery ordering for a dirty tree; capped at 4 rather than 5 because the verification gate lacks an explicit validate→fix→re-run feedback loop and the flake handling is asserted rather than looped.	4 / 5
Progressive Disclosure	Well-organized sections with no bundle files needed and no nested references; content is appropriately self-contained and easy to navigate, which the rubric's under-50-line/simple-skill guidance rewards with a 5 even without external file references.	5 / 5
	Total	19 / 20 Passed

Description

76%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 specific, third-person description with concrete actions and clear scope/boundary (read-only, explicit-only), but it omits an explicit 'Use when…' trigger clause and a few natural trigger phrases, which bounds trigger-term quality and completeness.

Suggestions

Add an explicit trigger clause such as 'Use when a contributor has freshly cloned this repo and asks am I current, does it build, does it pass, or what changed while I was away.'

Surface natural user phrasing in the description ('onboarding', 'does my checkout pass CI', 'what's new since I last pulled') so the skill matches how the request is actually phrased.

Sharpen distinctiveness by naming the checkout-local, network-free constraint up front so it does not collide with general build/CI skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'inspect sync state against main, build, run the repository's exact verification gate, and produce a local what's-new digest' — with comprehensive coverage of the onboarding task; not below 5 since coverage is broad and concrete, not the single-domain handful of actions at 4.	5 / 5
Completeness	Clearly states what it does and implies the when ('Help a new contributor get productive'), but lacks an explicit 'Use when…' trigger clause, which caps completeness at 4 per the rubric guideline rather than 5.	4 / 5
Trigger Term Quality	Contains natural contributor-language triggers ('get productive on this checkout', 'what's-new digest', 'build', 'sync state') but omits common synonyms like 'onboarding', 'am I current', or 'does it pass' that a user might say; good coverage but a few natural terms missing, so not 5.	4 / 5
Distinctiveness Conflict Risk	The 'new contributor get productive / build / run verification gate' framing is fairly distinct, yet overlaps with general CI/build and git-status skills; 'somewhat specific but could still overlap with similar skills' fits best, and the lack of an explicit trigger clause keeps it from 4.	3 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: Hmbown/CodeWhale
Path: crates/tui/assets/skills/contributor-onboarding/SKILL.md
Commit: 8ae401b

Reviewed: 1 day 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.