cw-gates

Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.

Quality

88%

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

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.

The body is a tightly written, fully executable verification ladder with strong sequencing and explicit validation feedback loops. Its only weak spots are minor verbosity in the anecdotal justifications and the lack of separated reference files.

Dimension	Reasoning	Score
Conciseness	The body is lean and mostly commands with terse justification, but the embedded war stories ('burned twice', the v0.9.10 clippy anecdote) are slightly verbose even though they are load-bearing for the rules they motivate.	4 / 5
Actionability	Fully executable, copy-paste-ready commands throughout — `cargo fmt --all -- --check`, `scripts/dev-test.sh ...`, the full set of `python3 scripts/check-*.py` budget checks, and an exact clippy invocation with all flags — covering the common cases.	5 / 5
Workflow Clarity	A clearly sequenced Rung 1–5 ladder ordered by risk, with explicit validation checkpoints (quote the real test-result line, confirm N>0 for the relevant tests, focused rerun before calling a flake) and an Output checklist; feedback loops are present throughout.	5 / 5
Progressive Disclosure	Well-organized into clear sections with one-level-deep, clearly signaled references to sibling skills and repo docs; no bundle files exist to defer to, and the bulk stays inline, leaving minor organization gaps versus a fully split structure.	4 / 5
	Total	18 / 20 Passed

Description

87%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.

The description is repo-specific and clearly answers both what the skill does and when to use it, with concrete natural-language trigger terms. It is strong overall, with only minor room to add verb-form actions and a few extra trigger synonyms.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete components — 'the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test' — but frames them as items provided rather than verb-actions, so it sits just below the fully comprehensive anchor.	4 / 5
Completeness	Explicitly answers both: what ('verification ladder', 'budget checks CI enforces', 'rules for a passing test') and when ('Use before claiming any Codewhale change is done, green, or ready to land') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural trigger phrases a user would actually say — 'done', 'green', 'ready to land' — appear explicitly with good coverage, though a few common synonyms (e.g. 'passing', 'CI green') are only implied.	4 / 5
Distinctiveness Conflict Risk	The Codewhale-scoped niche ('Codewhale change', 'budget checks CI enforces', 'verification ladder') is distinct and unlikely to trigger for unrelated skills, with minimal conflict risk.	5 / 5
	Total	18 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 6 suspicious	Warning
referenced_paths_exist	Referenced path issues: 15 missing	Warning

	Total	14 / 16 Passed

Repository: Hmbown/Codewhale
Path: docs/skills/cw-gates/SKILL.md
Commit: 21282f1

Reviewed: 6 days 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.