release

Use this skill for EVERY ClawRouter release. Enforces the full checklist — version sync, CHANGELOG, build, tests, npm publish, git tag, GitHub release. No step can be skipped.

Quality

76%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/release/SKILL.md

Quality

Content

85%Weight 40%Scale 1-3

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

The body is highly actionable and workflow-clear, with strong validation checkpoints for a release process, but loses conciseness to verbose historical explanation of a deprecated manual-sync step.

Suggestions

Collapse Step 4's historical prose and code block to a one-line note ('No server-side constant edit needed — blockrun auto-fetches the latest version from the npm registry'), moving detail to a reference if ever needed.

Trim the Common Mistakes table entries that merely restate step ordering already enforced by the numbered sequence.

Dimension	Reasoning	Score
Conciseness	Most steps are lean executable commands, but Step 4 spends substantial prose plus a full code block explaining a manual-sync pattern that 'no longer' applies — historical context Claude does not need — and the Common Mistakes table restates prior steps, so it is mostly efficient with unnecessary padding rather than fully lean.	2 / 3
Actionability	Every step provides concrete, copy-paste-ready commands (cat, npm run build, git tag, gh release create, npm publish) and a runnable final-verification block, matching the fully-executable anchor.	3 / 3
Workflow Clarity	A clearly sequenced 12-step process with explicit validation checkpoints ('All must pass' in Step 6, the 5-point 'All 5 must match' verification in Step 12 with 'fix before declaring done') provides strong feedback loops for this destructive/batch operation.	3 / 3
Progressive Disclosure	It is a single-file, single-purpose skill with no bundle files, organized into well-numbered sections and a reference table, which per the scoring notes qualifies for a 3 when content is well-organized.	3 / 3
	Total	11 / 12 Passed

Description

67%Weight 40%Scale 1-3

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 specific and clearly niche-scoped to ClawRouter releases, but it lacks an explicit 'Use when...' trigger clause and natural trigger terms within the description text itself, which caps completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' clause to the description naming natural user phrasings (e.g. 'Use when releasing, shipping, or publishing ClawRouter').

Fold one or two natural trigger phrases ('version bump', 'tag the release') into the description rather than relying solely on the triggers field.

Tighten 'No step can be skipped' — it restates the checklist framing and adds little for trigger identification.

Dimension	Reasoning	Score
Specificity	The description enumerates concrete release actions — 'version sync, CHANGELOG, build, tests, npm publish, git tag, GitHub release' — matching the multiple-specific-actions anchor.	3 / 3
Completeness	It clearly answers 'what' (the full release checklist) but lacks an explicit 'Use when...' clause giving the 'when'; the guidelines cap completeness at 2 when such trigger guidance is missing.	2 / 3
Trigger Term Quality	It states 'Use this skill for EVERY ClawRouter release' but the natural user phrasings ('ship clawrouter', 'version bump', 'tag clawrouter release') live in the triggers field rather than the description, so common variations are missing from the description itself.	2 / 3
Distinctiveness Conflict Risk	The named product 'ClawRouter' and specific release-only scope make it a clear niche unlikely to trigger for the wrong skill.	3 / 3
	Total	10 / 12 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: BlockRunAI/ClawRouter
Path: skills/release/SKILL.md
Commit: c6587c1

Reviewed: 11 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.