skill-sync

Sync skills between local installation and the GitHub source-of-truth repository. Use when asked to install, update, list, or push skills.

6.69x

Quality

82%

Does it follow best practices?

Impact

87%

6.69x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

65%

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

The body is token-efficient and well-structured, but it stays at the prose-command level without pointing to the bundled executable script, lacking validation checkpoints for batch/destructive operations and a clear reference to the implementation file.

Suggestions

Add a pointer to the executable, e.g. 'See [scripts/skill-sync](scripts/skill-sync) for the implementation', so the bundle file is clearly surfaced as a one-level-deep reference.

For 'install --all' and 'push', add a validation checkpoint (e.g. verify install succeeded or confirm the PR opened) to lift workflow clarity above 2.

Expand the Commands section with the key options/parameters and exit behavior instead of restating the one-line summaries, so guidance is fully actionable.

Dimension	Reasoning	Score
Conciseness	Lean body with no concept explanations; every section earns its place and it assumes Claude's competence, e.g. 'Pushes local skill changes via branch + PR (`gh` CLI).'	3 / 3
Actionability	Quick Reference gives copy-paste-ready shell commands ('skill-sync install <skill-name>'), but the Commands section restates them as prose without parameters/options and never references the executable `scripts/skill-sync` implementation, leaving some guidance incomplete.	2 / 3
Workflow Clarity	Commands are listed as discrete steps, but there are no validation checkpoints or error-recovery feedback loops for batch/destructive operations like 'install --all' or 'push', which the rubric says should cap workflow clarity at 2.	2 / 3
Progressive Disclosure	Well-organized sections and a real bundle file exist (scripts/skill-sync), but the body never signals or links to that file, so the executable implementation is not surfaced as a one-level-deep reference.	2 / 3
	Total	9 / 12 Passed

Description

100%

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 concise, third-person description that names concrete actions, supplies a clear 'Use when' trigger, and occupies a distinct niche. Score is not capped because completeness and voice are correct.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'install, update, list, or push skills' — naming the domain (skill sync) and several specific operations rather than vague abstractions.	3 / 3
Completeness	Explicitly answers both what ('Sync skills between local installation and the GitHub source-of-truth repository') and when ('Use when asked to install, update, list, or push skills').	3 / 3
Trigger Term Quality	Natural user verbs 'install, update, list, or push skills' are exactly the phrasing a user would say; these are common variations rather than jargon.	3 / 3
Distinctiveness Conflict Risk	Clear niche (skill management against a GitHub source-of-truth repo) with distinct verbs unlikely to conflict with unrelated skills.	3 / 3
	Total	12 / 12 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: jdrhyne/agent-skills
Commit: a4d31ad

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.