skill-sync
Sync skills between local installation and the GitHub source-of-truth repository. Use when asked to install, update, list, or push skills.
89
88%
Does it follow best practices?
Impact
87%
6.69xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid, concise description that clearly communicates both purpose and trigger conditions. It uses appropriate third-person voice and includes natural trigger terms. The only minor weakness is that the specific actions could be slightly more detailed (e.g., what 'sync' or 'push' entails), but overall it performs well across all dimensions.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (skill syncing between local and GitHub) and some actions (install, update, list, push), but doesn't elaborate on what each action entails or describe the full range of capabilities. | 2 / 3 |
Completeness | Clearly answers both 'what' (sync skills between local installation and GitHub source-of-truth repository) and 'when' (explicitly states 'Use when asked to install, update, list, or push skills'). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'install', 'update', 'list', 'push', 'skills', 'sync'. These are terms a user would naturally use when managing skills. | 3 / 3 |
Distinctiveness Conflict Risk | Very distinct niche — syncing skills between local and GitHub is a specific operational task unlikely to conflict with other skills. The triggers (install/update/list/push skills) are clearly scoped. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
87%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, concise CLI reference skill that provides immediately actionable commands. Its main weakness is the lack of workflow sequencing and validation guidance—particularly around the push command which creates PRs and could benefit from a pre-push checklist or error recovery steps. The quick reference + detailed commands pattern is effective for discoverability.
Suggestions
Add a brief recommended workflow sequence (e.g., 'Run `skill-sync update` before `install` to ensure latest versions') and mention what to do if `gh` CLI auth fails during push.
Add a validation step or checklist before `skill-sync push` (e.g., verify no secrets in SKILL.md, confirm changes are tested locally).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every line serves a purpose. No unnecessary explanations of what skills are or how Git works. The quick reference table and command descriptions are lean and assume Claude's competence. | 3 / 3 |
Actionability | Provides exact, copy-paste-ready CLI commands for every operation. Each command is concrete with clear syntax including arguments and flags. | 3 / 3 |
Workflow Clarity | Commands are clearly listed but there's no explicit workflow sequence (e.g., 'update before install' or 'validate after push'). The push command involves a destructive/external operation (creating a PR) but lacks validation checkpoints or error handling guidance. | 2 / 3 |
Progressive Disclosure | For a simple CLI wrapper skill under 50 lines, the content is well-organized with a quick reference section for fast lookup and a detailed commands section for specifics. Configuration defaults are cleanly separated at the end. | 3 / 3 |
Total | 11 / 12 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 — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- jdrhyne/agent-skills
- Commit
6768672
- 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.