open-source-maintainer
End-to-end GitHub repository maintenance for open-source projects. Use when asked to triage issues, review PRs, analyze contributor activity, generate maintenance reports, or maintain a repository. Triggers include "triage", "maintain", "review PRs", "analyze issues", "repo maintenance", "what needs attention", "open source maintenance", or any request to understand and act on GitHub issues/PRs. Supports human-in-the-loop workflows with persistent memory across sessions.
75
92%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
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.
This is a strong skill description that clearly communicates its purpose, lists concrete actions, provides explicit trigger guidance with natural user terms, and occupies a distinct niche. The inclusion of both a 'Use when' clause and a 'Triggers include' list makes it highly effective for skill selection. Minor note: the mention of 'persistent memory across sessions' is a nice differentiator but is more of an implementation detail than a selection trigger.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: triage issues, review PRs, analyze contributor activity, generate maintenance reports, and maintain a repository. Also mentions human-in-the-loop workflows and persistent memory across sessions. | 3 / 3 |
Completeness | Clearly answers both 'what' (end-to-end GitHub repository maintenance including triaging, reviewing PRs, analyzing activity, generating reports) and 'when' (explicit 'Use when...' clause and a 'Triggers include...' list with specific keywords). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'triage', 'maintain', 'review PRs', 'analyze issues', 'repo maintenance', 'what needs attention', 'open source maintenance'. These are natural phrases a user would actually use when requesting these tasks. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to GitHub repository maintenance for open-source projects with distinct triggers like 'triage', 'repo maintenance', and 'open source maintenance'. Unlikely to conflict with general coding skills or other GitHub-adjacent skills due to the specific maintenance/ops focus. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%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, high-quality skill that provides clear operational guidance for repository maintenance. Its strongest features are the explicit workflow stages with human-in-the-loop gates, the just-in-time reference router pattern, and concrete script usage examples. Minor weaknesses include some redundancy between sections (Gates vs Reference Router, repeated human-approval constraints) that could be consolidated for better token efficiency.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient and avoids explaining basic concepts, but includes some redundancy (e.g., the 'Gates' section largely repeats the 'Reference Router' table, and the 'Human Approval Required' section at the end restates what's already in the Operating Contract). Some tightening is possible. | 2 / 3 |
Actionability | Provides concrete, executable commands for the triage script with multiple flag options, specific file paths for persistent state, a clear citation format, and explicit step-by-step workflow stages. The guidance is specific enough to act on immediately. | 3 / 3 |
Workflow Clarity | The six-stage workflow (Setup → Capture → Analyze → Synthesize → Align → Execute → Record) is clearly sequenced with explicit validation checkpoints (human approval gates, reference-loading gates before destructive/public actions). The gates section provides clear stop-and-verify points for risky operations like public comments and closures. | 3 / 3 |
Progressive Disclosure | The Reference Router table is an excellent progressive disclosure mechanism — it explicitly tells Claude which reference to load and when, avoiding upfront loading of all files. The per-repo state table and clear file-purpose mapping support easy navigation. However, no bundle files were provided to verify the referenced paths exist, but the structure itself is well-designed. | 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
- numman-ali/n-skills
- Commit
a518c67
- 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.