CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

70

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

72%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 skill body is well-architected with executable commands, a clear staged workflow, and excellent progressive disclosure via real reference files. The main gaps are conciseness redundancy and the absence of explicit validation/feedback loops for destructive public actions.

Suggestions

Add an explicit validate-then-retry checkpoint before any public-facing action (e.g., dry-run/review the drafted comment or closure, verify, then post on approval) to lift workflow clarity above 2 for batch/irreversible operations.

Deduplicate the Gates section against the Reference Router table, or fold both into a single 'load-before-acting' table, to remove repeated reference citations and tighten conciseness.

Trim the Interaction Model prose to bullet form so every remaining token earns its place against the lean-and-efficient anchor.

DimensionReasoningScore

Conciseness

The body is mostly efficient and free of padded explanations of concepts Claude already knows, but sections like the 'Gates' partially restate the Reference Router table and the Interaction Model adds prose that could be tightened; it is not as lean as a minimal all-essential-tokens anchor would require.

2 / 3

Actionability

Provides copy-paste-ready commands (`npx tsx …/scripts/triage.ts` with --delta/--keep/--datetime/--config), concrete citation examples (ISSUE:42:C:3), and a routing table mapping each task to a named reference file plus required output, fully matching the executable-and-specific anchor.

3 / 3

Workflow Clarity

The Stage 0–6 workflow is clearly sequenced with a human-approval gate, but batch/irreversible public actions (commenting, closing, labeling) lack an explicit validate-then-retry feedback loop, which the rubric caps at 2 for destructive/batch operations.

2 / 3

Progressive Disclosure

A concise overview body points to 8 real one-level-deep references via an explicit Reference Router table and Gates section, each signal paired with its required output; the referenced files (references/*.md, scripts/triage.ts) all exist, matching the clear-overview-with-well-signaled-references anchor.

3 / 3

Total

10

/

12

Passed

Description

100%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 strong: concrete capabilities, an explicit and natural trigger list, and a clearly bounded niche. Third-person voice is used throughout, so no specificity penalty applies. No meaningful improvement needed.

DimensionReasoningScore

Specificity

Names the domain (open-source GitHub repo maintenance) and lists multiple concrete actions — 'triage issues, review PRs, analyze contributor activity, generate maintenance reports, or maintain a repository' — which is comprehensive rather than partial, so it sits above the score-2 anchor.

3 / 3

Completeness

Explicitly answers both 'what' (end-to-end maintenance actions) and 'when' via 'Use when asked to…' plus an explicit 'Triggers include…' list, satisfying the explicit-triggers anchor for 3 and not the implied-only anchor at 2.

3 / 3

Trigger Term Quality

Provides broad coverage of natural user phrasings — 'triage', 'maintain', 'review PRs', 'analyze issues', 'repo maintenance', 'what needs attention', 'open source maintenance' — matching the 'good coverage of natural terms' anchor rather than the partial coverage at 2.

3 / 3

Distinctiveness Conflict Risk

The open-source GitHub repo-maintenance niche with its distinct trigger set ('review PRs', 'repo maintenance', 'what needs attention') is unlikely to fire for unrelated skills, matching the 'clear niche with distinct triggers' anchor.

3 / 3

Total

12

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
numman-ali/n-skills
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.