Fix a single GitHub issue end-to-end: triage, research, write the fix, review, and create a PR. Use when asked to fix an issue: "fix issue 1234", "resolve #500", "create a PR for issue 200".
99
100%
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 concisely covers the full workflow (triage, research, fix, review, PR), uses third person voice correctly, and includes an explicit 'Use when' clause with realistic user trigger phrases. It is well-scoped to a specific niche (single GitHub issue resolution) and would be easily distinguishable from other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: triage, research, write the fix, review, and create a PR. These are clear, actionable steps in a well-defined workflow. | 3 / 3 |
Completeness | Clearly answers both 'what' (fix a single GitHub issue end-to-end: triage, research, write the fix, review, create a PR) and 'when' (explicit 'Use when' clause with concrete trigger examples). | 3 / 3 |
Trigger Term Quality | Includes natural trigger phrases users would actually say: 'fix issue 1234', 'resolve #500', 'create a PR for issue 200'. Covers common variations including issue numbers with and without '#' prefix. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to fixing a single GitHub issue end-to-end with PR creation. The specific trigger terms ('fix issue', 'resolve #', 'create a PR for issue') are distinct and unlikely to conflict with general coding or PR review skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent orchestration skill that clearly defines a decision tree for handling GitHub issues end-to-end. It is concise, actionable with concrete commands, has a well-sequenced workflow with validation loops, and appropriately delegates to composable sub-skills for progressive disclosure. The only minor note is that without bundle files, we can't verify the referenced sub-skills exist, but the structure is sound.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section is lean and purposeful. No unnecessary explanations of what GitHub issues are or how git works. The decision tree is expressed concisely with clear branching logic, and the bash examples contain only what's needed. | 3 / 3 |
Actionability | Provides concrete executable bash commands for closing/commenting on issues, clear invocation patterns for sub-skills (/triage-issue, /research, /write, /review-changes, /create-pr), and specific decision criteria at each branch point. The guidance is copy-paste ready where it needs to be. | 3 / 3 |
Workflow Clarity | The 8-step workflow is clearly sequenced with explicit decision points after triage (close/escalate/leave open/fix). Step 5 includes a feedback loop (fix and re-review until clean). Early exit points are clearly marked with 'Done.' labels, and the workflow handles error/edge cases (upstream issues, unverifiable URLs). | 3 / 3 |
Progressive Disclosure | The skill acts as a clean orchestration overview, delegating detailed work to composable sub-skills (/triage-issue, /research, /write, /review-changes, /create-pr). Each step is one level deep with clear signaling. The SKILL.md stays at the decision-tree level without inlining the details of each sub-skill. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
c0aa985
Table of Contents
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.