gh-issues
Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments. Usage: /gh-issues [owner/repo] [--label bug] [--limit 5] [--milestone v1.0] [--assignee @me] [--fork user/repo] [--watch] [--interval 5] [--reviews-only] [--cron] [--dry-run] [--model glm-5] [--notify-channel -1002381931352]
72
61%
Does it follow best practices?
Impact
100%
2.00xAverage score across 3 eval scenarios
Risky
Do not use without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/gh-issues/SKILL.mdQuality
Discovery
67%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 effectively communicates specific capabilities around GitHub issue processing and PR automation, establishing a clear niche. However, it lacks an explicit 'Use when...' clause, and the bulk of the description is consumed by CLI flag documentation rather than natural trigger terms that would help Claude select this skill appropriately.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to automatically fix GitHub issues, create pull requests from issues, or monitor PR review feedback.'
Replace or supplement the verbose CLI flag listing with natural language trigger terms like 'bug fixes', 'pull requests', 'code review comments', 'automated issue resolution', 'GitHub automation'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: fetch GitHub issues, spawn sub-agents to implement fixes, open PRs, monitor PR review comments, and address review comments. These are clear, actionable capabilities. | 3 / 3 |
Completeness | The 'what' is well covered (fetch issues, implement fixes, open PRs, monitor reviews). However, there is no explicit 'Use when...' clause or equivalent trigger guidance — the 'Usage:' line describes CLI syntax, not when Claude should select this skill. | 2 / 3 |
Trigger Term Quality | Contains good keywords like 'GitHub issues', 'PRs', 'PR review comments', 'fixes', but the description is heavily dominated by CLI flag documentation rather than natural language terms users would say. Missing natural phrases like 'bug fixes', 'pull requests', 'code review'. | 2 / 3 |
Distinctiveness Conflict Risk | Very distinct niche: automated GitHub issue triage with sub-agent spawning, PR creation, and review monitoring. The specific command '/gh-issues' and detailed flags make it clearly distinguishable from other skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
55%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a highly actionable and well-structured workflow with excellent validation checkpoints and error handling across all phases. However, it suffers severely from verbosity and lack of progressive disclosure — the ~600+ line monolithic document repeats patterns (especially GH_TOKEN resolution and curl headers), embeds full sub-agent prompt templates inline, and includes details that could be split into referenced files. The content would benefit enormously from extracting sub-agent templates and Phase 6 into separate files.
Suggestions
Extract the two sub-agent prompt templates (fix agent and review handler agent) into separate files (e.g., TEMPLATES/fix-agent.md and TEMPLATES/review-agent.md) and reference them from the main skill.
Consolidate the GH_TOKEN resolution logic into a single section referenced by name rather than repeating the full resolution steps 4+ times throughout the document.
Split Phase 6 (PR Review Handler) into a separate file since it functions as an independent workflow triggered by --reviews-only, and reference it from the main skill.
Remove explanations Claude can infer, such as how to parse HTTPS vs SSH git URLs, what HTTP 401/403 means, and basic jq usage patterns — replace with concise one-liners.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | This skill is extremely verbose at ~600+ lines. While the complexity of the task justifies significant length, there is substantial redundancy — GH_TOKEN resolution is repeated 4+ times across the main body and sub-agent prompts, the same curl patterns are shown repeatedly, and explanations that Claude could infer (like extracting owner/repo from git URLs) are spelled out in excessive detail. | 1 / 3 |
Actionability | The skill provides fully executable curl commands, git commands, and specific API endpoints with exact parameters. Code examples are copy-paste ready with clear variable substitution patterns. Sub-agent prompts are complete and self-contained with concrete step-by-step instructions. | 3 / 3 |
Workflow Clarity | The 6-phase workflow is clearly sequenced with explicit validation checkpoints throughout — Phase 4 has 7 pre-flight checks including PR existence, branch existence, claim-based tracking, and token validation. Error handling is specified for each failure mode with specific error messages and recovery paths (stop vs loop back in watch mode). | 3 / 3 |
Progressive Disclosure | The entire skill is a monolithic wall of text with no references to external files. The sub-agent prompt templates alone account for hundreds of lines that could be in separate template files. The review handler (Phase 6) is essentially a second skill embedded inline. There is no separation of overview from detail — everything is in one massive document. | 1 / 3 |
Total | 8 / 12 Passed |
Validation
63%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 7 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (866 lines); consider splitting into references/ and linking | Warning |
metadata_version | 'metadata.version' is missing | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 7 / 11 Passed | |
- Repository
- qsimeon/openclaw-engaging
- Commit
4467e04
- 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.