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]
79
Quality
72%
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 ./openclaw/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 automation and PR workflows, with good distinctiveness. However, it lacks an explicit 'Use when...' clause and relies too heavily on CLI flag documentation rather than natural language trigger terms that users would actually say.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to automate GitHub issue fixes, batch process bugs, or automatically respond to PR reviews.'
Include more natural language trigger terms users would say, such as 'fix bugs automatically', 'batch PR creation', 'automate pull requests', 'GitHub automation'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Fetch GitHub issues', 'spawn sub-agents to implement fixes', 'open PRs', 'monitor and address PR review comments'. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers 'what' (fetch issues, implement fixes, open PRs, monitor reviews), but lacks an explicit 'Use when...' clause. The usage syntax implies when but doesn't explicitly state trigger conditions. | 2 / 3 |
Trigger Term Quality | Contains relevant keywords like 'GitHub issues', 'PRs', 'PR review comments', 'bug', 'milestone', 'assignee', but focuses heavily on CLI flags rather than natural language terms users would say (e.g., 'fix bugs', 'pull requests', 'code review'). | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific GitHub workflow focus, sub-agent spawning, and the unique /gh-issues command. Unlikely to conflict with other skills due to its specialized automation pipeline. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
77%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 sophisticated orchestration skill with excellent actionability and workflow clarity. The multi-phase structure with explicit validation checkpoints, parallel sub-agent spawning, and review handling demonstrates expert-level design. However, the document's length and lack of progressive disclosure to external files makes it harder to navigate, and some redundancy (repeated token setup, verbose tables) could be trimmed.
Suggestions
Extract the sub-agent task prompts (fix agent and review handler) into separate reference files (e.g., FIX_AGENT_PROMPT.md, REVIEW_HANDLER_PROMPT.md) and reference them from the main skill
Consolidate the GH_TOKEN resolution logic into a single reusable section at the top, then reference it instead of repeating the full setup in multiple places
Consider moving the detailed flag table to a separate REFERENCE.md file, keeping only essential flags inline
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but includes some redundant explanations (e.g., repeated GH_TOKEN setup instructions across multiple sections, verbose flag tables). Some sections could be tightened, though most content is necessary for the complex orchestration task. | 2 / 3 |
Actionability | Excellent actionability with fully executable curl commands, complete git commands, specific API endpoints, and copy-paste ready sub-agent prompts. Every step includes concrete, runnable code rather than pseudocode or vague descriptions. | 3 / 3 |
Workflow Clarity | Outstanding workflow clarity with 6 clearly numbered phases, explicit validation checkpoints (pre-flight checks in Phase 4), error handling paths, and feedback loops (confidence check, test-fix-retry). The claim-based tracking and cursor system for cron mode show sophisticated state management. | 3 / 3 |
Progressive Disclosure | The skill is a monolithic ~600-line document with no references to external files. While internally well-organized with clear headers, the sub-agent prompts and detailed API examples could be split into separate reference files to improve scannability. | 2 / 3 |
Total | 10 / 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
- trpc-group/trpc-agent-go
- Commit
50ef2f3
- 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.