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]

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Risky

Do not use without reviewing

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable and its six-phase workflow is clearly sequenced with strong validation and error recovery. Its weaknesses are repetition that hurts token efficiency and a monolithic structure with no progressive disclosure of the large embedded prompt templates.

Suggestions

De-duplicate the token-resolution and spawn-config blocks into a single shared section referenced by each phase to improve conciseness.

Extract the two large sub-agent prompt templates into reference files (e.g. references/fix-agent-prompt.md, references/review-agent-prompt.md) and link to them, moving from a monolith toward one-level-deep progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body avoids explaining concepts Claude already knows, but it is verbose through repetition — token resolution appears three times, the spawn-config block is restated three times, and 'do NOT use the gh CLI' is repeated several times — so it is 'mostly efficient but could be tightened' rather than fully lean.	2 / 3
Actionability	Guidance is fully executable: concrete curl invocations with exact headers and endpoints, git/jq commands, and complete JSON request payloads for PR creation and comment replies, matching the copy-paste-ready score-3 anchor.	3 / 3
Workflow Clarity	Six phases are explicitly sequenced with validation checkpoints (dirty-tree check, token validity, existing-PR, branch, claim-based in-progress tracking, confidence check) and clear error-recovery feedback loops, satisfying the score-3 anchor for batch operations.	3 / 3
Progressive Disclosure	The skill is a single 870-line monolith with no bundle references; the repeated sub-agent prompt templates are content that could be split into separate files, fitting the score-2 'content that should be separate is inline' anchor rather than the score-3 well-signaled reference structure.	2 / 3
	Total	10 / 12 Passed

Description

82%

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 specific, action-oriented, and distinct, with good natural trigger terms. Its only gap is the absence of an explicit 'Use when...' trigger clause, which caps completeness at 2.

Suggestions

Add an explicit trigger clause such as 'Use when the user wants to automatically fix GitHub issues or address PR review comments' to lift completeness to 3.

Trim the long flag list from the description into the body, keeping the description focused on capabilities and trigger terms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments' — matching the score-3 anchor of multiple specific actions rather than a single named domain.	3 / 3
Completeness	The 'what' is clearly stated, but there is no explicit 'Use when...' clause; the 'Usage: /gh-issues ...' line documents invocation syntax rather than trigger scenarios, so per the guidelines completeness is capped at 2.	2 / 3
Trigger Term Quality	Natural terms users would say are well covered — 'GitHub issues', 'PRs', 'review comments', 'fixes' — unlike the jargon-only score-1 example; it is not the score-2 'missing common variations' case because the core vocabulary is complete.	3 / 3
Distinctiveness Conflict Risk	The niche is distinct — parallel sub-agents that auto-fix GitHub issues and handle PR review comments — making accidental triggering of other skills unlikely, fitting the score-3 'clear niche' anchor.	3 / 3
	Total	11 / 12 Passed

Validation

81%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (871 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

	Total	13 / 16 Passed

Repository: trpc-group/trpc-agent-go
Commit: 737835b

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.