prp-issue

Investigate a GitHub issue and implement the fix - analyze codebase, create a plan, then code, PR, and self-review. Use when the user wants to investigate or triage a GitHub issue or bug report, fix an investigated issue, implement an issue fix, or invokes /prp-issue.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/prp-issue/SKILL.md

Quality

Content

65%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.

A clean, token-efficient router with a clear two-phase structure, but it delegates its substantive steps to workflow files that are absent from the bundle, and its side-effecting fix phase lacks any validation checkpoint.

Suggestions

Ship the referenced workflow files (workflows/investigate.md, workflows/fix.md) or inline their key steps — the body currently routes to files that aren't in the bundle, breaking navigation and leaving the actual investigate/fix guidance unactionable.

Add explicit validation/verification checkpoints to the side-effecting fix workflow (e.g., confirm the investigation artifact exists and tests pass before committing and opening a PR) so workflow_clarity isn't capped at 2 for destructive operations.

Include a concise inline summary of the concrete investigate and fix steps (analyze → plan → code → PR → self-review) so the skill remains actionable even before the referenced files are loaded.

Dimension	Reasoning	Score
Conciseness	The body is lean — "Two-phase issue workflow: investigate an issue into an implementation artifact, then fix it from that artifact" — with an executable resolver block and no explanations of concepts Claude already knows; every section earns its place.	3 / 3
Actionability	Routing is concrete ("strip the leading verb... follow the matching workflow file end-to-end") but defers the actual investigate/fix steps to workflows/investigate.md and workflows/fix.md, which are not present in the bundle, so the guidance dead-ends.	2 / 3
Workflow Clarity	The two-phase sequence and routing are clear, but "fix is side-effecting: it creates a branch, commits, opens a PR" with no validation/verification checkpoint, so the rubric cap of 2 for destructive ops without validation applies.	2 / 3
Progressive Disclosure	The routing table signals one-level-deep references cleanly (workflows/investigate.md, workflows/fix.md), but those files do not exist in the bundle, so the well-designed navigation is broken in practice.	2 / 3
	Total	9 / 12 Passed

Description

92%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.

A strong description that clearly states concrete actions and an explicit 'Use when' trigger set with natural keywords. Its only weakness is moderate overlap risk between its generic issue-fixing triggers and other coding/PR skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "analyze codebase, create a plan, then code, PR, and self-review" — matching the anchor for several specific concrete actions rather than a domain with only some actions (level 2).	3 / 3
Completeness	Explicitly answers both what ("Investigate a GitHub issue and implement the fix - analyze codebase...") and when ("Use when the user wants to investigate or triage..."), with a present 'Use when' clause so no cap applies.	3 / 3
Trigger Term Quality	Covers natural terms a user would say — "investigate or triage a GitHub issue or bug report" and the "/prp-issue" invocation — giving good coverage of common phrasings, not just jargon.	3 / 3
Distinctiveness Conflict Risk	The "/prp-issue" command is distinct, but natural-language triggers like "fix an investigated issue, implement an issue fix" overlap with generic bug-fix/PR skills, so it could still trigger for the wrong skill.	2 / 3
	Total	11 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: Wirasm/prp
Path: .claude/skills/prp-issue/SKILL.md
Commit: 1142738

Reviewed: 11 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.