CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

67

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/prp-issue/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

60%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.

The body is concise and well-structured as a routing overview, but it delegates all substantive workflow detail to 'workflows/*.md' files that are not present in the bundle, leaving the references dangling and capping both actionability and progressive disclosure.

Suggestions

Ship the referenced workflow files (workflows/investigate.md and workflows/fix.md) so the body's one-level-deep references resolve to actual content.

Add explicit validation/feedback checkpoints for the side-effecting 'fix' phase (e.g., verify tests pass and the artifact exists before committing, self-review checklist before opening the PR) to lift workflow clarity.

Inline a minimal executable example of each phase (the artifact filename/structure written under $PRP_DIR/issues/, the branch-naming and commit conventions) so the body is actionable even before opening the workflow files.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence, routing on a verb via a compact table and noting side-effects in terse bullets; every line earns its place with no padded concept explanation.

3 / 3

Actionability

It gives a concrete routing table and an explicit 'strip the leading verb... follow the matching workflow file' instruction, but the substantive coding work is delegated to missing workflow files with no inline executable detail, so guidance is real but incomplete.

2 / 3

Workflow Clarity

The two-phase sequence and verb routing are clearly laid out, but a side-effecting 'fix' workflow (branch, commit, PR, self-review) has no validation/verification checkpoints in the body, and the guideline caps workflow clarity at 2 for destructive operations lacking feedback loops.

2 / 3

Progressive Disclosure

The body references 'workflows/investigate.md' and 'workflows/fix.md' for the real instructions, but no workflows/, references/, scripts/, or assets/ directories exist in the bundle, so the one-level-deep references are dangling with no destination to navigate to.

1 / 3

Total

8

/

12

Passed

Description

100%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.

The description is strong across all dimensions: it names concrete actions, provides explicit natural-language triggers via a 'Use when...' clause, uses third person, and carves out a distinct niche tied to a named invocation token.

DimensionReasoningScore

Specificity

Lists several concrete actions ('analyze codebase, create a plan, then code, PR, and self-review'), mirroring the score-3 anchor that rewards multiple specific actions rather than vague language.

3 / 3

Completeness

Explicitly answers both what the skill does and when to use it via a clear 'Use when...' clause enumerating several trigger conditions.

3 / 3

Trigger Term Quality

Covers natural trigger phrasings users would actually say ('investigate or triage a GitHub issue or bug report', 'fix an investigated issue', 'implement an issue fix'), plus the literal '$prp-issue' invocation token.

3 / 3

Distinctiveness Conflict Risk

The two-phase issue-investigation-and-fix niche, anchored to the '$prp-issue' invocation token, is distinct and unlikely to trigger for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
Wirasm/prp
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.