CtrlK
BlogDocsLog inGet started
Tessl Logo

prp-maintainer-triage

Quickly triages a contributor pull request or reported issue against repository policy and lightweight evidence without full review or root-cause analysis. Publishes the disposition to GitHub, and on a contributor pull request that links no issue it may open a tracking issue and close the pull request. Use when the user asks to "triage this contributor PR", "sanity-check this PR", "triage this issue", "reproduce this reported issue", "check whether this bug still exists", or invokes /prp-maintainer-triage.

77

Quality

97%

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

SKILL.md
Quality
Evals
Security

Quality

Content

100%Weight 40%Scale 1-5

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

An exemplary dispatcher-style SKILL.md: a lean router that resolves the target deterministically, routes to exactly one well-scoped workflow file, and stays out of the way. The heavy logic is appropriately delegated to two real, well-structured reference files whose destructive GitHub operations carry explicit validation, read-back verification, and idempotency safeguards.

DimensionReasoningScore

Conciseness

The 24-line body is a pure router — 'Resolve one GitHub pull request or issue, then load only its lightweight triage workflow' — where every line is routing logic, a disambiguation rule, a boundary, or a resource pointer. This matches the 5 anchor ('lean and efficient; every token earns its place'), not 4, because there are no instances of over-explanation to trim: even the repeated prohibitions ('Do not read the issue workflow', 'Do not triage both kinds in one invocation') are single-clause, load-bearing routing constraints.

5 / 5

Actionability

Fully actionable instruction-only guidance: exact input handling ('$ARGUMENTS (if absent, use the target named in the conversation)'), a deterministic resolution rule ('For a bare number, resolve a pull request with that number first, then an issue'), an explicit fallback ('ask the user which PR or issue to triage'), and exact file paths with execution instructions ('read `references/pr-triage.md` completely, then execute it end to end'). This matches the 5 anchor; not 4 because every branch (bare number, unresolvable, PR, issue) has a specific, executable instruction with no gaps.

5 / 5

Workflow Clarity

The routing sequence is clearly ordered (resolve input → determine type from GitHub metadata → read exactly one workflow file → execute end to end) with an explicit ambiguity checkpoint ('If no single target can be resolved, ask the user which PR or issue to triage'). The destructive GitHub operations are delegated to workflow files that contain explicit validation and feedback loops ('Read back every changed label, comment, or state before claiming it succeeded', idempotent publication, refresh-and-recheck if the head changed, create-issue-before-close ordering), so the missing-validation cap does not apply, and the simple-skill exception holds since the single routing action is unambiguous. Matches the 5 anchor; not 4 because checkpoints and error-recovery loops are explicit rather than merely mostly present.

5 / 5

Progressive Disclosure

A lean overview routing to two one-level-deep references, both of which exist in the bundle (references/pr-triage.md, references/issue-triage.md), with navigation signaled twice — bold-labeled routing bullets and a Resources section with one-line descriptions ('lightweight contributor PR policy and reviewability triage'). Content is appropriately split per target type with no nested bundle references (files named inside the workflows are repository inputs, not bundle files). Matches the 5 anchor (clear overview, well-signaled one-level-deep references, easy navigation); not 4 because there are no organization gaps.

5 / 5

Total

20

/

20

Passed

Description

96%Weight 40%Scale 1-5

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: concrete third-person actions covering the entire triage-to-publication workflow, explicit exclusions that delineate it from heavier workflows, and an explicit 'Use when' clause with six natural trigger phrases spanning both PR and issue targets. The only weakness is mild trigger overlap with debugging/review skills for reproduction-style requests.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions covering the full workflow — 'triages a contributor pull request or reported issue against repository policy and lightweight evidence', 'Publishes the disposition to GitHub', 'may open a tracking issue and close the pull request' — plus explicit exclusions ('without full review or root-cause analysis'), all in third person. This matches the 5 anchor (comprehensive coverage of concrete actions) rather than 4, since no part of the workflow is left uncovered.

5 / 5

Completeness

Explicitly answers both 'what' (triage against policy and lightweight evidence, publish disposition, open tracking issue, close PR, without full review or root-cause analysis) and 'when' via an explicit 'Use when the user asks to…' clause with concrete quoted trigger phrases. This matches the 5 anchor exactly; it is not 4 because the 'when' is not merely present but fully explicit with multiple concrete phrases.

5 / 5

Trigger Term Quality

Includes six concrete natural trigger phrases — 'triage this contributor PR', 'sanity-check this PR', 'triage this issue', 'reproduce this reported issue', 'check whether this bug still exists', '/prp-maintainer-triage' — covering both target types, a synonym variation, and the slash command. This matches the 5 anchor (comprehensive natural-term coverage including synonyms); it is not 4 because no obvious natural phrasing for this domain is missing.

5 / 5

Distinctiveness Conflict Risk

The niche is clear and explicitly bounded away from review and debugging ('without full review or root-cause analysis'), but triggers like 'reproduce this reported issue', 'check whether this bug still exists', and 'sanity-check this PR' are natural phrasings that debugging or code-review skills could also claim — minor overlap with closely related skills, matching the 4 anchor. Not 5 because a few triggers contend with neighboring skills; not 3 because the explicit boundary keeps conflict narrow rather than broad.

4 / 5

Total

19

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

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.