CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

pr-review

One-shot read-only review of a GitHub PR: dispatches the `pr-reviewer` agent once and reports its verdict and findings without touching your code. Also writes maintainer relevance rules via `/pr-review remember <fact>`; invoke with /pr-review.

Quality

82%

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

88%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.

The body is an exemplar of operational instruction: fully executable commands and dispatch prompts, an explicitly sequenced workflow with validation and fallback paths for every failure mode, and rationale properly pushed to a one-level-deep reference file. Its only weaknesses are moderate repetition of the hard rules across sections and a bundle whose rules/remember.md, README.md, and assets/ files are not wired to the SKILL.md links from the shipped copy.

DimensionReasoningScore

Conciseness

The body is dense and operational — exact commands, paths, and dispatch formats with rationale offloaded to references/design-rationale.md — assuming Claude's competence throughout, matching the 4 anchor's "efficient; minor instances of over-explanation that could be trimmed". It is not a 5 because the read-only rule, the capability-vs-name dispatch test, and the one-dispatch rule are each restated two to three times (body, examples, Hard rules), and not a 3 because there is no concept-explaining padding — every repeat is a brief hard-rule restatement rather than unnecessary explanation.

4 / 5

Actionability

Guidance is fully executable: copy-paste bash (the prepare-review.mjs pipeline with jq, telemetry, and date stamps), verbatim dispatch prompts with a resolved INTENT_WAIT line, exact stop/skip messages, a RIGHT/WRONG dispatch pair, and a fill-in report template. This matches the 5 anchor's "fully executable; copy-paste ready code or commands; specific examples cover the common cases" — the hybrid, in-context, pass-2, and fallback branches are each concretely specified.

5 / 5

Workflow Clarity

The sequence is explicit (Step 0 parse → Step 1 resolve PR → Step 2 dispatch → Step 3 report) with validation checkpoints and error-recovery feedback loops throughout: prepare exit 2 "report prepare's message and stop", "If prepare exits non-zero, dispatch `pr-reviewer` alone with no `--context`", the no-PR one-line stop, the Agent0 prepared/unprepared/neither triage, and the dispatch-unavailable skip — plus a Hard rules checklist. This matches the 5 anchor; the read-only nature of the skill means the destructive-operation cap does not apply.

5 / 5

Progressive Disclosure

Good structure: a Contents TOC, rationale split cleanly into the one-level-deep references/design-rationale.md (well signaled: "Why each choice below exists"), and clearly scoped sections — matching the 4 anchor's "most content is appropriately placed; references mostly clear; minor organization gaps". The gaps keeping it from 5: the body's relative links to `./rules/remember.md` and `./README.md` are dangling in this bundle (no rules/ or README.md alongside SKILL.md), and the six assets/ files (lenses-finding, lenses-flow, review-levers) are never referenced from the body — the skill explains the installed-copy resolution, but the bundle as shipped has orphaned assets and two dead links.

4 / 5

Total

18

/

20

Passed

Description

70%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.

The description is concrete and distinctive, clearly stating both operations (one-shot read-only review and `remember` rule-writing) with specific actions, but it lacks any explicit "when to use this" trigger guidance and slips into second person ("your code"). Adding a "Use when..." clause and recasting to third person would lift completeness and specificity.

Suggestions

Add an explicit trigger clause such as "Use when the user asks to review a pull request/PR, get a review verdict, or check PR findings without applying changes" — its absence currently caps completeness at 3.

Recast "without touching your code" in third person (e.g., "without modifying the working tree") to remove the second-person voice penalty on specificity.

Include the spelled-out synonym "pull request" alongside "GitHub PR" to broaden natural trigger-term coverage.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — "dispatches the `pr-reviewer` agent once", "reports its verdict and findings", "writes maintainer relevance rules via `/pr-review remember`" — with comprehensive coverage of both operations, which matches the 5 anchor; however, the second-person phrasing "without touching your code" violates the third-person-voice rule, reducing the score by 1. It is not a 3 because the actions are numerous, distinct, and concrete rather than a bare 1-2 action list.

4 / 5

Completeness

The "what" is clear and explicit (one-shot read-only review via a single agent dispatch, plus a memory-write operation), but there is no "Use when..." clause or equivalent explicit trigger guidance — "invoke with /pr-review" states how, not when, so the completeness cap of 3 applies. It is not a 4 because the "when" is only weakly implied, and not a 2 because the "what" is fully concrete.

3 / 5

Trigger Term Quality

Natural trigger terms are present — "review of a GitHub PR", "read-only", "verdict and findings", "remember" — covering what a user would say when asking for a PR review, but common synonyms like the spelled-out "pull request" and phrasings like "review my PR" are missing. Good coverage with a few natural terms absent fits the 4 anchor; it is not 5 because the synonym set is not comprehensive, and not 3 because the core terms users actually say (review, PR, findings) are all there.

4 / 5

Distinctiveness Conflict Risk

The description carves out a clear niche — "One-shot read-only review of a GitHub PR" — with distinct triggers (dispatch-once, read-only, verdict reporting, remember) that separate it from apply/fix/loop-style commands, matching the 5 anchor's "clear niche with distinct triggers; minimal conflict risk". It is not a 4 because nothing in the phrasing overlaps meaningfully with other skills' triggers.

5 / 5

Total

16

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

relative_links

Relative link issues: 3 missing, 4 suspicious

Warning

Total

14

/

16

Passed

Repository

mthines/agent-skills

Path

skills/quality/pr-review/SKILL.md

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.