CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

prepare-pr-review

Prepare a plain-language PR review briefing from a GitHub pull request URL or number. Use when the user says "help me review this PR", "summarize this PR for review", "what does this PR do", or wants the reason, systems involved, changes, risks, CI state, and questions needed before reviewing a pull request.

Quality

88%

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

81%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.

A high-quality instruction-only skill: a precisely sequenced read-only workflow with validation checkpoints, concrete output templates and examples, and a pre-response quality checklist. The minor gaps are the absence of specific `gh` subcommands, slight redundancy between the briefing-contents list and the Output format section, and limited offloading of the long output-format spec.

Suggestions

Add one or two concrete gh commands (e.g., `gh pr view --json ...`, `gh pr diff`) to the "Establish the PR and intent" step so the data-gathering step is copy-paste executable.

Merge or cross-reference the "What the briefing must answer" list with the Output format section, which largely restates the same eight points, to trim duplicate guidance.

Consider moving the detailed Output format section's worked examples (diagram, Before/After, checklist samples) into a references file to keep SKILL.md as a lean overview.

DimensionReasoningScore

Conciseness

The body is dense, prescriptive, and free of padding or explanations of concepts Claude already knows (it never explains what a PR or CI is). It is not anchor 5 because a few areas could be tightened — the "What the briefing must answer" list partially restates the Output format section, and some clarity rules are near-duplicates of workflow guidance — but these are minor instances of over-explanation, matching anchor 4.

4 / 5

Actionability

For an instruction-only skill, the guidance is highly concrete: exact steps ("Pin the review to the PR's base and head commits", "Use `gh` for GitHub data"), worked examples of the Before/After block, a request-flow diagram, and sample checklist questions. It falls just short of anchor 5 because no specific `gh` subcommands or copy-paste-ready commands are given, leaving minor gaps.

4 / 5

Workflow Clarity

A clear 7-step sequence with explicit validation checkpoints: "Confirm both resolve and the PR diff is non-empty", the independent-pass-before-reading-comments ordering, disagreement handling ("show the disagreement instead of silently choosing one"), and a final Quality check checklist. This matches anchor 5's clear sequence with explicit validation steps and checklists; the read-only nature means no destructive-operation feedback loop is required.

5 / 5

Progressive Disclosure

The skill is a single well-organized file with clear, non-nested sections and no buried or dangling references (no bundle files exist, and none are referenced). It is not anchor 5 because at ~270 lines content such as the detailed Output format specification could plausibly be offloaded to a reference file, but structure and placement are otherwise good, matching anchor 4.

4 / 5

Total

17

/

20

Passed

Description

91%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: it names a concrete deliverable, lists the briefing's contents, and gives explicit quoted trigger phrases in third person. The only weaknesses are minor — a composite single action rather than a list of distinct actions, and slight overlap risk with general code-review skills on the "review this PR" trigger.

DimensionReasoningScore

Specificity

The description states a concrete action ("Prepare a plain-language PR review briefing from a GitHub pull request URL or number") and enumerates concrete deliverables ("the reason, systems involved, changes, risks, CI state, and questions"), which lists several specific outcomes. It stops short of anchor 5 because this is one composite action with its contents rather than multiple distinct concrete actions, and it is above anchor 3 because coverage of the deliverables is specific and broad.

4 / 5

Completeness

It clearly answers "what" ("Prepare a plain-language PR review briefing") and "when" with an explicit "Use when the user says..." clause carrying concrete trigger phrases, exactly matching the anchor-5 structure. Anchor 4 is surpassed because the trigger guidance is explicit and quoted rather than merely present.

5 / 5

Trigger Term Quality

It quotes the exact natural phrases users would say — "help me review this PR", "summarize this PR for review", "what does this PR do" — and includes both "PR" and "pull request" synonyms. This comprehensively covers natural terms including synonyms, matching anchor 5; no common user variation is conspicuously missing.

5 / 5

Distinctiveness Conflict Risk

The niche is distinct (a read-only plain-language briefing rather than performing a review), with deliverables that separate it from generic summarization skills. It is not anchor 5 because triggers like "help me review this PR" could also naturally invoke a closely related code-review skill, creating minor overlap risk.

4 / 5

Total

18

/

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

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository

Agenta-AI/agenta

Path

.agents/skills/prepare-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.