CtrlK
BlogDocsLog inGet started
Tessl Logo

pr-report

Produce a maintainer-grade PR or contribution report as HTML or Markdown. Use when asked to deeply review a PR, explain a design, compare systems, or prepare a merge recommendation.

67

Quality

81%

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

78%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 lean, well-structured skill body with a clearly sequenced workflow, an explicit verification step, and exemplary progressive disclosure — both bundle files are real, purposefully described, and referenced at the right moment. The remaining headroom is small: a feedback loop for failed verification, concrete acquisition commands in step 1, and trimming mild redundancy between the posture and workflow sections.

DimensionReasoningScore

Conciseness

Efficient bullet-style body that assumes Claude's competence and explains nothing the model already knows; every section carries task-specific guidance. Not 5 because there is minor trimmable redundancy (the "Default posture" bullets reappear nearly verbatim as workflow steps, and the "Useful recommendation buckets" overlap the recommendation options); not 3 because there is no real over-explanation or padding.

4 / 5

Actionability

Concrete, executable guidance throughout — an 8-step workflow, a numbered report structure, explicit recommendation buckets ("merge as-is / merge after specific redesign / salvage specific pieces"), and a verification checklist; absence of code is acceptable for this instruction-only skill. Not 5 because step 1 ("acquire and frame the target") gives no concrete commands for obtaining a diff or branch, and no example finding format is shown; not 3 because the guidance is specific and directly executable rather than high-level hints.

4 / 5

Workflow Clarity

A clearly sequenced 8-step workflow with explicit numbered order and a terminal "Verify before handoff" checklist (artifact path exists, findings match code, forbidden strings absent, tests skipped declared). Not 5 because there is no feedback loop stating what to do when verification fails (fix and re-verify); not 3 because an explicit validation checkpoint is present, not missing or implicit.

4 / 5

Progressive Disclosure

Verified against the actual bundle: both referenced files (references/style-guide.md, assets/html-report-starter.html) exist, are described with purpose ("for visual direction and report presentation rules", "for a reusable standalone HTML/CSS starter"), and are pointed to at exactly the right point in the workflow ("Before building from scratch, read references/style-guide.md"). References are one level deep — the style guide references only the starter asset, not further nested files — and the body stays a proper overview. Matches the 5 anchor; no organization gaps to justify 4.

5 / 5

Total

17

/

20

Passed

Description

83%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 well-formed description with explicit what and when clauses and concrete trigger phrases. It sits just below the top anchors on specificity and trigger coverage because it misses common synonyms (pull request, code review, should I merge) that its own body lists, and leans slightly on the subjective qualifier "maintainer-grade".

DimensionReasoningScore

Specificity

Lists several specific actions — "deeply review a PR, explain a design, compare systems, or prepare a merge recommendation" plus output formats ("as HTML or Markdown") — with minor gaps. Not 5 because "maintainer-grade" is subjective and the coverage of report outputs is thin; not 3 because it goes well beyond naming the domain with 1-2 actions.

4 / 5

Completeness

Explicitly answers both: what ("Produce a maintainer-grade PR or contribution report as HTML or Markdown") and when ("Use when asked to deeply review a PR, explain a design, compare systems, or prepare a merge recommendation") with concrete trigger phrases. Matches the 5 anchor exactly; the 'when' clause is fully explicit, not merely present.

5 / 5

Trigger Term Quality

Good natural trigger phrases: "deeply review a PR", "explain a design", "compare systems", "prepare a merge recommendation", "contribution". Not 5 because common synonyms like "pull request", "code review", or "should I merge this" (which the body itself lists) are missing; not 3 because keyword coverage is solid rather than partial.

4 / 5

Distinctiveness Conflict Risk

A clear niche (PR/contribution reports and merge recommendations) distinct from most skills, though "deeply review a PR" and "compare systems" carry minor overlap risk with generic code-review or design-analysis skills. Not 5 because those broader triggers could pull in adjacent skills; not 3 because the core purpose is unmistakable.

4 / 5

Total

17

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
paperclipai/paperclip
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.