CtrlK
BlogDocsLog inGet started
Tessl Logo

pr-description

Write the body of a pull request in constructorfabric/insight — the shape a reviewer can decide from in under 30 seconds: bold inline labels for Why / What changed / Out of scope / Verified, a bold-led line per decision the diff cannot show, screenshots for anything visual, and a word cap per block so a three-line fix does not read as a document. Use whenever a PR body is being written or rewritten: 'write the PR description', 'open a PR for this branch', 'the description is too long', 'update the PR body', or right before `gh pr create` and before marking a draft ready. Also use when reviewing someone's description for what it is missing. The repo is PUBLIC and AGENTS.md bans production-derived information from PR bodies, so every number in a description comes from a local stand, a fixture, or a test run. It owns the prose only — `file-bug-insight` owns issues, `drive-ui` owns capturing the screenshots this skill asks for.

72

Quality

91%

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

82%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 tight, highly actionable body that assumes Claude's competence and supplies copy-paste commands, exact budgets, and worked examples rather than concept explanations. It is well-structured but slightly longer than necessary and lacks an explicit error-recovery loop in its workflow.

Suggestions

Trim the Common mistakes table to the highest-value rows or fold the rarest mistakes into their owning section, to reduce body length without losing the actionable fixes.

Add an explicit validate→fix→retry checkpoint in the Workflow (e.g., after drafting, re-read the body against the Shape and per-block caps before applying) to reach the score-5 workflow anchor.

Consider moving the Optional headings list and the assets-branch image recipe into a short reference section or file so the core Shape stays scannable, improving progressive disclosure toward one-level-deep references.

DimensionReasoningScore

Conciseness

Lean and free of concepts Claude already knows (no 'what is a PR/git' padding), but the Common mistakes table and Optional headings list add length that is useful yet could be trimmed slightly; mostly efficient with minor over-explanation.

4 / 5

Actionability

Fully executable guidance throughout: copy-paste git commands for the assets branch, `gh pr edit <n> --body-file <file>` / `gh pr create --body-file`, `gh pr diff <n>`, exact word budgets per block, and a concrete worked decision example — covers the common cases copy-paste ready.

5 / 5

Workflow Clarity

The Workflow section gives a clear numbered sequence with concrete commands per step and an explicit 'show it, and wait' user checkpoint, but it lacks a formal validate→fix→retry error-recovery loop; minor validation gap relative to the score-5 anchor.

4 / 5

Progressive Disclosure

Well-organized into clearly labeled sections (Shape, The parts, Size, Optional headings, Images, Workflow, Common mistakes) with no nested references and an appropriately scoped body; no bundle files exist to verify, and the single-file structure is mostly appropriate though the skill exceeds the 50-line simple-skill exception.

4 / 5

Total

17

/

20

Passed

Description

100%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.

An exemplary description: third-person voice, concrete capabilities, comprehensive natural trigger phrases, and explicit what/when coverage, all scoped to a distinct niche with sibling-skill boundaries stated. It does not pad or over-claim.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Write the body of a pull request', 'bold inline labels for Why / What changed / Out of scope / Verified', 'screenshots for anything visual', and 'word cap per block' — with comprehensive coverage of the skill's mechanics.

5 / 5

Completeness

Explicitly answers both what (the shape a reviewer can decide from in under 30 seconds with bold labels, decisions, screenshots, word caps) and when ('Use whenever a PR body is being written or rewritten' with concrete trigger phrases).

5 / 5

Trigger Term Quality

Comprehensive natural trigger coverage quoted directly: 'write the PR description', 'open a PR for this branch', 'the description is too long', 'update the PR body', plus `gh pr create` and 'marking a draft ready' — phrases a user would naturally say.

5 / 5

Distinctiveness Conflict Risk

Carves a clear niche — PR prose for constructorfabric/insight — and explicitly disambiguates from sibling skills: '`file-bug-insight` owns issues, `drive-ui` owns capturing the screenshots', giving minimal conflict risk.

5 / 5

Total

20

/

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.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

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

Warning

relative_links

Relative link issues: 1 suspicious

Warning

Total

14

/

16

Passed

Repository
constructorfabric/insight
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.