CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

pr

Use when writing a PR body.

Quality

64%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/pr/SKILL.md

The canonical home for this skill is pr in mattpocock/skills

SKILL.md
Quality
Evals
Security

Quality

Content

75%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 a tight, actionable template with strong worked examples and clear section-by-section guidance; it respects token budget and assumes Claude's competence. The main weaknesses are a dangling GLOSSARY.md reference, conceptual guidance in the Merge Danger section, and a visualization catalog that could be split out for progressive disclosure.

Suggestions

Resolve the 'GLOSSARY.md' reference — either ship it in the bundle (e.g., references/glossary.md) or drop the instruction, since it currently points to a nonexistent file.

Make the Merge Danger section more actionable with a concrete example (e.g., a filled-in door and blast-radius line) to match the specificity of the Summary section.

Consider moving the visualization example catalog (pseudocode/call-tree/component-tree/file-tree/Mermaid/diff variants) into a references/ file, keeping SKILL.md as a lean overview.

DimensionReasoningScore

Conciseness

The body is lean and imperative ('Skip all preambles and keep prose brief', 'Pick the smallest view that makes the key point clear') with every example earning its place. Minor over-explanation of concepts Claude likely knows (one-way/two-way doors, blast radius) keeps it just below anchor 5.

4 / 5

Actionability

A copy-paste-ready template plus concrete worked examples for each visual type (pseudocode, call tree, component tree, file tree, Mermaid, and four diff shapes) covers the common cases. Minor gaps remain: vague placeholders like '<one-word description>' and conceptual rather than executable guidance in the Merge Danger section.

4 / 5

Workflow Clarity

The single task (fill in the template) is unambiguous with a clear template-then-section-guidance structure, and no destructive operations require validation checkpoints. It falls short of anchor 5 because evidence gathering and visual selection are guided by principle rather than an explicit sequence or checklist.

4 / 5

Progressive Disclosure

The single-file body (~170 lines) is well organized into Summary, Evidence, and Merge Danger sections with clear subsections, and no bundle files exist to navigate. Minor gaps: the body references 'GLOSSARY.md' which is not present in the bundle, and the extensive visualization example catalog could arguably live in a reference file.

4 / 5

Total

16

/

20

Passed

Description

40%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 concise and has a clear trigger, but it is essentially only a trigger: it never states what the skill does. Adding a one-line capability statement (e.g., a structured PR-body template with Summary, Evidence, and Merge Danger sections) and synonyms like 'pull request description' would raise specificity, completeness, and trigger coverage.

Suggestions

Add a 'what' statement before the trigger, e.g., 'Write PR bodies from a structured template with Summary, Evidence, and Merge Danger sections. Use when writing a PR or pull request description.'

Include natural trigger synonyms such as 'pull request', 'PR description', and 'drafting a PR' to broaden trigger term coverage.

State the concrete capabilities (choosing the right diagram/diff visual, before/after evidence, blast-radius assessment) so the description is not trigger-only.

DimensionReasoningScore

Specificity

The description 'Use when writing a PR body' names the domain (PR body writing) but contains no concrete actions or capability statements beyond the trigger itself. It does not reach anchor 3 because no specific action like 'draft', 'structure', or 'fill in a template' is enumerated.

2 / 5

Completeness

Only the 'when' clause is present ('Use when writing a PR body'); the 'what' — what the skill actually does, such as providing a structured template with Summary, Evidence, and Merge Danger sections — is entirely absent. This matches anchor 2 ('only when is present without what').

2 / 5

Trigger Term Quality

'PR body' is a natural phrase users would say, but common variations and synonyms such as 'pull request', 'PR description', or 'draft a PR' are missing. Coverage exists but is not comprehensive, matching anchor 3.

3 / 5

Distinctiveness Conflict Risk

'PR body' is a fairly distinct trigger unlikely to fire for unrelated skills, though it could overlap with closely related skills like PR review or commit message generation. This matches anchor 4 (mostly distinct, minor overlap risk with closely related skills).

4 / 5

Total

11

/

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

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository

withcoral/coral

Path

.agents/skills/pr/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.