CtrlK
BlogDocsLog inGet started
Tessl Logo

writing-pr-body-title-description

Use when writing or editing a pull request title or body.

57

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/writing-pr-body-title-description/SKILL.md
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.

The body is an exemplar of token efficiency — a dense, directive set of rules covering the common PR cases with no filler. Its only weaknesses are organizational and exemplification: a single paragraph instead of labeled sections, and no sample title/body to anchor the conventions.

DimensionReasoningScore

Conciseness

At ~70 words the body is lean and assumes Claude's competence: 'Keep PR titles and bodies concise; do not write essays. Focus on bullet points, Mermaid diagrams, and useful code samples.' Every directive carries new information with no padding or explanation of concepts Claude already knows, matching anchor 5 ('lean and efficient; every token earns its place').

5 / 5

Actionability

Directives are concrete and case-specific: 'include a before/after table with uploaded images or videos', 'For benchmarks, always include a before/after table', 'describe the final squash-merge outcome'. It falls short of anchor 5 because there is no example title or body template to copy, leaving minor gaps between the rules and a concrete artifact.

4 / 5

Workflow Clarity

This is a simple single-task skill and the action (write a concise PR title/body) is unambiguous, with explicit case branches for visual changes, benchmarks, and impressive changes. It does not reach 5 because 'truly impressive changes' leaves ambiguous when the technical-blog style applies, a minor checkpoint gap rather than the incoherence of anchor 3 or below.

4 / 5

Progressive Disclosure

The skill is under 50 lines with no bundle files and no need for external references, and the content is short and scannable. It misses anchor 5's bar of 'well-organized sections' — it is a single unsegmented paragraph where per-case rules (visual, benchmark, impressive changes) could be broken out — so anchor 4 ('good structure; minor organization gaps') is the best fit.

4 / 5

Total

17

/

20

Passed

Description

47%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 a clean, well-targeted trigger phrase with good natural keywords, but it is purely a 'when' clause. It never states what the skill does — the conciseness rules, formatting preferences, and before/after table conventions are invisible from the frontmatter alone.

Suggestions

State the 'what' alongside the 'when': e.g., 'Formats PR titles and bodies as concise bullet-point summaries with Mermaid diagrams, code snippets, and before/after tables for visual and benchmark changes. Use when writing or editing a pull request title or body.'

Add a few concrete capability verbs (keep concise, include before/after tables, describe the final squash-merge outcome) so the description previews the skill's actual guidance.

Include common synonyms such as 'PR' or 'PR description' in the trigger clause to broaden natural keyword coverage.

DimensionReasoningScore

Specificity

The description names the domain ('pull request title or body') and the user's activity ('writing or editing'), but states no concrete capability of the skill itself — nothing about what conventions or guidance it provides. This matches anchor 2 ('names the domain but actions are minimal or generic') better than anchor 3, whose example ('Processes PDF files and extracts content') describes skill actions rather than the user's task.

2 / 5

Completeness

Only the 'when' is present ('Use when writing or editing a pull request title or body') with no 'what' at all — the skill's actual function is never stated. This exactly matches anchor 2 ('only when is present without what'); it cannot reach anchor 3, which requires a clear 'what'.

2 / 5

Trigger Term Quality

Natural terms are well covered: 'writing', 'editing', 'pull request', 'title', 'body' — phrases a user would plausibly say. It falls short of anchor 5 because common synonyms like 'PR', 'PR description', or 'draft pull request' are missing, matching anchor 4 ('good keyword coverage; a few natural terms missing').

4 / 5

Distinctiveness Conflict Risk

PR title/body authorship is a distinct niche with clear triggers, with only minor overlap risk against closely related commit-message or general-writing skills. It fits anchor 4 ('mostly distinct; minor overlap risk') rather than anchor 5, since it does not fully disambiguate from adjacent git-workflow skills.

4 / 5

Total

12

/

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
langchain-ai/open-swe
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.