CtrlK
BlogDocsLog inGet started
Tessl Logo

code-change-summarizer

Generates clear and structured pull request descriptions from code changes. Use when Claude needs to: (1) Create PR descriptions from git diffs or code changes, (2) Summarize what changed and why, (3) Document breaking changes with migration guides, (4) Add technical details and design decisions, (5) Provide testing instructions, (6) Enhance descriptions with security, performance, and architecture notes, (7) Document dependency changes. Takes code changes as input, outputs comprehensive PR description in Markdown.

83

1.15x
Quality

76%

Does it follow best practices?

Impact

95%

1.15x

Average score across 3 eval scenarios

SecuritybySnyk

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/code-change-summarizer/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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 content is highly actionable and well-sequenced, but it is substantially verbose and self-duplicating, and it inlines template material that already lives in the references file. Trimming repetition and moving detailed templates into the reference would materially improve it.

Suggestions

Remove the recurring OAuth2 example: illustrate each section once and reference a single worked example in references/pr-templates.md instead of repeating it across steps 3-8 and Common Scenarios.

Delete the standalone Output Format and Best Practices sections, which restate the per-step workflow verbatim; keep one consolidated template in the reference file and link to it.

Move the Common Scenarios worked examples into references/pr-templates.md so SKILL.md reads as a lean overview with a single clearly-signaled reference, raising progressive_disclosure and conciseness.

DimensionReasoningScore

Conciseness

The ~680-line body is noticeably verbose: the same OAuth2 example recurs essentially verbatim across steps 3-8 and the Common Scenarios, the full Output Format template re-states every workflow step, and Best Practices repeats guidance already in the workflow, with much of it also duplicated in references/pr-templates.md — several padded/duplicated sections rather than just minor tightening.

2 / 5

Actionability

Provides copy-paste-ready markdown templates, concrete before/after code blocks, specific commands (`npm start`, `npm run process-large-dataset`), explicit title formats with type prefixes, and checklists that cover the common PR cases end to end.

5 / 5

Workflow Clarity

An 11-step numbered workflow is clearly sequenced and closes with a Review-and-Refine validation step plus completeness checklist, but validation is concentrated at the end rather than as intermediate checkpoints interspersed through the process.

4 / 5

Progressive Disclosure

There is a single clearly-signaled one-level reference (references/pr-templates.md), but the body inlines large template/example blocks (Output Format, Best Practices, Common Scenarios) that duplicate the reference file and would be better split out, so structure exists but content that should be separate is inline.

3 / 5

Total

14

/

20

Passed

Description

88%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 strong: it explicitly states both what the skill does and when to use it, lists comprehensive concrete actions in third person, and uses natural trigger terms. The only minor gaps are a few missing synonyms and slight overlap with adjacent git-related skills.

DimensionReasoningScore

Specificity

Lists seven numbered concrete actions (create PR descriptions, summarize what changed and why, document breaking changes with migration guides, add technical details, provide testing instructions, enhance with security/performance/architecture notes, document dependency changes), giving comprehensive coverage of the PR-description domain rather than just several.

5 / 5

Completeness

Explicitly answers 'what' ('Generates clear and structured pull request descriptions from code changes' and 'Takes code changes as input, outputs comprehensive PR description in Markdown') and 'when' via an explicit 'Use when Claude needs to:' clause with seven concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes natural user terms like 'pull request descriptions', 'PR descriptions', 'git diffs', 'code changes', 'breaking changes', 'migration guides', and 'testing instructions' with the PR/pull-request synonym pair, but a few natural variations (e.g. 'release notes', 'code review') are absent and there are no file-extension cues (n/a for this domain).

4 / 5

Distinctiveness Conflict Risk

The PR-description niche is clearly bounded by distinct triggers (PR/pull request descriptions, git diffs), with only minor overlap risk against closely related skills such as commit-message or release-notes generators.

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

skill_md_line_count

SKILL.md is long (684 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
ArabelaTso/Skills-4-SE
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.