CtrlK
BlogDocsLog inGet started
Tessl Logo

request-refactor-plan

通过用户访谈创建带小提交的详细重构计划,然后作为 GitHub issue 提交。适用于用户想规划重构、创建重构 RFC,或把重构拆成安全的增量步骤时。

76

Quality

93%

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

SKILL.md
Quality
Evals
Security

Quality

Content

87%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, concise instruction skill with concrete steps and a ready-to-use issue template. Its main weakness is workflow clarity: the sequence is clear but lacks explicit validation checkpoints or feedback loops for the multi-step process.

Suggestions

Add explicit validation checkpoints to the workflow, e.g. after exploring the repo (step 2) and before filing the issue (step 8) — 'confirm scope and coverage gaps are resolved with the user before proceeding'.

For the conditional step 6, spell out the feedback loop: if test coverage is insufficient, record the user's testing plan in the issue's Testing Decisions section rather than just asking.

Consider a short 'Definition of done' checklist at the end so each step's completion can be verified before moving to the next.

DimensionReasoningScore

Conciseness

The body is lean and instruction-only: terse numbered steps plus a copy-paste-ready template, with no padding explaining concepts Claude already knows. The Fowler quote is brief and directly load-bearing for the 'tiny commits' step.

3 / 3

Actionability

Steps give concrete directives (explore the repo and verify assertions, check test coverage, break into tiny commits, file the issue) and the refactor-plan-template is a complete, ready-to-fill structure. For an instruction-only skill the guidance is specific and actionable.

3 / 3

Workflow Clarity

The eight steps are clearly numbered and sequenced with some conditionals (verify assertions in step 2, finalize scope in step 5, conditional test-coverage check in step 6), but there are no explicit validate-then-proceed checkpoints or fix-retry feedback loops, and it is multi-step so the simple-skill exemption does not clearly apply.

2 / 3

Progressive Disclosure

A single well-organized file (~60 lines) with no bundle files and no nested references; the inline template is the deliverable itself and is appropriately kept inline. Structure is clear and easy to navigate.

3 / 3

Total

11

/

12

Passed

Description

100%

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 strong, third-person description that states concrete capabilities and gives explicit use-when triggers covering several natural request phrasings. It is specific, complete, and clearly distinguishable from other skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — '通过用户访谈创建带小提交的详细重构计划' and '作为 GitHub issue 提交' — rather than vague language. It names the deliverable, the method (user interviews), and the small-commit constraint.

3 / 3

Completeness

Explicitly answers both what (create a detailed refactor plan with small commits and submit it as a GitHub issue) and when ('适用于用户想规划重构…时' is an explicit Use-when trigger clause).

3 / 3

Trigger Term Quality

Covers natural phrasings a user would actually say — '规划重构', '创建重构 RFC', and '把重构拆成安全的增量步骤'. These map well to real requests rather than internal jargon.

3 / 3

Distinctiveness Conflict Risk

It carves a clear niche — interview-driven refactor planning filed as a GitHub issue RFC — with distinct triggers unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
vinvcn/mattpocock-skills-zh-CN
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.