CtrlK
BlogDocsLog inGet started
Tessl Logo

clarify-before-change

在修改前澄清范围、风险、假设与验收标准,避免误改。用于修改 Skill、AGENTS.md、项目规则、工作流规则、仓库结构、复杂代码或具有结构影响的文档,也用于优化 Skill、调整规则、重构、重组或需求不完整的场景。

63

Quality

75%

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 ./skills/clarify-before-change/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 well-organized, actionable governance skill with a clear numbered workflow, a decision-record template, and explicit acceptance criteria. Its main weaknesses are some verbosity in the canonical intent-resolution section and a dangling reference to a non-existent examples file.

Suggestions

Tighten the '意图解析策略(Canonical)' section into bullets or a compact table to cut token weight while preserving the rules.

Make the validation step an explicit feedback loop ('validate → if fail, fix and re-validate → only proceed when valid') to push workflow clarity higher.

Either add the referenced examples/ambiguous-restructure.md or remove the link so progressive disclosure points only to real files.

DimensionReasoningScore

Conciseness

The body is mostly efficient and free of generic concept explanations Claude already knows, but the long '意图解析策略(Canonical)' block restates governance/confirmation rules at length and the multi-clause sentences could be tightened, placing it at mostly-efficient with some padding.

3 / 5

Actionability

It gives concrete, executable guidance — a numbered workflow, a decision-record template with explicit fields, and a three-tier request classification (audit/change/high-risk) — with only minor gaps (no literal example of a recorded 'assumption' entry or a sample question).

4 / 5

Workflow Clarity

The six-step workflow is clearly sequenced with an explicit checkpoint ('只有缺失信息确实阻止继续时才提一个关键问题') and a validation section listing observable acceptance conditions; it stops short of 5 because the validate→fix→retry feedback loop is implied rather than spelled out as an explicit retry cycle.

4 / 5

Progressive Disclosure

Structure is good with well-labeled sections and a one-level-deep reference ([ambiguous-restructure.md](examples/ambiguous-restructure.md)); however the referenced examples/ directory does not exist in the bundle, so the single reference points to a missing file, keeping it below 5.

4 / 5

Total

15

/

20

Passed

Description

83%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.

A strong, well-scoped description that clearly states both what the skill does and when to use it, with concrete trigger scenarios and an explicit boundary against executing changes. Minor gains are possible from adding a few more natural synonyms and tightening the long enumeration of targets.

Suggestions

Lead with a shorter verb-first 'what' clause before the enumeration so the core action is immediately visible.

Add a couple of everyday synonyms (e.g. '确认范围/对齐预期/改之前对一下') to broaden natural trigger coverage.

DimensionReasoningScore

Specificity

The description names a clear domain ('修改前澄清范围、风险、假设与验收标准') and lists several concrete actions (澄清范围/风险/假设/验收标准) plus multiple concrete targets (Skill、AGENTS.md、项目规则、工作流规则、仓库结构、复杂代码), with only minor coverage gaps around what 'clarify' concretely produces.

4 / 5

Completeness

It explicitly answers both 'what' (在修改前澄清范围、风险、假设与验收标准,避免误改) and 'when' (用于修改 Skill、AGENTS.md... 也用于优化 Skill、调整规则、重构、重组或需求不完整的场景) with concrete trigger phrases, matching the 5 anchor.

5 / 5

Trigger Term Quality

It includes natural trigger terms users would say ('修改前', '优化 Skill', '调整规则', '重构', '重组', '需求不完整') which map well to real requests; a few common synonyms or phrasings are missing, so not a full 5.

4 / 5

Distinctiveness Conflict Risk

It carves a clear niche ('修改前澄清,不执行修改') with distinct triggers and a stated boundary ('本 Skill 只建立变更边界,不执行修改'); minor overlap risk remains with general change-management skills, keeping it just below 5.

4 / 5

Total

17

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
ooooooooooooooooooop/agent-tools
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.