CtrlK
BlogDocsLog inGet started
Tessl Logo

make-skill

用于把当前会话沉淀为可复用的 workspace skill。当用户希望把当前对话、工作流或排错路径写成 SKILL.md 时触发。触发表达包括「把这个变成 skill」「记住我是怎么做 X 的」「保存这个工作流」「make a skill from this」以及任何 /make-skill <focus> 调用。

64

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./src/qwenpaw/agents/skills/make-skill-zh/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%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.

An actionable, well-sequenced skill body with explicit validation loops and copy-paste-ready code and parameter specs. It is somewhat verbose and repeats the absolute-path caution in several places, and the large inline batch template could be moved to a reference file.

Suggestions

Trim repetition of the absolute-path requirement — state it once in the batch-writing guidance and refer back, rather than re-explaining it in 步骤 2b, the batch-writing tips, and the path note.

Move the long inline batch JSON + Python example into a scripts/ reference file and reference it from the body to reduce inline bulk and model the progressive-disclosure structure the skill itself advocates.

Tighten prose around 步骤 2a/2b where '内容能撑得起就不嫌长' and overlapping batch-philosophy paragraphs restate the same automation rationale.

DimensionReasoningScore

Conciseness

The body is comprehensive and mostly earns its place, but quoted phrases like '内容能撑得起就不嫌长' and the long worked batch example plus repeated absolute-path caveats show noticeable padding and re-explanation of the same point (absolute path requirement) across multiple sections.

3 / 5

Actionability

Fully executable: quoted concrete calls like materialize_skill(name=..., description=..., body=..., extra_files=...), create_plan with its four required parameters spelled out, run_tool_batch(file_path=..., args=...), and a complete copy-paste-ready batch JSON + Python script example covering the common case.

5 / 5

Workflow Clarity

A clearly sequenced multi-phase workflow (步骤 0→5) with explicit validation checkpoints: quoted '验证 $steps 引用' table, '试跑 batch' loop, '反复修正直到跑通', and error-recovery branches (4c–4f); the summary diagram closes the loop.

5 / 5

Progressive Disclosure

No bundle files exist (references/scripts/assets absent), and the body is appropriately self-contained with well-organized sections and the summary diagram as overview; minor gap is the large inline batch-JSON template (步骤 2b) that conceptually belongs in a reference file, keeping it just short of a 5.

4 / 5

Total

17

/

20

Passed

Description

81%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, specific description that states both what the skill does and when to trigger it, with rich natural-language triggers in two languages. Slight room to separate trigger scenarios from invocation phrasing for maximum clarity.

Suggestions

Add an explicit 'Use this skill when...' clause separated from the trigger phrasing list to cleanly mark the when-context (e.g. scenarios where the user wants to preserve a workflow or debugging path).

Include a few more natural synonyms a user might spontaneously say (e.g. '把这段流程存下来', 'make this reusable', 'save this pattern') to widen trigger coverage.

DimensionReasoningScore

Specificity

Names the domain ('workspace skill') and concrete actions (沉淀为可复用 skill, 写成 SKILL.md, 通过 materialize_skill 持久化); the literal product is one artefact so the action set is bounded, but it lists the mechanism and outcome explicitly.

4 / 5

Completeness

What is explicit ('用于把当前会话沉淀为可复用的 workspace skill') and when is explicit (a 'Use when...' trigger list); the when-clause is concrete but blends trigger phrasing with invocation rather than a fully separated trigger-and-scenario statement, so not a 5.

4 / 5

Trigger Term Quality

Natural trigger phrases quoted include 「把这个变成 skill」「记住我是怎么做 X 的」「保存这个工作流」「make a skill from this」 plus /make-skill <focus>; covers common synonyms across Chinese and English but is missing file-extension-style equivalents and a couple of natural phrasings a user might say.

4 / 5

Distinctiveness Conflict Risk

Clear niche — converting a running session into a SKILL.md via /make-skill — with highly specific triggers unlikely to fire for unrelated skills; minimal overlap risk.

5 / 5

Total

17

/

20

Passed

Validation

75%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation12 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (640 lines); consider splitting into references/ and linking

Warning

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

referenced_paths_exist

Referenced path issues: 9 missing

Warning

Total

12

/

16

Passed

Repository
agentscope-ai/QwenPaw
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.