make-skill

Use this skill when sedimenting a session into a reusable workspace skill. Triggers when the user wants to turn the current conversation, workflow, or troubleshooting path into a SKILL.md. Phrases like 'turn this into a skill', 'remember how I did X', 'save this workflow', 'make a skill from this', and any /make-skill <focus> invocation should fire this skill.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

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.

Highly actionable with an excellent validation-gated workflow and concrete executable examples, but it is long and repetitive for a single file and does not actually split its substantial template/reference material into bundle files despite describing a scripts/ convention. Tightening repeated rules and moving the batch-template/boilerplate into a reference file would lift the weaker dimensions.

Suggestions

De-duplicate the repeated 'do not call write_file, use materialize_skill' and absolute-path instructions — state each rule once and reference it, to cut ~150 lines.

Move the large SKILL.md body-structure template (lines ~365-449) and the extract_headings.py / extract.json worked example into a bundled reference file under references/, linking to it one level deep, so progressive disclosure is real rather than illustrative.

Trim explanatory prose about why LLMs under-trigger skills and why batches are preferred; keep the directive and one short justification, trusting Claude to infer the rest.

Dimension	Reasoning	Score
Conciseness	At ~700 lines the body restates the same guidance repeatedly (the 'do not call write_file' / 'use materialize_skill' rule, absolute-path instructions, and batch parameter rules each appear several times) and explains tool mechanics Claude can infer, so it is mostly efficient but noticeably padded.	3 / 5
Actionability	Provides fully executable, copy-paste-ready guidance: complete batch JSON, a runnable extract_headings.py, concrete run_tool_batch and materialize_skill calls with real argument shapes, and worked parameter examples covering the common cases.	5 / 5
Workflow Clarity	Multi-step flow is clearly sequenced (Step 0→5) with explicit validation checkpoints and feedback loops: the 2f self-check, 4a $steps reference verification table, 4b mandatory test-run, and 4a/4b/4c/4d error-recovery loops for a destructive/batch operation.	5 / 5
Progressive Disclosure	The body is a single monolithic SKILL.md with no bundle files present in references/scripts/assets, yet it inlines a full batch-JSON template, a python script, and a large body-structure spec that read as material which could live in separate reference files; references are illustrative rather than real one-level-deep links.	3 / 5
	Total	16 / 20 Passed

Description

95%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-targeted description that clearly states purpose and trigger conditions with natural user phrasings and an explicit invocation. Minor specificity gap (the description does not mention the batch-first execution model or materialize_skill) keeps it just below perfect on the capability-detail axis.

Dimension	Reasoning	Score
Specificity	Names the domain ('sedimenting a session into a reusable workspace skill', 'turn the current conversation, workflow, or troubleshooting path into a SKILL.md') and several concrete actions (turn into skill, save workflow, make a skill), with only minor coverage gaps relative to the full skill scope.	4 / 5
Completeness	Explicitly answers both 'what' (sediment a session into a reusable workspace skill / SKILL.md) and 'when' (an explicit 'Triggers when...' clause plus enumerated trigger phrases and the /make-skill invocation).	5 / 5
Trigger Term Quality	Comprehensive natural trigger phrasings including synonyms ('turn this into a skill', 'remember how I did X', 'save this workflow', 'make a skill from this') plus the explicit /make-skill <focus> invocation, covering what users would actually say.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (creating workspace skills from a session) with specific, distinctive triggers (/make-skill, 'turn this into a skill') and minimal overlap risk with unrelated skills.	5 / 5
	Total	19 / 20 Passed

Validation

75%

Warnings & errors only

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

Validation — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (724 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
Path: src/qwenpaw/agents/skills/make-skill-en/SKILL.md
Commit: 2094e07

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.