skill-creator

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

77%

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

The body is highly actionable and well-sequenced with explicit validation checkpoints, but it is over-length and padded with conversational asides, and several promoted references (agents/, eval-viewer/) are missing from the bundle.

Suggestions

Trim conversational padding and redundant restatements to bring the body under the 500-line guideline, moving environment-specific sections (DeerFlow, Claude.ai, Cowork) into reference files.

Restore or remove the broken references — the agents/ directory (grader.md, comparator.md, analyzer.md) and eval-viewer/generate_review.py are cited but absent from the bundle.

Replace chatty emphasis ('Cool? Cool.', 'gonna go all caps here') with terse imperative instructions to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	At ~535 lines the body exceeds the recommended <500-line budget and includes chatty padding ('Cool? Cool.', 'Sorry in advance but I'm gonna go all caps here', 'we are trying to create billions a year in economic value here'), so it is mostly efficient but could be tightened — matching the score-2 rather than the lean score-3 anchor.	2 / 3
Actionability	Provides copy-paste-ready executable commands (e.g. 'python -m scripts.aggregate_benchmark', 'nohup python .../generate_review.py'), concrete JSON templates, and exact field-name specs ('text', 'passed', 'evidence'), fully meeting the score-3 anchor of executable guidance with specific examples.	3 / 3
Workflow Clarity	The eval flow is an explicitly sequenced continuous process with numbered Steps 1–5, validation checkpoints ('Only proceed when validation passes', 'process each notification as it arrives'), and clear termination criteria, matching the score-3 anchor.	3 / 3
Progressive Disclosure	The body signals one-level-deep references to agents/*.md and references/schemas.md, but the referenced agents/ and eval-viewer/ directories do not exist in the bundle (broken pointers), leaving it at 'some structure but could be better organized' rather than the fully navigable score-3 anchor.	2 / 3
	Total	10 / 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.

The description is strong: it states concrete capabilities and provides an explicit, well-scoped 'Use when' trigger clause with natural user phrasings. It is both complete and clearly distinguishable from other skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Create new skills, modify and improve existing skills, and measure skill performance' plus 'run evals,' 'benchmark skill performance with variance analysis,' and 'optimize a skill's description for better triggering accuracy,' matching the score-3 anchor of multiple specific concrete actions.	3 / 3
Completeness	Explicitly answers both 'what does this do' (create/modify/improve/measure skill performance) and 'when should Claude use it' via an explicit 'Use when users want to...' clause, satisfying the score-3 anchor.	3 / 3
Trigger Term Quality	Covers natural phrasings a user would actually say — 'create a skill from scratch,' 'edit,' 'optimize an existing skill,' 'run evals,' 'benchmark skill performance' — giving good coverage of common variations rather than technical jargon.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche — skill creation and iterative optimization — with distinct triggers unlikely to overlap with unrelated skills; no generic phrasing that would cause it to fire for the wrong skill.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (535 lines); consider splitting into references/ and linking	Warning
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	14 / 16 Passed

Repository: bytedance/deer-flow
Path: skills/public/skill-creator/SKILL.md
Commit: cd9432b

Reviewed: about 13 hours 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.