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

68%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/public/skill-creator/SKILL.md

Quality

Content

45%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 lays out a strong, well-sequenced eval-and-iterate workflow with concrete commands, but it is padded with conversational filler and critically contains broken references to missing bundle files while leaving real bundle files unlinked. Fixing file references and trimming the chatty asides would substantially raise the score.

Suggestions

Resolve broken references: create the referenced agents/*.md and eval-viewer/generate_review.py files, or rewrite the body to point only at files that actually exist (references/schemas.md, references/output-patterns.md, references/workflows.md, and the present scripts).

Add pointers to the unreferenced bundle files — output-patterns.md, workflows.md, and scripts like quick_validate.py, init_skill.py, generate_report.py, improve_description.py — so the progressive-disclosure structure is actually navigable.

Trim conversational padding (e.g. 'Cool? Cool.', the 'plumbers and grandparents' aside, 'billions a year in economic value', and repeated all-caps interjections) to reduce token cost without losing the useful guidance.

Dimension	Reasoning	Score
Conciseness	At ~534 lines the body is noticeably verbose and padded with conversational asides ('Cool? Cool.', 'how could you, it's only very recently that it started', 'we are trying to create billions a year in economic value here!', repeated all-caps interjections) that do not earn their tokens.	2 / 5
Actionability	It gives concrete executable commands (e.g. 'python -m scripts.aggregate_benchmark', 'python -m scripts.run_loop'), but key guidance points to files that do not exist (agents/grader.md, agents/comparator.md, agents/analyzer.md, eval-viewer/generate_review.py, scripts/helper.py), so several instructions cannot actually be executed as written.	3 / 5
Workflow Clarity	The create → test → grade → aggregate → analyst pass → viewer → feedback → iterate loop is clearly sequenced with validation checkpoints and an explicit feedback loop, with only minor gaps (e.g. some checkpoint commands reference missing files).	4 / 5
Progressive Disclosure	Multiple references resolve to nonexistent files (agents/*.md, eval-viewer/generate_review.py, scripts/helper.py) while three present reference files (output-patterns.md, workflows.md) and six present scripts are never referenced from the body, so navigation is broken and content is not appropriately split.	2 / 5
	Total	11 / 20 Passed

Description

92%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.

The description is specific, complete, and well-targeted, clearly stating both capabilities and explicit trigger contexts. Only minor synonym coverage keeps trigger term quality from a perfect score.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Create new skills, modify and improve existing skills, and measure skill performance', 'run evals', 'benchmark skill performance with variance analysis', 'optimize a skill's description' — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both what ('Create new skills, modify and improve existing skills, and measure skill performance') and when ('Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural phrasing ('create a skill from scratch', 'edit, or optimize an existing skill', 'run evals', 'benchmark skill performance') with good coverage, but a few common synonyms (e.g. 'build a skill', 'test a skill') are missing.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (skill authoring, evaluation, and description optimization) with distinct triggers and minimal realistic overlap with other skills.	5 / 5
	Total	19 / 20 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: 0d49253

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.