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

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

63%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.

A thorough, actionable skill-authoring guide with a clear iteration workflow, undermined by conversational padding, a body over its stated length budget, and several broken bundle references. Tightening prose and fixing/creating the referenced files would materially raise quality.

Suggestions

Remove conversational filler ('Cool? Cool.', 'Good luck!', the economic-value pep talk, the 'Communicating with the user' tangent) to bring the body under its 500-line target and respect the context-window budget.

Fix broken references: create the missing agents/grader.md, agents/comparator.md, agents/analyzer.md files and the eval-viewer/generate_review.py script (or correct the references to the existing scripts/generate_report.py), so navigation actually resolves.

Move the Cherry Studio, Claude.ai, and Cowork-specific instructions into separate environment reference files and link to them from a short dispatch section, reducing inline bulk and improving progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The core workflow and command examples are dense and useful, but conversational padding ('Cool? Cool.', 'Good luck!', 'we are trying to create billions a year in economic value here', the 'Communicating with the user' aside about plumbers and grandparents) explains context Claude already knows and could be trimmed.	3 / 5
Actionability	Provides concrete, executable commands (`python -m scripts.aggregate_benchmark`, `python -m scripts.run_loop`, `echo "$CHERRY_STUDIO_SKILLS_DIR"`) and complete JSON examples, but heavy use of placeholders and several references to paths that do not exist in the bundle keep it from being fully copy-paste ready.	4 / 5
Workflow Clarity	The eval/iterate process is laid out as explicit numbered Steps 1–5 with a termination condition and a feedback loop (improve → rerun → review → repeat), but validation relies mostly on human review rather than explicit programmatic checkpoints.	4 / 5
Progressive Disclosure	Section headers and one-level-deep references to real files (references/schemas.md, assets/eval_review.html, scripts/) are present, but the 512-line body exceeds its own 500-line ideal, inlines three large environment-specific blocks, and points to non-existent paths (agents/grader.md, agents/comparator.md, agents/analyzer.md, eval-viewer/generate_review.py).	3 / 5
	Total	14 / 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.

A strong, third-person description that covers what the skill does and when to use it with concrete trigger phrases and low conflict risk. Only minor improvement possible in casual-synonym coverage of trigger terms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Create new skills, modify and improve existing skills, and measure skill performance' plus 'run evals', 'benchmark 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... run evals... benchmark... optimize a skill's description') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural-term coverage with synonyms ('create a skill from scratch', 'edit', 'optimize an existing skill', 'run evals', 'benchmark'), though a few casual phrasings a user might actually say (e.g. 'make a skill', 'fix my skill') are absent.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (skill authoring/evaluation tooling) with triggers scoped to skill creation, editing, evals, and benchmarking, so overlap with unrelated skills is minimal.	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 (518 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: CherryHQ/cherry-studio
Path: resources/skills/skill-creator/SKILL.md
Commit: c649419

Reviewed: 3 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.