skill-creator

To create new CLI skills following Anthropic's official best practices with zero manual configuration. This skill automates brainstorming, template application, validation, and installation processes while maintaining progressive disclosure patterns and writing style standards.

Quality

55%

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 ./skills/skill-creator/SKILL.md

Quality

Content

52%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 is well-sequenced with executable bash and validation checkpoints, but it is padded with repeated decorative progress art and — more seriously — documents a bundle layout that does not match the real files, undermining progressive disclosure and navigation.

Suggestions

Reconcile the 'Bundled Resources' section with the actual bundle: reference the real files (references/output-patterns.md, references/workflows.md, scripts/init_skill.py, package_skill.py, quick_validate.py) and remove or create the nonexistent ones.

Collapse the six duplicated ASCII progress-box blocks into a single reusable template referenced once, cutting significant token padding.

Replace invocations of missing scripts (validate-skill-yaml.sh, validate-skill-content.sh) with the bundled scripts/quick_validate.py, or add the referenced scripts to the bundle.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose: large decorative ASCII progress-box art is duplicated once per phase (six near-identical boxes) plus repeated one-line progress bars, adding substantial padding with little instructional value beyond the first instance.	2 / 5
Actionability	Concrete, mostly executable bash is provided throughout (mkdir, sed substitution, ln -sf symlinks, git config extraction), with only minor gaps such as references to template paths not present in the bundle.	4 / 5
Workflow Clarity	A clear Step 0 + Phase 1–6 sequence with an explicit validation phase and feedback loops (validation failure → auto-fix → retry) is present; held below 5 because the validation scripts invoked (validate-skill-yaml.sh, validate-skill-content.sh) do not exist in the bundle.	4 / 5
Progressive Disclosure	The 'Bundled Resources' section lists reference, example, and script files that do not exist, while the actual bundle (output-patterns.md, workflows.md, init_skill.py, etc.) is never referenced, breaking navigation; additionally large display/standards content that belongs in references is inlined.	2 / 5
	Total	12 / 20 Passed

Description

58%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 clearly communicates a distinct purpose (automated CLI skill scaffolding) and enumerates several capabilities, but it omits any explicit 'when to use' trigger guidance, capping completeness and limiting trigger-term quality.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user asks to create, scaffold, or generate a new CLI skill, or to package domain knowledge into a skill.'

Add natural synonyms users would actually say ('make a skill', 'build a skill', 'scaffold a skill') to broaden trigger coverage.

Tighten 'brainstorming, template application, validation, and installation processes' toward concrete operations so capabilities read as actions rather than process labels.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — "automates brainstorming, template application, validation, and installation processes" — but they are process-level abstractions rather than the crisp concrete operations of the score-5 anchor, so it sits just below it.	4 / 5
Completeness	The 'what' is clearly stated (creating and automating skill scaffolding), but there is no 'Use when...' or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	"create new CLI skills" and "skill creation" are relevant, but natural synonyms like "make/build/scaffold a skill" are absent and there is no trigger-phrase clause, so coverage is partial rather than comprehensive.	3 / 5
Distinctiveness Conflict Risk	The skill-creation meta-niche is clearly distinct from ordinary utility skills, but the absence of explicit triggers leaves minor overlap risk with general scaffolding/automation skills, placing it just below the score-5 anchor.	4 / 5
	Total	14 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (591 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 3 missing	Warning

	Total	13 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/skill-creator/SKILL.md
Commit: fbdfd63

Reviewed: about 17 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.