auto-claude-spec

Auto-Claude spec creation and management. Use when creating feature specs, understanding spec pipeline phases, modifying requirements, or managing spec lifecycle.

Quality

76%

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/auto-claude-spec/SKILL.md

Quality

Content

65%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 content with concrete commands and formats, but it is a long monolithic file and its destructive/batch workflows omit validation checkpoints. Splitting reference material into separate files and adding pre-delete validation would lift the weaker dimensions.

Suggestions

Add a validation/confirmation step before destructive operations: e.g., require checking spec status and confirming before 'rm -rf' or 'run.py --spec 001 --discard', and validate each spec in the batch-creation loop.

Move the detailed file-format schemas (spec.md, requirements.json, implementation_plan.json) and the full phase breakdown into separate reference files linked from SKILL.md to improve progressive disclosure and reduce inline length.

Trim explanatory filler such as 'Specs are the foundation of Auto-Claude builds' and 'Master the spec creation pipeline for autonomous builds' to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and largely domain-specific knowledge Claude would not already have, but the ~345-line body includes trimmable explanatory lines ('Specs are the foundation...', 'Master the spec creation pipeline...') and could be tightened.	3 / 5
Actionability	Provides fully copy-paste-ready commands (spec_runner.py invocations, run.py --list, validate_spec.py) plus concrete JSON and directory-layout examples covering creation, listing, editing, deletion, and troubleshooting.	5 / 5
Workflow Clarity	The phase sequence is clear and a review checklist exists, but destructive operations (rm -rf, run.py --discard) and the batch-creation loop lack validation/verification steps, capping this dimension at 3 per the rubric guideline.	3 / 5
Progressive Disclosure	Section headers are well organized, but the skill is a monolithic 345-line file with no one-level-deep references; detailed JSON schemas and phase breakdowns that could live in separate reference files are inlined.	3 / 5
	Total	14 / 20 Passed

Description

87%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 description that clearly states the skill's purpose and gives explicit, natural trigger guidance in third person. Minor room to sharpen the most generic action ('managing spec lifecycle').

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('creating feature specs, understanding spec pipeline phases, modifying requirements, or managing spec lifecycle'), but 'managing spec lifecycle' is generic, leaving minor coverage gaps versus a 5.	4 / 5
Completeness	Explicitly answers both what ('Auto-Claude spec creation and management') and when via a concrete 'Use when...' clause with multiple trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Good natural keyword coverage ('feature specs', 'spec pipeline phases', 'requirements', 'spec lifecycle') that users would plausibly say, though a few common synonyms or variations are missing.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (Auto-Claude specs) with distinct, specific triggers, making overlap with unrelated skills minimal.	5 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: fernandezbaptiste/Skrillz
Path: skills/auto-claude-spec/SKILL.md
Commit: 93ed392

Reviewed: 1 day 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.