auto-claude-build

Auto-Claude autonomous build system. Use when running builds, understanding agent workflow, managing parallel execution, or troubleshooting build issues.

Quality

73%

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-build/SKILL.md

Quality

Content

71%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 a concrete, actionable reference with strong executable commands and a well-validated build/QA workflow. Its main weaknesses are redundancy across sections and a monolithic structure with no progressive disclosure to separate reference files.

Suggestions

Remove redundancy: the Build Flow section restates the Agent Roles/Architecture, and the QA loop appears as both a flow diagram and an ASCII tree — keep one canonical version of each.

Split detailed reference material (QA validation details, troubleshooting, advanced configuration) into one-level-deep files under references/ and link to them from SKILL.md to improve progressive disclosure.

Add explicit validation checkpoints to the manual troubleshooting workflow (e.g., verify the build restarted cleanly after a force restart) to lift workflow clarity.

Dimension	Reasoning	Score
Conciseness	Mostly concrete reference material (commands, paths, tables), but noticeable redundancy — the Build Flow section restates the Agent Roles/Architecture, and the QA loop is shown twice (flow diagram and ASCII); not a 4 because the duplicated sections could be tightened.	3 / 5
Actionability	Provides copy-paste-ready commands throughout ("python run.py --spec 001", "tail -f ...", "touch ... PAUSE", "DEBUG=true DEBUG_LEVEL=3 python run.py") plus a concrete create_client() SDK example, covering the common cases.	5 / 5
Workflow Clarity	Clear 4-step build sequence with an explicit QA validate→fix→retry feedback loop and agent recovery (so the destructive/batch validation cap does not apply); not a 5 because the manual troubleshooting sections lack explicit validation checkpoints.	4 / 5
Progressive Disclosure	No bundle files exist and the ~300-line SKILL.md is a monolith with good internal headers but content (QA details, troubleshooting, advanced config) that should be split into one-level-deep reference files is inline; over 50 lines so the simple-skill exception does not apply.	3 / 5
	Total	15 / 20 Passed

Description

75%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 states both what the skill is and when to use it, with concrete, natural trigger phrases. It is held back from top marks by a terse 'what' clause that names the system without enumerating its concrete capabilities.

Dimension	Reasoning	Score
Specificity	Names the domain ("Auto-Claude autonomous build system") and lists several concrete use-actions ("running builds, ... managing parallel execution, ... troubleshooting build issues"), with minor gaps in capability coverage; not a 5 because the 'what' side is a terse noun phrase rather than a comprehensive capability list.	4 / 5
Completeness	Both 'what' ("Auto-Claude autonomous build system") and 'when' ("Use when running builds, ... troubleshooting build issues") are present and explicit; not a 5 because the 'what' is terse and does not enumerate concrete capabilities.	4 / 5
Trigger Term Quality	Natural phrases a user would actually say ("running builds", "troubleshooting build issues", "parallel execution") give good keyword coverage; not a 5 because common synonyms and variations are missing.	4 / 5
Distinctiveness Conflict Risk	Targets a specific niche (autonomous agent build pipeline) with distinct triggers and only minor overlap with the related auto-claude skill family and generic build/CI skills; not a 5 because some overlap with generic build skills remains.	4 / 5
	Total	16 / 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-build/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.