autopilot

Full autonomous execution from idea to working code

Quality

53%

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/autopilot/SKILL.md

Quality

Content

70%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 well-sequenced, actionable orchestration guide with strong validation and feedback loops, but it is over-inline: dense configuration and workflow-profile material that should live in one-level-deep reference files is folded into the main skill, and some sections are verbose.

Suggestions

Move the dense Workflow_Profiles section (lock mechanics, transcript boundaries, v1 deferrals) into a dedicated reference doc and keep only the selection contract in SKILL.md.

Move the full Configuration block to a referenced CONFIG.md and inline only the most common settings.

Tighten the Workflow_Profiles prose to remove implementation detail Claude does not need to act (kernel advisory locking, SHA-256 internals).

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with clear phases and commands, but the Workflow_Profiles section is padded with low-value implementation detail (flock, kernel advisory locking, SHA-256 hashes, transcript boundary traversal) that could be tightened.	3 / 5
Actionability	It gives concrete executable guidance — specific Task() subagent calls, config JSONC blocks, and commands like 'omc team 1:cursor "<task>"' — with only minor gaps where phases stay abstract (e.g., 'Architect extracts requirements').	4 / 5
Workflow Clarity	Phases 0-5 are clearly sequenced with explicit validation checkpoints (Phase 3 QA, Phase 4 multi-reviewer approval), feedback loops (QA cycles, re-validation on rejection), stop conditions, and a Final_Checklist.	5 / 5
Progressive Disclosure	Section headers and an <Advanced> block give some structure, but heavy inline content (Workflow_Profiles, Configuration) that belongs in separate reference files is kept in SKILL.md, and the only references (docs/REFERENCE.md, docs/company-context-interface.md) are not verifiable against any provided bundle.	3 / 5
	Total	15 / 20 Passed

Description

37%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 conveys a clear high-level purpose but is terse and omits concrete capabilities and any explicit use-when trigger guidance. It reads more like a tagline than a discoverable skill description.

Suggestions

Add 2-3 concrete capabilities (e.g., requirements analysis, parallel implementation, QA cycling, multi-perspective validation) to the description.

Append a 'Use when...' clause with natural trigger phrases users would actually say (e.g., 'Use when the user says autopilot, build me, or wants end-to-end autonomous execution').

Reference the lifecycle scope explicitly to sharpen distinctiveness against single-purpose build/exec skills.

Dimension	Reasoning	Score
Specificity	The description 'Full autonomous execution from idea to working code' names the domain (autonomous execution) and an outcome, but lists no concrete actions, matching the anchor 'Names the domain but actions are minimal or generic'.	2 / 5
Completeness	A clear 'what' is present (autonomous execution from idea to working code) but there is no 'when'/trigger clause, which per the guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Only generic keywords ('idea', 'working code') appear; the natural trigger phrases users would say ('autopilot', 'build me') live in the body, not the description, so natural phrases are missing.	2 / 5
Distinctiveness Conflict Risk	'Full autonomous execution' gives it a somewhat specific niche, but 'from idea to working code' is broad enough to overlap with general build/coding skills.	3 / 5
	Total	10 / 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: Yeachan-Heo/oh-my-claudecode
Path: skills/autopilot/SKILL.md
Commit: 5aa678c

Reviewed: 8 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.