autopilot

Full autonomous execution from idea to working code

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-sequenced, actionable six-phase orchestration workflow with strong validation checkpoints and concrete configs, commands, and per-phase agent assignments. It loses points for repeated content and for referencing docs files that are not actually bundled.

Suggestions

De-duplicate the 3-cycle QA stop rule and the 3-stage pipeline description so each appears in one canonical place, and trim the "Why_This_Exists" explanation of concepts Claude already knows.

Either bundle the referenced `docs/REFERENCE.md` and `docs/company-context-interface.md` files or remove the inline references, and consider moving the `<Advanced>` configuration/pipeline content into a separate reference file with a clearly signaled link.

Dimension	Reasoning	Score
Conciseness	The body repeats the 3-cycle QA rule across Execution_Policy, Phase 3, and Troubleshooting and re-explains the 3-stage pipeline in both Steps and a dedicated section, while "Why_This_Exists" states concepts Claude already knows; it is mostly efficient but could be tightened, matching the score-2 anchor.	2 / 3
Actionability	Concrete output paths (`.omc/autopilot/spec.md`), named agents per phase (Architect Opus, Critic Opus, Executor Haiku/Sonnet/Opus), copy-paste config blocks, and specific commands (`omc team 1:cursor "<implementation task>"`) make the guidance executable and copy-paste ready.	3 / 3
Workflow Clarity	Six numbered phases (0–5) with explicit validation checkpoints (QA stops after the same error repeats 3 times, Phase 4 requires unanimous reviewer approval, fix-and-revalidate loop) plus a Final_Checklist match the score-3 anchor of clear sequence with feedback loops and checklists.	3 / 3
Progressive Disclosure	No bundle files exist, yet the body references `docs/REFERENCE.md` and `docs/company-context-interface.md` that are not bundled, and the large inline `<Advanced>` block is content that could be split into a separate file, matching the score-2 anchor.	2 / 3
	Total	10 / 12 Passed

Description

35%

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 states a clear high-level purpose (idea→working code) but omits any 'Use when' triggers or natural keywords, capping completeness and trigger quality at low scores. It is distinguishable but generic enough to risk overlap with other build/plan skills.

Suggestions

Append a 'Use when...' clause with natural trigger terms to the description, e.g. 'Use when the user says "autopilot", "build me", or wants hands-off end-to-end execution from idea to working code.'

Move natural keywords (autopilot, build me, full auto) into the description field itself instead of leaving them only in the body, so the description scores on trigger-term quality.

List the concrete phases (requirements analysis, design, implementation, QA, validation) in the description to raise specificity from a single abstract transformation to multiple named actions.

Dimension	Reasoning	Score
Specificity	"Full autonomous execution from idea to working code" names a domain (autonomous execution) and a concrete transformation (idea→working code), but it does not enumerate multiple specific actions like the score-3 anchor, so it sits at 2 rather than 3.	2 / 3
Completeness	It states what the skill does but provides no "when" trigger guidance, and per the rubric guideline a missing "Use when..." clause caps completeness at 2; it is above 1 because the "what" is present.	2 / 3
Trigger Term Quality	The description contains no natural user keywords (no "build me", "autopilot", or "Use when"), and "autonomous execution" reads as technical jargon, matching the score-1 anchor; the natural triggers exist only in the body, not the description field.	1 / 3
Distinctiveness Conflict Risk	The "idea to working code" framing carves a niche, but with no trigger terms it could overlap with general build/plan skills, matching the score-2 anchor rather than the clearly-distinct score-3 example.	2 / 3
	Total	7 / 12 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
Commit: 6c59219

Reviewed: about 4 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.