autopilot

Full autonomous execution from idea to working code

Quality

31%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/autopilot/SKILL.md

Quality

Discovery

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description is critically weak across all dimensions. It reads like marketing copy rather than functional guidance, using buzzwords ('autonomous execution') instead of concrete capabilities. Without specific actions, trigger terms, or usage guidance, Claude cannot reliably select this skill from a pool of alternatives.

Suggestions

Replace abstract language with specific actions: e.g., 'Scaffolds complete projects, generates boilerplate code, implements features end-to-end, sets up project structure and dependencies'

Add explicit trigger guidance: 'Use when the user wants to build something from scratch, requests a complete implementation, or says phrases like "create an app", "build a project", or "implement from start to finish"'

Include distinguishing scope markers to differentiate from simpler code generation skills: e.g., 'For multi-file projects requiring architecture decisions, not single functions or snippets'

Dimension	Reasoning	Score
Specificity	The description uses vague, abstract language ('full autonomous execution', 'idea to working code') without listing any concrete actions like 'generates functions', 'writes tests', or 'creates modules'.	1 / 3
Completeness	Missing both clear 'what' (no specific capabilities listed) and 'when' (no 'Use when...' clause or trigger guidance). The description is too abstract to answer either question.	1 / 3
Trigger Term Quality	Contains no natural keywords users would say. Terms like 'autonomous execution' are technical jargon; users would more likely say 'build an app', 'write code for', or 'create a program'.	1 / 3
Distinctiveness Conflict Risk	Extremely generic - 'working code' could apply to virtually any coding skill. Would conflict with code generation, refactoring, debugging, and many other development-related skills.	1 / 3
	Total	4 / 12 Passed

Implementation

62%

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

This skill excels at workflow clarity with well-defined phases, validation checkpoints, and escalation conditions. However, it's moderately verbose with explanatory sections that could be trimmed, and lacks executable code examples for the core operations. The progressive disclosure could be improved by moving the Advanced section content to separate reference files.

Suggestions

Add executable code examples for key operations like spawning Task agents and checking state files

Move the 'Why_This_Exists' section content into a brief inline comment or remove it entirely - Claude doesn't need motivation explained

Extract the Advanced section (configuration, troubleshooting, deep-interview integration) into a separate ADVANCED.md file with clear links

Simplify the Examples section - the 'Why good/bad' explanations are unnecessary; just show the examples

Dimension	Reasoning	Score
Conciseness	The skill is reasonably efficient but includes some unnecessary explanation (e.g., 'Why_This_Exists' section, verbose 'Examples' section explaining why examples are good/bad). The Advanced section is lengthy and could be trimmed or moved to a separate file.	2 / 3
Actionability	Provides clear phase descriptions and tool usage patterns, but lacks executable code examples. The Task() syntax is shown but not complete/executable. Configuration JSON is helpful but the core workflow lacks copy-paste ready commands.	2 / 3
Workflow Clarity	Excellent multi-step workflow with 6 clearly sequenced phases, explicit validation checkpoints (QA cycles with retry limits, multi-perspective validation requiring all approvals), and clear escalation/stop conditions. Feedback loops are well-defined.	3 / 3
Progressive Disclosure	Has an Advanced section for configuration and troubleshooting, but the main content is somewhat monolithic. References to other skills (deep-interview, ralplan, ralph) are mentioned but not linked. The 3-stage pipeline explanation could be in a separate file.	2 / 3
	Total	9 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

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

	Total	10 / 11 Passed

Repository: Yeachan-Heo/oh-my-claudecode
Commit: 48ffaac

Reviewed: 4 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.