pua-loop

PUA Loop alias for Codex. Codex subcommand mapping for Claude Code /pua:loop style usage; invoke with $pua-loop.

Quality

81%

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

Quality

Content

77%

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

The body is highly actionable with concrete commands, signal tokens, and a clear validation feedback loop, making the core workflow easy to follow. Its weak spots are conciseness (motivational/autoresearch-comparison padding) and progressive disclosure (everything inline in one file with no external reference structure).

Suggestions

Trim the opening autoresearch blockquote and the closing '与 autoresearch 的关系' comparison table, or move them to a separate reference file, since they are background rather than operational guidance.

Consider extracting the detailed .claude/pua-loop-history.jsonl schema and the pressure-escalation tables into a references file, leaving SKILL.md as a lean overview that points to them.

Dimension	Reasoning	Score
Conciseness	Mostly concrete and instructional, but the motivational autoresearch blockquote and the closing '与 autoresearch 的关系' comparison table add context Claude does not need and could be trimmed.	2 / 3
Actionability	Provides copy-paste-ready commands (the setup-pua-loop.sh invocation, --verify examples) and concrete signal tokens (<promise>LOOP_DONE</promise>, <loop-abort>, <loop-pause>) plus a real history.jsonl schema.	3 / 3
Workflow Clarity	Sequences the multi-step flow clearly (启动 Steps 1-3, the read-history→git-log→execute→verify→repeat loop) with an explicit validation feedback loop on Oracle rejection, matching the checkpoint pattern the rubric rewards.	3 / 3
Progressive Disclosure	Well-sectioned and self-contained with no deep reference nesting, but it is a monolithic single file with inline tables/diagrams/history schema that could be split into reference files; no bundle files are present.	2 / 3
	Total	10 / 12 Passed

Description

85%

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 is specific, complete, and well-scoped with an explicit use-when trigger, covering both what the skill does and when to invoke it. Its main weakness is trigger-term breadth, relying on 'loop'/'自动迭代' and missing common natural-language variations a user might utter.

Suggestions

Broaden trigger terms to include natural variations users might say, such as 'iterate', 'auto-iterate', 'repeat until it works', or 'keep going until done', not just 'loop'/'自动迭代'.

Keep the explicit 'Use only when...' clause but consider pairing it with the negative case (e.g. 'Do not use for one-shot tasks') to further reduce conflict risk.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — 'guided iterative development with recurring checks, completion evidence, and pause/abort markers' — rather than vague abstractions.	3 / 3
Completeness	Clearly states what it does and provides an explicit 'Use only when the user explicitly asks for loop/自动迭代 mode' trigger clause, answering both what and when.	3 / 3
Trigger Term Quality	Includes relevant natural terms ('loop', 'iterative development', '自动迭代') but misses common phrasings users might say like 'iterate', 'auto-iterate', or 'keep going until done'.	2 / 3
Distinctiveness Conflict Risk	The narrow 'loop/自动迭代 mode' niche with an explicit opt-in trigger makes it unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: tanweai/pua
Path: codex/pua-loop/SKILL.md
Commit: 3fd4e5a

Reviewed: 2 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.