pua-loop

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

Quality

61%

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 ./codex/pua-loop/SKILL.md

Quality

Content

72%Weight 40%Scale 1-3

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

The content is admirably concise and appropriately scoped for a thin alias skill, but its core guidance is abstract rather than executable and the config-modification workflow lacks an explicit validation feedback loop.

Suggestions

Add a concrete example command or snippet showing how the alias is invoked and what a verify/stop condition looks like.

Make the config-change workflow explicit with a validate -> fix -> retry checkpoint (e.g. how to verify ~/.pua/config.json after editing).

Specify the 'explicit verify commands and stop conditions' referenced in the body rather than leaving them implied by the aliased pua-loop skill.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence with no padding or explanation of known concepts; every line ('Load and follow the pua-loop skill/protocol', the config-safeguard line) earns its place.	3 / 3
Actionability	'preserve unknown fields and create ~/.pua/ if missing' is concrete, but the core instruction 'Set up or run iterative verification loops with explicit verify commands and stop conditions' is abstract with no executable commands or examples, so it is incomplete guidance rather than copy-paste ready.	2 / 3
Workflow Clarity	A risky config-modification step is mentioned but the only checkpoint is the implicit 'Do not claim completion without command/output evidence'; there is no explicit validate-then-fix feedback loop for the config change, capping workflow clarity at 2.	2 / 3
Progressive Disclosure	The skill is well under 50 lines with no bundle files and a single clearly organized heading; for a simple skill this meets the 'well-organized sections' bar for a 3 without needing external file references.	3 / 3
	Total	10 / 12 Passed

Description

50%Weight 40%Scale 1-3

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 identifies the skill as a Codex alias for the Claude Code /pua:loop command with a concrete invocation path, but it lacks an explicit 'when to use' trigger and is light on concrete capabilities. It sits at the middle anchor across all dimensions.

Suggestions

Add an explicit 'Use when...' clause stating when Claude should invoke this alias (e.g. iterative verification loops).

List a couple more concrete actions the alias performs rather than only 'subcommand mapping' and 'invoke'.

Include natural-language trigger terms a user might actually say (e.g. 'verification loop', 'run pua loop') alongside the CLI tokens.

Dimension	Reasoning	Score
Specificity	Phrases like 'Codex subcommand mapping' and 'invoke with $pua-loop' name the domain and an action, but the action set is thin and not comprehensive, so it sits at the 'names domain and some actions' anchor rather than the multiple-concrete-actions anchor at 3.	2 / 3
Completeness	It states what the skill is (an alias/subcommand mapping) but has no 'Use when...' clause or explicit trigger guidance, so per the judging guideline completeness is capped at 2.	2 / 3
Trigger Term Quality	Terms '/pua:loop', '$pua-loop', and 'Codex subcommand' are relevant but lean toward CLI jargon and miss common natural-language variations a user might say, matching the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	It is tied to a specific command ('/pua:loop', '$pua-loop') giving it a niche, but the phrasing could still overlap with generic loop/verification skills, matching the 'somewhat specific but could overlap' anchor.	2 / 3
	Total	8 / 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: 23 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.