pua-loop

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

Quality

59%

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

61%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 content is admirably concise and lean, but its actionability is weak because the central loop mechanics (verify commands, stop conditions) are named rather than specified, and it delegates to an external protocol that is not bundled. The workflow is implied and verification is mentioned but not structured into checkpoints.

Suggestions

Specify concrete verify commands and stop conditions (or at least concrete examples) instead of only naming that they should be 'explicit'.

Add executable steps for the config hygiene rules (e.g., 'mkdir -p ~/.pua' and a concrete method for preserving unknown fields when editing ~/.pua/config.json).

Number the workflow steps and mark explicit validation checkpoints (validate config after change; confirm evidence before declaring completion).

Dimension	Reasoning	Score
Conciseness	The body is a lean ~5-line instruction set with no concept over-explanation and no padding; every line (alias identity, protocol delegation, config hygiene, evidence rule) earns its place, matching the 'lean and efficient; assumes Claude's competence' anchor.	5 / 5
Actionability	It provides minimal concrete guidance — config-dir creation and field preservation are named but without executable commands, and the core task ('iterative verification loops with explicit verify commands and stop conditions') names the required elements without specifying what they are or how to run them, matching 'high-level hints but missing the specific steps to execute'.	2 / 5
Workflow Clarity	An implied sequence exists (load protocol, set up/run loops, handle config changes, require evidence before claiming completion) and verification is explicitly invoked ('explicit verify commands', 'command/output evidence'), but the steps are not numbered and checkpoints are implicit rather than structured, matching 'sequence present but checkpoints missing or implicit'.	3 / 5
Progressive Disclosure	The short body is well-organized for a small alias skill and signals its one external reference ('Load and follow the pua-loop skill/protocol'), but it has no section headers and the referenced skill is not bundled, leaving it just below the 'clear overview with well-signaled one-level-deep references' top anchor.	4 / 5
	Total	14 / 20 Passed

Description

57%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 is concise and clearly identifies the skill's niche as a Codex alias for the pua:loop command, but it lacks an explicit 'when to use' trigger clause and leans on technical phrasing over natural user keywords. Its distinctiveness is strong due to the highly specific invocation terms.

Suggestions

Add an explicit 'Use when...' clause stating when Claude should invoke this alias (e.g., 'Use when running iterative verification loops in Codex or when the user references pua loop / pua:loop').

Replace technical phrasing like 'Codex subcommand mapping' with natural user-facing terms and synonyms users would actually say.

Expand the capability list beyond 'invoke' to concrete actions such as setting up, running, and stopping verification loops.

Dimension	Reasoning	Score
Specificity	Names the domain ('Codex subcommand mapping', 'Claude Code /pua:loop style usage') and a concrete action ('invoke with $pua-loop'), but does not enumerate multiple concrete capabilities, so it sits at the '1-2 concrete actions, not comprehensive' anchor rather than the comprehensive 4-5.	3 / 5
Completeness	It gives a clear 'what' (an alias/mapping for the pua:loop command) but no explicit 'Use when...' trigger clause, so per the missing-trigger guidance completeness is capped at 3 with 'when' only weakly implied by the invocation phrase.	3 / 5
Trigger Term Quality	It surfaces the core term 'PUA Loop' and the invocation syntax '/pua:loop' and '$pua-loop', but the phrasing is technical ('Codex subcommand mapping') and lacks natural user variations or synonyms, matching 'some relevant keywords but missing common variations'.	3 / 5
Distinctiveness Conflict Risk	It carves a clear niche ($pua-loop / /pua:loop aliasing for Codex) with distinct triggers and minimal overlap with other skills, matching the 'clear niche with distinct triggers; minimal conflict risk' anchor; not lowered because no neighbor anchor fits better.	5 / 5
	Total	14 / 20 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: ac50267

Reviewed: 10 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.