pua-en

Trae-compatible English PUA/PIP high-agency governance skill. Use only for explicit PUA/PIP requests, repeated failures, user frustration, passive/giving-up behavior, or unverified completion. Not for normal first-attempt tasks.

Quality

86%

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

85%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 body is a tight, well-structured governance contract with concrete templates and a strong validation-driven workflow including an error-recovery loop. Its only real weakness is mild verbosity from the cultural-narrative and 'INTJ insight' flavor that does not always advance the procedure.

Suggestions

Tighten the 'Cultural narrative' section and drop the 'INTJ insight' line unless each tag is directly tied to a concrete action Claude must take, to lift conciseness toward 5.

Make the confidence-loop steps more executable by giving a minimal worked example of the diagnosis line and a concrete example of switching approaches after two failures.

Consider converting the 'Use only when' triggers in the body into a short checklist so the gating condition is scannable alongside the workflow.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient, using a duties table and numbered loop instead of prose, and avoids re-explaining basics Claude already knows; however the 'INTJ insight' line and the cultural-narrative section add flavor that could be trimmed, so not every token earns its place.	4 / 5
Actionability	Provides concrete, copy-paste-ready templates (the '[PUA-DIAGNOSIS]' one-liner and the fill-in delivery template) and specific check types (unit/integration/build/lint/curl/E2E), but several loop steps ('State 2-3 mutually exclusive hypotheses', 'Choose the smallest verifiable action') stay at the guidance level with minor gaps.	4 / 5
Workflow Clarity	The 'De facto 100% confidence loop' is a clearly sequenced 6-step process with explicit validation checkpoints (run a check, after two failures switch approach, provide evidence before delivery, stop for user confirmation) and a built-in error-recovery feedback loop, matching the top anchor.	5 / 5
Progressive Disclosure	It is a single self-contained file with no bundle files and well-organized section headers; nothing that belongs in a separate file is inlined or buried, and no external references are needed, so the well-sectioned overview is sufficient.	5 / 5
	Total	18 / 20 Passed

Description

87%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 well-constructed: it states a distinct purpose, gives concrete trigger conditions, and includes an explicit negative boundary that prevents misfiring on routine tasks. Its only weakness is that the core 'what' relies on the somewhat abstract phrase 'high-agency governance skill'.

Dimension	Reasoning	Score
Specificity	Lists several specific trigger conditions ('explicit PUA/PIP requests, repeated failures, user frustration, passive/giving-up behavior, or unverified completion') rather than vague language, though the core 'what' ('high-agency governance skill') stays somewhat abstract, so it falls just short of comprehensive concrete actions.	4 / 5
Completeness	Clearly answers both 'what' (PUA/PIP high-agency governance) and 'when' via an explicit 'Use only for ...' clause with concrete trigger phrases plus a 'Not for normal first-attempt tasks' negative boundary, matching the anchor that requires both with concrete triggers.	5 / 5
Trigger Term Quality	Good coverage of natural trigger phrases a user would express ('repeated failures', 'user frustration', 'giving-up behavior', 'unverified completion'), but 'PUA/PIP' is niche jargon and a few common synonyms are missing, so not fully comprehensive.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (high-agency PUA/PIP governance) with distinct, specific triggers and an explicit exclusion ('Not for normal first-attempt tasks'), giving minimal overlap risk with other skills.	5 / 5
	Total	18 / 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: .trae/skills/pua-en/SKILL.md
Commit: ac50267

Reviewed: 7 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.