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

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./.trae/skills/pua-en/SKILL.md

Quality

Content

62%

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 clear, well-sequenced workflows and strong validation emphasis, but it is far too verbose for its token budget and ships as a monolithic file with no progressive disclosure of its large flavor-pack and team-integration material.

Suggestions

Move the Corporate PIP Flavor Pack and Agent Team Integration into separate reference files (e.g., FLAVORS.md, AGENT_TEAM.md) and keep SKILL.md as a concise overview with one-level-deep links.

Collapse the redundant flavor variants into a compact table of trigger→flavor mappings, since they restate the same core principles many times.

Bundle the referenced agents/pua-enforcer.md (or remove the dangling reference) so the file listing matches what the body points to.

Dimension	Reasoning	Score
Conciseness	The ~340-line body is heavily padded: the Corporate PIP Flavor Pack restates the same handful of leadership principles (Ownership, Bias for Action, Dive Deep, verify-with-evidence) across 7+ corporate-dialect variants, repeating ideas already covered in the Non-Negotiables and Anti-Rationalization Table rather than adding new guidance.	1 / 3
Actionability	For an instruction skill it gives concrete, executable guidance: a 5-step methodology with specific sub-actions ('search the complete error message', '50 lines of context around the error'), numbered checklists, an excuse→counter-attack→escalation table, a failure-mode selector, and copy-paste-ready output formats ([Auto-select: ...] and [PIP-REPORT]).	3 / 3
Workflow Clarity	Multi-step processes are clearly sequenced (the 5-step methodology and its 5 ordered Elevate dimensions), explicit validation is enforced throughout ('Verify with tools, not words', the mandatory proactivity checklist), and there are feedback loops plus a gated exit ('A Dignified Exit' requires all 7 checklist items completed).	3 / 3
Progressive Disclosure	There are no bundle files and the entire skill is a single ~340-line monolith; section headers provide decent organization, but large blocks (the Corporate PIP Flavor Pack, Agent Team Integration) are content that should be split into separate reference files, and an external file (agents/pua-enforcer.md) is referenced but not bundled.	2 / 3
	Total	9 / 12 Passed

Description

67%

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 third-person, answers both what and when with explicit triggers, and names a distinctive behavioral niche, but its named actions are somewhat abstract and a few trigger terms are more jargon than natural user phrasing.

Suggestions

Replace abstract actions ('structured troubleshooting', 'evidence-first delivery habits') with concrete behaviors a user can recognize, mirroring the specificity of the body's checklists.

Swap jargon trigger terms ('passive behavior', 'completion-quality issues') for phrasings a user would naturally say (e.g., 'agent gives up', 'ships without verifying').

Tighten the 'when' clause into an explicit 'Use when...' form to lock in the completeness score.

Dimension	Reasoning	Score
Specificity	Names the domain ('Performance-coaching mode') and a couple of action-types ('structured troubleshooting and evidence-first delivery habits'), but the actions are more abstract than the concrete multi-action list expected at level 3, and it is not comprehensive.	2 / 3
Completeness	It states what the skill does ('Performance-coaching mode... Uses structured troubleshooting and evidence-first delivery habits') and gives equivalent explicit trigger guidance via 'for repeated failures, passive behavior, completion-quality issues, or explicit try-harder requests', so both what and when are answered; the missing-'Use when' cap does not apply.	3 / 3
Trigger Term Quality	Lists relevant trigger phrases ('repeated failures', 'completion-quality issues', 'explicit try-harder requests'), and 'try-harder' is natural, but terms like 'passive behavior' and 'completion-quality issues' read as jargon and common variations a user would actually say are missing.	2 / 3
Distinctiveness Conflict Risk	The behavioral-coaching niche is fairly distinctive, but the skill itself lists pairings with systematic-debugging and verification-before-completion, indicating real overlap with adjacent debugging/verification skills rather than a clean isolated trigger set.	2 / 3
	Total	9 / 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: .trae/skills/pua-en/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.