nopua

The anti-PUA. Drives AI with wisdom, trust, and inner motivation instead of fear and threats. Activates on: task failed 2+ times, about to give up, suggesting user do it manually, blaming environment unverified, stuck in loops, passive behavior, or user frustration ('try harder', 'figure it out', '换个方法', '为什么还不行'). ALL task types. Not for first failures.

Quality

76%

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 ./skills/nopua/SKILL.md

Quality

Content

62%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.

A well-structured, genuinely actionable behavioral methodology with strong workflow sequencing, but it suffers from heavy cross-section redundancy and a monolithic single-file layout that should be split into references. Conciseness and progressive disclosure are the weakest dimensions.

Suggestions

Consolidate redundancy: state 'tool-verify, don't mouth-verify' and 'going in circles' once each in an authoritative section and reference it, instead of restating across ~6 and ~3 sections respectively, to cut length and token cost.

Split the monolith into progressive disclosure: move the Seven Ways detail, Honest Self-Check Table, and Agent Team Integration into reference files (e.g. SEVEN-WAYS.md, TEAM-INTEGRATION.md) and keep a concise overview in SKILL.md linking to them.

Separate executable procedure from motivational framing: lead each section with the concrete steps (search exact error, read 50 lines context, curl/build/test, paste output) and trim the philosophical self-talk so actionability is not diluted by prose.

Dimension	Reasoning	Score
Conciseness	The 458-line body carries useful novel methodology but is heavily padded: 'tool-verify, don't mouth-verify' recurs across ~6 sections, 'going in circles' across ~3, and Dao De Jing quotes plus 'replacing X' reframings repeat the same ideas; it is more than 'could be tightened' yet not pure fluff, so it lands at 2 rather than 1 or 3.	2 / 3
Actionability	It supplies concrete, specific guidance — exact commands (curl/build/test), 'read 50 lines of context', a [NOPUA-REPORT] template, an Auto-Selection format string, and copy-paste checklists — but this is diluted by extensive motivational self-talk and philosophical reframing rather than uniformly executable steps, matching the 'some concrete guidance but incomplete/mixed' anchor.	2 / 3
Workflow Clarity	Multi-step processes are clearly sequenced with checkpoints: the Water Methodology (Stop→Observe→Turn→Act→Realize), the 7-Point Clarity Checklist, Cognitive Elevation keyed by failure count with mandatory actions, and a multi-round Situation Wisdom Selector — together forming explicit validation steps and failure-count feedback loops.	3 / 3
Progressive Disclosure	No bundle files exist and the skill is a single 458-line monolith with well-organized sections but no file-level disclosure; content that belongs in references (Seven Ways, Honest Self-Check Table, Agent Team Integration) is inline, and the only cited reference (agents/nopua-mentor.md) is not present in the bundle — matching 'some structure, content that should be separate is inline'.	2 / 3
	Total	9 / 12 Passed

Description

90%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.

A strong description that explicitly covers what the skill does, when to activate it, and when not to, with natural multilingual user-frustration trigger phrases. Its only weakness is an abstract, buzzword-laden action statement in place of concrete capability verbs.

Dimension	Reasoning	Score
Specificity	It names the domain ('The anti-PUA', 'Drives AI with wisdom, trust, and inner motivation') and concrete trigger behaviors ('task failed 2+ times', 'stuck in loops'), but the action statement is abstract and buzzword-heavy rather than listing concrete actions the skill performs; not score 1 because the trigger list adds concreteness, not score 3 because no multiple specific concrete actions are enumerated.	2 / 3
Completeness	It clearly answers what ('Drives AI with wisdom, trust, and inner motivation instead of fear and threats') and when ('Activates on: task failed 2+ times, about to give up...') with an explicit negative trigger ('Not for first failures.'), matching the anchor that requires both what AND when with explicit triggers.	3 / 3
Trigger Term Quality	Explicit natural user phrases are quoted directly — 'try harder', 'figure it out', '换个方法', '为什么还不行' — alongside behavioral states users would actually express, giving good coverage of natural trigger terms.	3 / 3
Distinctiveness Conflict Risk	The trigger set (2+ failures, about to give up, stuck in loops, specific user-frustration phrases) carves a clear niche in motivational/behavioral reframing of failure states that is unlikely to fire for the wrong skill, despite the broad 'ALL task types' scope.	3 / 3
	Total	11 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: wuji-labs/nopua
Path: skills/nopua/SKILL.md
Commit: bf4b2b6

Reviewed: 12 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.