nopua-zh

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

77%

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-zh/SKILL.md

Quality

Content

65%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 thorough, genuinely actionable behavioral skill with strong templates and checklists, weakened by heavy cross-sectional repetition of the same guidance and a monolithic structure containing a dangling file reference. The Daoist framing adds length without proportional operational value.

Suggestions

De-duplicate the repeated verify/build/test guidance that recurs across the spectrum table, 7-item checklist, and the 炉火/践行/耕种道 sections; state it once and reference it, to lift conciseness toward 3.

Move the five 道 and/or the Agent Team integration (long, self-contained blocks) into reference files and link to them one level deep, turning the body into a true overview.

Resolve the missing agents/nopua-mentor.md reference (create the file or drop the mention) to fix the progressive-disclosure navigation defect.

Reframe verification as an explicit gated loop ('run validate → if fail, fix & re-run → only when green, proceed') within the methodology steps to strengthen workflow clarity.

Dimension	Reasoning	Score
Conciseness	Accurate and useful, but heavily padded: the same operational messages ('用工具验证，不要用嘴验证', the 7-item checklist, build/test/curl verification) are restated verbatim across the spectrum table, checklist, and the overlapping 道 sections (炉火/践行/耕种), plus Daoist-quote ornamentation.	2 / 3
Actionability	Provides concrete, actionable guidance: a numbered 5-step methodology with sub-steps, a 7-item checklist with per-task-type equivalents, a passive→active spectrum table, a 5-item structured handoff report, and a concrete [NOPUA-REPORT] message template.	3 / 3
Workflow Clarity	Multi-step processes are clearly sequenced (止→观→转→行→悟, failure-count cognitive escalation, decision selector table), but validation is framed as mindset reminders rather than an explicit validate→fix→re-validate→only-then-proceed gated loop.	2 / 3
Progressive Disclosure	Single-file skill with no bundle directories and well-demarcated sections, but it is a ~460-line monolithic body with no offloaded references, and one body reference (agents/nopua-mentor.md) does not exist on disk.	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 clearly states both purpose and activation triggers with concrete, natural-language trigger terms in two languages. The main weakness is that the capability side is framed abstractly ('wisdom, trust, inner motivation') rather than as concrete operations.

Suggestions

Pair the abstract capability framing with one or two concrete actions (e.g., 'runs the 5-step diagnostic, executes the 7-item self-check, produces a structured handoff report') to lift specificity to 3.

Tighten the mildly generic triggers ('stuck in loops', 'passive behavior') by tying them to the concrete failure modes defined later in the body to further reduce conflict risk.

Dimension	Reasoning	Score
Specificity	Lists concrete trigger conditions ('task failed 2+ times, about to give up, suggesting user do it manually, blaming environment unverified, stuck in loops, passive behavior'), but the action side ('Drives AI with wisdom, trust, and inner motivation') is abstract rather than naming multiple concrete operations.	2 / 3
Completeness	Explicitly answers both what ('The anti-PUA. Drives AI with wisdom, trust, and inner motivation') and when ('Activates on: ...', 'Not for first failures'), with an explicit trigger clause and scope exclusion.	3 / 3
Trigger Term Quality	Good coverage of natural phrases users would actually say ('try harder', 'figure it out', '换个方法', '为什么还不行', 'about to give up', 'stuck in loops') in both English and Chinese.	3 / 3
Distinctiveness Conflict Risk	The anti-give-up/persistence-coaching niche with explicit trigger set and 'Not for first failures' exclusion is recognizable and unlikely to fire for unrelated skills, though terms like 'stuck in loops'/'passive behavior' are mildly generic.	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-zh/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.