pua

Use for PUA/try-harder productivity coaching when the user expresses frustration, repeated failure, quality complaint, passive behavior, says retry/change approach/don't give up, asks for evidence/completion check/test before done, or wants Ding-style workplace reminders. Triggers include: try harder, stop giving up, figure it out, again??, why still failing, change approach, no evidence, run tests, done without proof, 换个方法, 再试试, 别摆烂, 别偷懒, 为什么还不行, 又错了, 证据呢, 没跑测试别说完成, 验收, 闭环, 自嗨, 置身钉外, 无招, 老板体感. Do not use for calm first-attempt requests.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

85%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.

The content is highly actionable with clear sequenced workflows, validation checkpoints, and a well-structured progressive-disclosure layout backed by real reference files. Its main weakness is conciseness — the body is long and contains redundant flavor tables and rhetorical padding that could be consolidated.

Suggestions

Merge the two near-identical flavor示范 tables (旁白示范 and 味道速查) into one canonical table to remove significant duplicated content.

Trim the motivational/rhetorical framing paragraphs (e.g. the opening P8 framing) to the minimum needed to set tone, since they do not add actionable guidance.

Consider moving the full per-company keyword/methodology breakdown table to references/flavors.md and keeping only the routing summary inline, reducing SKILL.md length.

Dimension	Reasoning	Score
Conciseness	The body is dense and mostly earns its tokens, but at ~425 lines it includes redundancy (two near-identical flavor示范 tables and repeated flavor lists) and some rhetorical padding, placing it at 'mostly efficient but could be tightened' rather than lean.	2 / 3
Actionability	Highly actionable: exact marker strings ('[PUA生效 🔥]', '[PUA-DIAGNOSIS] ...'), concrete code blocks, lookup tables mapping task types to flavors, and explicit checklists — copy-paste ready guidance throughout.	3 / 3
Workflow Clarity	Multi-step processes are clearly sequenced with explicit validation checkpoints: L0-L4 escalation table, the 5-step 通用方法论, the 7-item L3 checklist, and a confidence-gate loop ('漏洞→修复→验证') with feedback loops for risky operations.	3 / 3
Progressive Disclosure	SKILL.md acts as a clear overview with well-signaled, one-level-deep references (display-protocol, methodology-router, flavors, de-escalation-protocol, harness-governance, and per-company methodology files), all verified to exist as real bundle files; navigation is easy and content is appropriately split.	3 / 3
	Total	11 / 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.

The description is specific, trigger-rich, and complete, with explicit use/non-use guidance that clearly distinguishes it from other skills. Its only mild weakness is that capability specificity leans on trigger enumeration rather than enumerating concrete actions.

Suggestions

Lead with one sentence naming 2-3 concrete capabilities (e.g. 'Applies pressure-coaching voice, failure-count escalation, and evidence-based completion gating') before the trigger list, so 'what it does' is as strong as 'when to use it'.

Dimension	Reasoning	Score
Specificity	Names the coaching domain and the reminder/coaching actions ('productivity coaching', 'Ding-style workplace reminders') but the bulk of the description is trigger enumeration rather than a comprehensive list of concrete capabilities, matching the 'Names domain and some actions' anchor.	2 / 3
Completeness	Explicitly answers both 'what' ('PUA/try-harder productivity coaching ... Ding-style workplace reminders') and 'when' with a clear 'Use for ...' clause, a 'Triggers include:' list, and a 'Do not use for ...' exclusion, satisfying the top anchor.	3 / 3
Trigger Term Quality	Excellent coverage of natural phrases users would actually say in both English ('try harder', 'why still failing', 'run tests') and Chinese ('换个方法', '别摆烂', '证据呢'), matching the 'good coverage of natural terms' anchor.	3 / 3
Distinctiveness Conflict Risk	A clear niche (pressure/coaching behavior) with highly specific triggers and an explicit negative trigger ('Do not use for calm first-attempt requests'), making conflict with other skills unlikely.	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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: tanweai/pua
Path: skills/pua/SKILL.md
Commit: 3fd4e5a

Reviewed: 20 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.