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

80%

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/pua/SKILL.md

Quality

Content

73%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 highly actionable with strong, well-sequenced workflows and validation loops, and it makes good use of a deep reference bundle. Its main weakness is conciseness: redundant flavor tables and a couple of minor navigation issues keep it from being fully lean.

Suggestions

Remove the duplicated 味道速查 flavor table (lines 161-176); keep a single keyword/旁白 table and point detailed variants to references/flavors.md to reclaim a large block of redundant tokens.

Fix the harness-governance.md reference path to the actual bundle location (references/harness-governance.md) so the navigation pointer resolves correctly.

Consolidate the two 开工旁白 example blocks (lines 143-153 and the per-flavor rows at 161-176) into one canonical example set to reduce repeated content.

Dimension	Reasoning	Score
Conciseness	The 422-line body is mostly skill-specific and actionable, but the flavor keyword/旁白 tables are duplicated twice (the 关键词库 table and the later 味道速查 table repeat ~15 rows of near-identical content), which is noticeable padding that should be tightened.	3 / 5
Actionability	Provides concrete executable artifacts — the [PUA-DIAGNOSIS] output template, [PUA生效 🔥] markers, decision tables mapping failure modes to flavor switches, a 7-item checklist, and a copy-paste sub-agent prompt injection block — with only minor details (exact banner drawing) deferred to references.	4 / 5
Workflow Clarity	Multi-step processes are clearly sequenced with explicit validation checkpoints and feedback loops: the 5-step 通用方法论, the 6-step 信心门控 Confidence Gate that loops back to 找漏洞, and the 7-item L3 checklist, all reinforced by the 闭环/evidence red lines.	5 / 5
Progressive Disclosure	Good one-level-deep structure with clearly signaled references (display-protocol, methodology-router, flavors, methodology-{company}, de-escalation-protocol) that resolve to real bundle files, but the harness-governance.md pointer uses an inconsistent path ('skills/pua/references/...') and the duplicated inline flavor tables belong better in flavors.md alone.	4 / 5
	Total	16 / 20 Passed

Description

86%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 strong: it explicitly covers what, when, and when-not-to-use with an extensive bilingual set of natural trigger phrases. The only gap is that the concrete capabilities/actions are stated minimally rather than enumerated.

Dimension	Reasoning	Score
Specificity	Names the domain ('PUA/try-harder productivity coaching', 'Ding-style workplace reminders') with 1-2 concrete actions but does not enumerate the specific behaviors it performs (pressure escalation, de-escalation, flavor switching), so coverage is not comprehensive.	3 / 5
Completeness	Explicitly answers both what ('PUA/try-harder productivity coaching ... Ding-style workplace reminders') and when ('when the user expresses frustration, repeated failure ... Do not use for calm first-attempt requests') with concrete trigger phrases and a negative trigger.	5 / 5
Trigger Term Quality	Comprehensive coverage of natural trigger phrases in both English ('try harder', 'again??', 'no evidence', 'run tests') and Chinese (换个方法, 别摆烂, 验收, 闭环), including synonyms and slang users would actually say.	5 / 5
Distinctiveness Conflict Risk	The PUA/try-harder framing is a clear niche with distinct triggers and a negative scope clause, but generic triggers like 'run tests', 'no evidence', '验收', '闭环' create minor overlap risk with verification/debugging skills.	4 / 5
	Total	17 / 20 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: ac50267

Reviewed: 10 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.