CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

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 and well-structured with strong validation feedback loops and a clean one-level reference layer, but it is longer than necessary due to duplicated flavor/Owner tables that inflate the token budget without adding new guidance.

Suggestions

Deduplicate the flavor tables: the keyword/methodology table (lines 139-155) and the opening-line table (lines 177-192) largely restate each other — collapse into one table and defer variants to references/flavors.md.

Merge the two Owner意识 sections (lines 101-107 'Owner 意识 / 冰山下面' and lines 200-216 'Owner 意识(谁痛苦谁改变)') into a single block to remove redundancy.

Move the per-flavor opening-line demonstrations into references/flavors.md so SKILL.md keeps only the routing table and load instructions as the overview.

DimensionReasoningScore

Conciseness

At ~439 lines the body is mostly efficient and does not explain concepts Claude already knows, but it suffers noticeable duplication — the flavor keyword table and opening-line table each appear twice (lines 139-155 and 177-192) and Owner意识 is repeated (lines 101-107 and 200-216) — so it could be meaningfully tightened. Not below 3 because the padding is redundant protocol detail rather than generic over-explanation.

3 / 5

Actionability

Provides concrete executable templates ([PUA-DIAGNOSIS] line, [PUA-CHECKPOINT] schema, sub-agent spawn snippet, feedback.jsonl format), explicit failure-count-to-level tables, and a checkable 7-item checklist; minor gaps keep it just below copy-paste-perfect.

4 / 5

Workflow Clarity

The pressure-escalation L0-L4 sequence, the 6-step confidence-gating loop with explicit validate→fix→retry feedback, and the mandatory L3 7-item checklist provide clear sequencing with explicit validation checkpoints and error-recovery loops.

5 / 5

Progressive Disclosure

SKILL.md is an overview with clearly signaled one-level-deep references (all real files in references/, each annotated with when to load it), but a fair amount of content (full flavor tables, keyword libraries) is inlined that could live in flavors.md, leaving minor organization gaps.

4 / 5

Total

16

/

20

Passed

Description

95%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 exceptionally specific: it states what the skill does, enumerates a rich set of natural bilingual trigger phrases, and includes an explicit negative-boundary clause. It is clearly distinguishable from generic productivity skills.

DimensionReasoningScore

Specificity

Names concrete actions ('coaching', 'evidence/completion check/test before done', 'Ding-style workplace reminders') and several trigger behaviors, but frames most content as trigger conditions rather than distinct performed actions, leaving minor coverage gaps versus the comprehensive 5-anchor.

4 / 5

Completeness

Explicitly answers both what ('PUA/try-harder productivity coaching') and when (a long explicit trigger list plus a negative-boundary clause 'Do not use for calm first-attempt requests') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural-term coverage in both English and Chinese ('try harder', 'again??', 'why still failing', '别摆烂', '证据呢', '闭环', '自嗨') including synonyms and slang, exactly matching the comprehensive-coverage-with-synonyms anchor.

5 / 5

Distinctiveness Conflict Risk

Clear niche (aggressive workplace-flavored productivity coaching) with highly specific bilingual triggers and an explicit exclusion clause, yielding minimal conflict risk with other skills.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository

tanweai/pua

Path

skills/pua/SKILL.md

Reviewed

Table of Contents

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.