ding

Use for Ding-style (钉内/钉外) workplace reminders rooted in the 7.5万字 essay 《置身钉内》 and VP response 《置身钉外》. Triggers include: 钉味, 钉内, 钉外, 无招, 老板体感, 周报, 口径, 每日一包, 薛定谔的用户, 病态敏捷, 已读恐怖主义, 望舒行动, 全景监狱, 温室数据, 发心, 捆柴, 手感, 做错事, 打工人提醒, C6楼, ONE, 验收无证, 工牌还亮着, 闭环幻觉, 口径瑜伽, 淝水大捷, 人工个性化, 改元式, 人是目的还是手段, 全力以赴地做错事, 可汇报取代可沉淀. Do not use for pure coding tasks with no workplace/org/delivery context.

Quality

84%

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

Quality

Content

78%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 a well-organized, lean overview with concrete output formats, a scenario-routing table, and clean one-level-deep references to bundled material. The main weakness is minor redundancy between the body and the methodology reference file.

Suggestions

Trim the scenario-routing table and default-reminder block from the body since they are duplicated in methodology-ding.md, keeping only a pointer to that file.

For routed scenarios that currently stay abstract (e.g. "冻结原口径，新增解释字段"), add one concrete executable step so the guidance is copy-paste ready.

The instruction to immediately read all three reference files somewhat undercuts on-demand disclosure; consider marking which file is needed only for complex tasks (as already done for display-protocol.md).

Dimension	Reasoning	Score
Conciseness	The ~83-line body is lean and assumes Claude's competence with no over-explanation of known concepts; it is not a 5 because the scenario-routing table and default-reminder block are duplicated in methodology-ding.md and could be trimmed.	4 / 5
Actionability	It gives a concrete blockquote output format, an exact execution-layer field template, an exact config path and content ("~/.pua/config.json" -> {"flavor": "ding"}), and a scenario-to-action routing table, matching anchor 4; not a 5 because some routed scenarios remain abstract rather than copy-paste ready.	4 / 5
Workflow Clarity	A clear sequence is present (immediately read three files -> route by scenario -> output per format) and the status field (candidate / needs_check / done_with_evidence) acts as a checkpoint, matching anchor 4; there are no destructive/batch operations requiring the cap.	4 / 5
Progressive Disclosure	The body is a clear overview pointing to three well-signaled one-level-deep references, each annotated with its purpose and read-condition, with content appropriately split across the bundled reference files, matching anchor 5.	5 / 5
	Total	17 / 20 Passed

Description

90%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 a strong, complete trigger specification: it states a clear niche purpose, an extensive list of natural trigger terms, and an explicit negative boundary. The only weakness is that the stated action ("reminders") is single and generic rather than a list of several concrete capabilities.

Dimension	Reasoning	Score
Specificity	"Use for Ding-style (钉内/钉外) workplace reminders rooted in the 7.5万字 essay" names the domain and one concrete action (produce reminders), matching anchor 3; it is not a 2 because a clear concrete action is stated, and not a 4 because only one action is given rather than several.	3 / 5
Completeness	It explicitly answers both what (Ding-style workplace reminders rooted in the named essays) and when (an explicit "Triggers include" list plus "Do not use for pure coding tasks"), matching anchor 5.	5 / 5
Trigger Term Quality	The description lists 30+ natural trigger terms a user in this subculture would actually say, including synonyms (钉味/钉内/钉外) and an explicit negative boundary, matching the comprehensive-coverage anchor 5.	5 / 5
Distinctiveness Conflict Risk	The triggers are a highly niche Chinese workplace-essay vocabulary unlikely to match other skills, and the explicit "Do not use for pure coding tasks" exclusion further sharpens the niche, matching anchor 5.	5 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: tanweai/pua
Path: skills/ding/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.