p9

P9 Tech Lead mode — write Task Prompts, manage P8 agent teams, never write code yourself. Use when user says 'P9模式', 'tech-lead', '帮我管理这个项目', '任务拆解', or when coordinating 3+ parallel agents. Produces: Task Prompts (六要素) + P8 team delivery.

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/p9/SKILL.md

Quality

Content

37%

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 minimal stub that defers all substance to external files which are not present in the bundle, leaving it non-actionable and workflow-less on its own. It is token-efficient and structurally well-signaled, but the missing references and absence of any inline guidance are the dominant weaknesses.

Suggestions

Inline the core actionable essentials directly in SKILL.md — the 六要素 Task Prompt structure, the three red lines, and the aside protocol — so the skill works without the missing external files (actionability).

Add an explicit sequenced P9 workflow with validation checkpoints (decompose task → write Task Prompts → dispatch to P8 team → verify delivery) rather than deferring entirely to a protocol file (workflow_clarity).

Create the referenced bundle files or relocate the detail into ./references/ so the signaled paths (`../pua/references/p9-protocol.md`, `agent-team.md`) actually resolve (progressive_disclosure).

Dimension	Reasoning	Score
Conciseness	The body is six lean lines with no padding and no explaining of concepts Claude already knows; every line points somewhere or states a constraint.	3 / 3
Actionability	It offers only abstract pointers ('详细协议见 ... 加载后按协议执行', '架构详见 ...', '遵循 ... 三条红线和旁白协议') with no concrete code, commands, or specific guidance — and the referenced files do not exist, so even the pointers are broken.	1 / 3
Workflow Clarity	There is no sequenced workflow or validation checkpoint despite this being a multi-step coordination skill; all process detail is deferred to a missing external protocol file.	1 / 3
Progressive Disclosure	The one-level-deep references are clearly signaled, but they point to non-existent files (`../pua/references/p9-protocol.md`, `../pua/references/agent-team.md`) and the body holds no real overview content of its own, so the disclosure is only partially functional.	2 / 3
	Total	7 / 12 Passed

Description

90%

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, well-structured description with explicit 'Use when ...' triggers, concrete produced artifacts, and a distinct niche. The only knock is voice: imperative/second-person phrasing ('write ... yourself') triggers the rubric's specificity penalty.

Dimension	Reasoning	Score
Specificity	It lists multiple concrete actions ('write Task Prompts, manage P8 agent teams, never write code yourself', 'Produces: Task Prompts (六要素) + P8 team delivery'), which would be a 3, but the rubric penalizes second-person/imperative voice ('write ... yourself') by reducing specificity by 1, yielding 2.	2 / 3
Completeness	It clearly answers both what it does (writes Task Prompts, manages P8 teams, produces deliverables) and when to use it via an explicit 'Use when ...' clause, matching the top anchor and avoiding the missing-trigger cap of 2.	3 / 3
Trigger Term Quality	It gives good coverage of natural terms a user would actually say across two languages — 'P9模式', 'tech-lead', '帮我管理这个项目', '任务拆解', and 'coordinating 3+ parallel agents'.	3 / 3
Distinctiveness Conflict Risk	It occupies a clear niche (P9 Tech Lead mode within the PUA framework) with distinct, framework-specific triggers, making it unlikely to fire for an unrelated skill.	3 / 3
	Total	11 / 12 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/p9/SKILL.md
Commit: 3fd4e5a

Reviewed: 2 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.