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

67%

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

51%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 token-efficient stub that correctly intends to defer to protocol and core-skill references, but as shipped it is non-functional: every detailed artifact it points to is missing, leaving the skill with no self-contained actionable guidance or workflow. The structure is sound in intent but broken in practice.

Suggestions

Ship the referenced files (p9-protocol.md and agent-team.md) in a local references/ bundle, or inline the minimum protocol (the 六要素 Task Prompt structure and the 三条红线) so the skill is self-contained.

Add a concrete, sequenced workflow with at least one validation checkpoint (e.g., review Task Prompt against 六要素 before dispatching a P8) rather than a single "load and execute" instruction.

Convert the dead ../pua relative paths to bundle-local references or a clearly-resolvable skill invocation so navigation does not dead-end.

Dimension	Reasoning	Score
Conciseness	The ~10-line body is lean and assumes Claude's competence — each line (red-line tagline, two reference pointers, core-skill deferral) earns its place with no padding or concept re-explanation.	5 / 5
Actionability	The body only delegates ("详细协议见…加载后按协议执行") with no concrete steps of its own, and the referenced files do not exist in the bundle, so the guidance is high-level hints rather than executable direction.	2 / 5
Workflow Clarity	No sequenced process is given; the only implied flow is "load protocol, then execute per protocol," which is poorly defined with no checkpoints, and the protocol it points to is absent.	2 / 5
Progressive Disclosure	References are well-signaled and one level deep ("详见…", "见…"), but the referenced paths (../pua/references/p9-protocol.md, agent-team.md) and the /pua core skill are not present in the bundle, so the promised detail is unreachable.	3 / 5
	Total	12 / 20 Passed

Description

83%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 well-constructed: it pairs concrete capabilities with an explicit, multilingual "Use when" clause and a clear output spec. It is held back only slightly by jargon-bound terms (P8/P9/六要素) that go undefined in the description itself.

Dimension	Reasoning	Score
Specificity	Names concrete actions — "write Task Prompts, manage P8 agent teams, never write code yourself" and an explicit "Produces:" deliverable — but leaves the 六要素 schema undefined, a minor coverage gap.	4 / 5
Completeness	Explicitly states both what it does (Task Prompt authoring, P8 team management, no-code constraint, output deliverable) and when to use it via concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Good multilingual natural triggers ("P9模式", "tech-lead", "帮我管理这个项目", "任务拆解", "coordinating 3+ parallel agents") with cross-language synonyms, though a few common project-management phrasings are missing.	4 / 5
Distinctiveness Conflict Risk	The P9 Tech Lead / manage-P8-not-P7 niche is distinct with dedicated triggers, with only minor overlap risk against generic tech-lead or project-management skills.	4 / 5
	Total	17 / 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/p9/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.