ask-matt

询问当前情境适合哪个技能或流程；它是本仓库所有 skills 的路由器。

Quality

64%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/engineering/ask-matt/SKILL.md

Quality

Content

75%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-structured, dense routing map with concrete decision branches and clear sequencing across the main flow, on-ramps, and standalone skills. Its main weaknesses are minor repetition between sections and a single broken external reference.

Suggestions

Add the missing PHASE-BOUNDARIES.md file (or remove the link) so the one signaled external reference resolves, improving navigation and progressive disclosure.

Consolidate the /grill-with-docs vs /grill-me comparison into a single location and cross-reference it elsewhere to reduce repetition and tighten conciseness.

Tighten the subjective triggers (e.g., define what makes an effort '巨大而模糊' enough to warrant /wayfinder) to push actionability toward fully unambiguous routing.

Dimension	Reasoning	Score
Conciseness	The body is information-dense with each skill earning its place via decision criteria and no padding of concepts Claude already knows; not a 5 because the /grill-with-docs vs /grill-me distinction is re-explained across the main flow, standalone, and vocabulary sections.	4 / 5
Actionability	Concrete if/then routing branches (e.g., '需要可运行的答案…就用 /prototype', 'Bugs 和 requests 堆积 -> /triage') give specific, actionable guidance appropriate for an instruction-only router; not a 5 because some boundaries rely on subjective judgment (e.g., '巨大而模糊的 effort') and a few edges could be sharper.	4 / 5
Workflow Clarity	The main flow (idea -> ship) is explicitly sequenced with numbered steps and decision branches, and Context hygiene / smart-zone limits plus the phase-boundary decision tree act as checkpoints; not a 5 because explicit error-recovery feedback loops are absent (less critical for a non-destructive router).	4 / 5
Progressive Disclosure	Content is well-organized into clear sections with one clearly signaled one-level-deep reference ([PHASE-BOUNDARIES.md]); not a 5 because that referenced file does not actually exist in the bundle, which harms navigation, and not a 3 because the section structure itself is solid rather than inlining content that belongs elsewhere.	4 / 5
	Total	16 / 20 Passed

Description

53%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 clearly conveys the skill's role as a router across the repo's skills but lacks an explicit 'Use when...' trigger clause and relies on fairly generic keywords. It is distinguishable as a meta-router but would benefit from concrete trigger phrasing.

Suggestions

Add an explicit 'Use when...' clause (e.g., 'Use when unsure which skill or process fits the current situation') to lift completeness above the cap of 3.

Include natural user-facing trigger terms and synonyms (e.g., 'which skill should I use', 'pick a workflow', 'route me') to improve trigger-term quality.

Name one or two more concrete routing actions (e.g., 'inspects the situation and recommends the matching skill') to raise specificity.

Dimension	Reasoning	Score
Specificity	Phrases '询问当前情境适合哪个技能或流程' and '它是本仓库所有 skills 的路由器' name the routing domain and one concrete action (ask which skill fits), matching the 'names domain and 1-2 concrete actions' anchor; not a 4 because there is only one action rather than several specific ones.	3 / 5
Completeness	The 'what' is clear (router that asks which skill fits), but there is no explicit 'Use when...' clause — the 'when' is only weakly implied, which per the guidelines caps completeness at 3; not a 4 because trigger guidance is not explicit.	3 / 5
Trigger Term Quality	Terms like 情境 (situation), 技能 (skill), 流程 (process) are relevant but generic, matching 'some relevant keywords but missing common variations'; not a 4 because natural trigger phrasing and synonyms are thin, and 路由器 (router) is technical jargon.	3 / 5
Distinctiveness Conflict Risk	The explicit 'router for all skills' framing carves a distinct meta-skill niche with only minor overlap risk against other question-asking skills; not a 5 because the triggers (situation/skill/process) are not uniquely distinctive.	4 / 5
	Total	13 / 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
relative_links	Relative link issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: vinvcn/mattpocock-skills-zh-CN
Path: skills/engineering/ask-matt/SKILL.md
Commit: 9fb0161

Reviewed: 12 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.