CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

69%

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

Fix and improve this skill with Tessl

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

Quality

Content

71%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.

A well-structured, opinionated routing map with concrete decision branches and unusually strong context-management guidance for an instruction-only skill. Its main defects are a broken bundle reference (PHASE-BOUNDARIES.md is cited but absent) and moderate duplication of explanations across sections.

Suggestions

Ship the referenced PHASE-BOUNDARIES.md in the skill's bundle, or remove the link and inline the five questions it promises — as written, the body's only progressive-disclosure pointer is broken.

Deduplicate the repeated explanations of /grill-me vs /grill-with-docs, /prototype, and /retro by stating each once and cross-referencing (e.g. "见「独立 skills」") from the main flow.

Add tie-breaking criteria for the judgment-call branches (e.g. when to prefer /implement-spec over per-ticket /implement beyond "当你更想编排这次 build").

DimensionReasoningScore

Conciseness

The body is dense and assumes Claude's competence — no filler explaining known concepts, and each skill entry is packed with routing rationale. It falls short of 5 because several explanations are duplicated (grill-me vs grill-with-docs, /prototype, and /retro are each described twice in different sections) and could be tightened with cross-references. Not 3: the redundancy is limited and serves self-contained routing entries rather than padding.

4 / 5

Actionability

Concrete decision branches (multi-session yes/no, working-directory test, "能否在对话中解决所有问题"), specific paths (".scratch/<feature>/issues/", "prototype/<name> branch"), and explicit thresholds (~150k token smart zone) make the guidance mostly executable. Not 5: some routing choices remain judgment calls ("当你更想编排这次 build") without tie-breaking criteria.

4 / 5

Workflow Clarity

The main flow (idea -> ship) is clearly sequenced with numbered steps, on-ramps are well-defined, and context-hygiene rules act as checkpoints ("步骤 1 到 /to-tickets 要留在同一个未中断的 context window 中"). Not 5: checkpoints are advisory guardrails rather than explicit validate-fix-retry loops, and this is not a destructive/batch skill so the cap does not apply.

4 / 5

Progressive Disclosure

Sections are well-organized and the one deep-dive reference is clearly signaled ("阅读 [PHASE-BOUNDARIES.md](PHASE-BOUNDARIES.md)"), but that file does not exist in the bundle — there are no references/, scripts/, or assets/ directories at all. Scoring against the actual bundle structure, the sole one-level-deep reference is broken, leaving the promised detail nowhere to go. Not 4: a clearly signaled but missing reference is a structural defect, not a minor organization gap.

3 / 5

Total

15

/

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 states what the skill is (a router for all skills in the repo) in third person, but lacks an explicit "Use when..." trigger clause and comprehensive trigger-term coverage. It is distinguishable from other skills yet under-specified for auto-selection scenarios.

Suggestions

Add an explicit trigger clause, e.g. "当你不知道该用哪个 skill 或流程时使用" (Use when you don't know which skill or process applies).

Broaden natural trigger terms and synonyms users would actually say, such as "该用哪个 skill"、"选哪个流程"、"workflow"、"问 Matt".

Enumerate one or two more concrete capabilities (e.g. reads each skill's SKILL.md and recommends a path) to raise specificity from domain-plus-one-action to a fuller capability list.

DimensionReasoningScore

Specificity

The description names its domain ("询问当前情境适合哪个技能或流程") and one-two concrete functions ("它是本仓库所有 skills 的路由器"), matching the anchor for domain plus 1-2 concrete actions without comprehensive coverage. It does not reach 4 because it lists no broader set of specific capabilities.

3 / 5

Completeness

The "what" is clear (router for all skills in this repo), but there is no explicit "Use when..." clause or equivalent trigger guidance — "当前情境" only weakly implies the when. Per the judging guideline, a missing explicit trigger clause caps completeness at 3.

3 / 5

Trigger Term Quality

It includes relevant keywords like "技能", "流程", and "路由器", but misses natural variations a user would say (e.g. "该用哪个 skill", "workflow", "不知道选哪个流程"). Some relevant keywords but missing common synonyms matches anchor 3.

3 / 5

Distinctiveness Conflict Risk

"它是本仓库所有 skills 的路由器" carves out a distinct meta-skill niche (routing/dispatch) with minor overlap risk. Not 5 because the description provides no distinctive trigger phrases that lock in its niche against adjacent skills.

4 / 5

Total

13

/

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

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

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.