ask-matt

Ask which skill or flow fits your situation. A router over the skills in this repo.

Quality

61%

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 ./.agents/skills/ask-matt/SKILL.md

The canonical home for this skill is ask-matt in mattpocock/skills

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, actionable routing map that earns most of its tokens with genuine decision guidance rather than padding. Its main weaknesses are minor redundant justifications and a single external reference (PHASE-BOUNDARIES.md) that is not present in the bundle.

Suggestions

Provide the missing PHASE-BOUNDARIES.md (or remove the reference) so the one-level-deep navigation actually resolves.

Dedupe the /grill-with-docs-vs-/grill-me rationale to a single canonical statement to tighten conciseness.

Add a compact decision summary or routing table at the top so the common cases can be resolved without reading the full prose.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and avoids explaining concepts Claude already knows, but carries minor over-explanation that could be trimmed, e.g. the /grill-with-docs-vs-/grill-me preference is justified in multiple places ("which makes it the better of the two whenever a repo is there to leave it in"; "so it is strictly the better one").	4 / 5
Actionability	Routing guidance is concrete and actionable, naming specific slash commands (/grill-with-docs, /to-spec, /implement) with clear Yes/No decision branches; minor gaps remain where situations are fuzzy and deferred ("the fuzziest decision in this whole map" for phase boundaries).	4 / 5
Workflow Clarity	The main flow is a clearly numbered sequence (1-3) with explicit branches and context-hygiene checkpoints (keep one unbroken window through /to-tickets; /compact at the smart-zone boundary), but it lacks full feedback-loop validation, fitting 'clear sequence with most checkpoints' rather than 5.	4 / 5
Progressive Disclosure	Sections are well-organized (main flow, on-ramps, vocabulary, phase boundaries, standalone, precondition) and the one external reference is clearly signaled ("Read PHASE-BOUNDARIES.md for the ordered tree..."), but that referenced file is absent from the bundle, a minor organization gap that keeps it below 5.	4 / 5
	Total	16 / 20 Passed

Description

48%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 over repo skills but is held back by second-person voice and the absence of an explicit 'Use when...' trigger clause. Trigger-term coverage is reasonable but lacks synonyms, and distinctiveness is strong for a meta-skill.

Suggestions

Rewrite in third person and add an explicit trigger clause, e.g. "Routes a request to the matching skill or flow in this repo. Use when unsure which skill fits the task or when the user asks which skill to use."

Broaden trigger terms with natural synonyms ("which skill," "which tool," "what should I use," "help me pick a flow") to lift trigger_term_quality toward 5.

Tighten the 'what' to list concrete routing actions (evaluates the situation, recommends a skill or flow, hands off) for fuller specificity.

Dimension	Reasoning	Score
Specificity	"A router over the skills in this repo" names the domain and one concrete action ("Ask which skill or flow fits your situation"), which would anchor at 3, but the second-person "your situation" triggers the voice penalty reducing specificity by one.	2 / 5
Completeness	The 'what' is clear ("A router over the skills in this repo") but there is no explicit 'Use when...' clause; the when is only weakly implied by "Ask which skill or flow fits your situation," so the missing-trigger-guidance cap of 3 applies.	3 / 5
Trigger Term Quality	"which skill or flow fits your situation" captures a fairly natural trigger phrase, but coverage is thin with no common synonyms ("which tool," "what should I use," "help me pick"), matching the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	As a meta-router it occupies a clear niche distinct from the skills it routes to, but the trigger phrasing ("fits your situation") is generic enough to leave minor overlap risk, fitting 'mostly distinct; minor overlap risk' rather than the 5 anchor.	4 / 5
	Total	12 / 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: The-Vibe-Company/companion
Path: .agents/skills/ask-matt/SKILL.md
Commit: 8d000e5

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.