Skip to content
Agentmart
Submit a tool

ask-matt

Choose one skill or workflow for a task across personal, Matt Pocock, Codex, and plugin capabilities.

Skill by linjuhon

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/linjuhon-ask-matt

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Choose one skill or workflow for a task across personal, Matt Pocock, Codex, and plugin capabilities. Use when the user asks which skill or flow fits, or presents a multi-step task with an unclear next step.

Use cases: productivity, agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/ask-matt

What's inside

Skill name
ask-matt
Description
Choose one skill or workflow for a task across personal, Matt Pocock, Codex, and plugin capabilities. Use when the user asks which skill or flow fits, or presents a multi-step task with an unclear next step.
License
MIT
Instructions
64 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • openai.yaml · agents/

SKILL.md (first lines)

# Ask Matt

Route one task at a time. Preserve the upstream idea-to-ship flow, then add a personal routing layer for evidence and external capabilities.

## Route in order

1. Identify the user's authorization: answer, research, plan, diagnose, change, validate, publish, or destructive cleanup.
2. Identify the destination and current stage: fog, decision, specification, execution, diagnosis, correctness, quality, performance, release, or operations.
3. Apply constraints first: scope, dirty worktree, ownership, external side effects, and evidence identity.
4. Select exactly one current router or an explicitly named leaf skill. Do not list a menu of plausible skills.
5. State the result in this form:

```markdown
## Destination

## Ownership branch

## Current stage

## Authority and constraints

## Selected router

## Use now

## Exit criterion

## Use next

## Missing evidence

## Out of scope
```

Use `Own` when the route is a personal skill, `External` when it is entirely Matt/Codex/plugin-managed, and `Mixed` when a personal router selects an external leaf skill.

## Own branch

Use a domain router for a multi-step task or when a choice among skills remains.

- **Planning and decisions** → `$route-planning`: research, ambiguous ideas, terminology, prototypes, Wayfinder, specs, or tickets.
- **Engineering and architecture** → `$route-engineering`: authorized code changes, TDD, reviews, merge conflicts, or codebase health.
- **Diagnostics** → `$route-diagnostics`: failures, regressions, CI, CUDA correctness, or performance symptoms. Diagnosis does not authorize a fix.
- **Evidence and release** → `$route-evidence`: identity, correctness, quality, performance, evidence packaging, patch decomposition, or upstream integration.
- **Artifacts and external operations** → `$route-operations`: documents, spreadsheets, browser work, GitHub, Gmail, Sites, or image/visual work.

When the next router can be selected reliably, invoke it in the current task. If invocation is unavailable, output its explicit `$route-*` command and the minimal context it needs.

## External branch

Use an explicit external leaf skill directly when the user's request already names it or is narrow enough to need no domain decision.

- **Matt Pocock**: retain the upstream flow: `grill-with-docs` or `grill-me` → `prototype` if necessary → `to-spec` → `to-tickets` → `implement`/`tdd` → `code-review`.
- **Large foggy work**: use `wayfinder` only when the destination spans more than one task and the route itself still requires decisions. It hands off to `to-spec`; it does not directly build.
- **Codex and plugins**: use the domain-specific skill for documents, PDF, slides, spreadsheets, browser, GitHub, Gmail, Sites, visualization, or image work.

## Guardrails

- Treat diagnosis, audit, planning, and implementation as different authorizations.
- Before modifying a repository, use `git-worktree-protection` when the worktree may be dirty or concurrent.
- Never claim release proof from a build, help output, UI exposure, or a single bounded test.
- For a direct leaf-skill request, do not interpose a router unless the leaf's own prerequisites are unresolved.

From linjuhon/codex-personal-skills, MIT.

More from linjuhon/codex-personal-skills

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Aug 8, 2026 (2 months ago)
Last release
Aug 8, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from linjuhon

Cite this page

ask-matt skill. Agent Mart. https://agentmart.dev/skills/linjuhon-ask-matt (last updated 2026-10-24)