ask-matt
Choose one skill or workflow for a task across personal, Matt Pocock, Codex, and plugin capabilities.
Skill by linjuhon
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.
About
Use cases: productivity, agent-building
Reviews
Write a reviewNo 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
- 0.524score
upstream-rebase
linjuhon
Rebase an accepted, dependency-ordered patch onto an already locked upstream revision with conflict, verification, and rollback evidence.
SkillBFreshness: BClaude Code +9 - 0.524score
documentation-organization
linjuhon
Organize project documentation into a clear authoritative structure, classify source documents, preserve traceability, and create indexes or handoff maps.
SkillBFreshness: BClaude Code +9 - 0.524score
oracle-validation
linjuhon
Compare runtime or kernel output with the project oracle, isolate the first divergence, and produce an evidence-ready verdict.
SkillBFreshness: BClaude Code +9 - 0.524score
patch-decomposition
linjuhon
Decompose fork-versus-base changes into one reviewable plugin patch with hunk ownership, dependencies, activation boundaries, verification, and rollback…
SkillBFreshness: BClaude Code +9 - 0.521score
cuda-kernel-debug
linjuhon
Narrow a CUDA kernel correctness failure to the first failing coordinate and one semantic owner using minimal probes.
SkillBFreshness: BClaude Code +9 - 0.521score
route-operations
linjuhon
Route multi-step document, artifact, browser, GitHub, Gmail, website, or image operations when the correct managed capability or write authorization is unclear.
SkillBFreshness: BClaude Code +9 - 0.521score
evidence-packaging
linjuhon
Package completed bounded execution output into one evidence claim with identity, observations, limitations, and receipt.
SkillBFreshness: BClaude Code +9 - 0.521score
git-worktree-protection
linjuhon
Protect dirty worktrees and narrow file ownership during execution, evidence archival, and cleanup.
SkillBFreshness: BClaude Code +9 - 0.521score
route-planning
linjuhon
Route multi-step planning, research, design decisions, specifications, and ticketing when the next planning skill is unclear.
SkillBFreshness: BClaude Code +9 - 0.521score
performance-profiling
linjuhon
Measure and diagnose performance only after correctness and quality prerequisites are closed.
SkillBFreshness: BClaude Code +9 - 0.521score
quality-evaluation
linjuhon
Run and interpret the project's quality matrix after correctness and route gates are closed.
SkillBFreshness: BClaude Code +9 - 0.521score
route-diagnostics
linjuhon
Route multi-step bug, regression, CI, CUDA, or performance diagnosis when failure isolation requires choosing a method.
SkillBFreshness: BClaude Code +9
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
- Source
- GitHubgithub-graphql
More from linjuhon
- 0.524score
upstream-rebase
linjuhon
Rebase an accepted, dependency-ordered patch onto an already locked upstream revision with conflict, verification, and rollback evidence.
SkillBFreshness: BClaude Code +9 - 0.524score
documentation-organization
linjuhon
Organize project documentation into a clear authoritative structure, classify source documents, preserve traceability, and create indexes or handoff maps.
SkillBFreshness: BClaude Code +9 - 0.524score
oracle-validation
linjuhon
Compare runtime or kernel output with the project oracle, isolate the first divergence, and produce an evidence-ready verdict.
SkillBFreshness: BClaude Code +9 - 0.524score
patch-decomposition
linjuhon
Decompose fork-versus-base changes into one reviewable plugin patch with hunk ownership, dependencies, activation boundaries, verification, and rollback…
SkillBFreshness: BClaude Code +9 - 0.521score
atomic-control
linjuhon
Drive the PLAN_100 autonomous audit loop via atomic-control MCP tools (5 tools).
SkillBFreshness: BClaude Code +9 - 0.521score
cuda-kernel-debug
linjuhon
Narrow a CUDA kernel correctness failure to the first failing coordinate and one semantic owner using minimal probes.
SkillBFreshness: BClaude Code +9
Cite this page
ask-matt skill. Agent Mart. https://agentmart.dev/skills/linjuhon-ask-matt (last updated 2026-10-24)