vitala89

ask-matt

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

improve-codebase-architecture

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

loop-me

Grill me about specs for the workflows I want to build, within this workspace.

setup-matt-pocock-skills

Configure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.

teach

Teach the user a new skill or concept, within this workspace.

to-questionnaire

Turn a decision you can't fully answer into a questionnaire for someone else to fill in.

to-spec

Turn the current conversation into a spec and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed.

Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker — edges as text in one file per ticket locally, or native blocking links on a real tracker.

triage

Move issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.

writing-fragments

Writing, explore — mine raw fragments, no structure yet.

writing-shape

Writing, exploit — shape raw material into an article, paragraph by paragraph.

aif-extension-review

Review an external skill, plugin, MCP server, or workflow pack for provenance, license, compatibility, capabilities, and unsafe automation before adoption or update. Use before external extension content becomes trusted or active.

aif-feature-discovery

Turn an ambiguous product or engineering idea into a reviewable feature brief through a focused interview and alternatives analysis. Use before specification or planning when new behavior, constraints, or success criteria are unsettled.

aif-verification-gate

Verify a completed change against its acceptance criteria and repository checks before any completion, commit, or pull-request claim. Use at the end of implementation, bug fixing, refactoring, or generated-output updates.

aif-task-router

Classify a non-trivial engineering request and recommend the smallest safe Intentloom workflow and skill set before planning or implementation. Use when the task route, required discovery, or review depth is not already explicit.

claude-handoff

Hand the current conversation off to a fresh background agent that picks up the work immediately.

handoff

Compact the current conversation into a handoff document for another agent to pick up.

Code & Development Listed

code-review

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".

codebase-design

Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.

diagnosing-bugs

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.

domain-modeling

Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a CONTEXT.md, or recording or editing an ADR.

prototype

Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.

tdd

Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

wizard

Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.

writing-for-agents

Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.

implement

Implement a piece of work based on a spec or set of tickets.

aif-branch-finisher

Prepare a completed branch for human handoff without external publication.

Code & Development Listed

aif-commit-writer

Draft a concise commit message for an already reviewed change.

aif-context-pack

Assemble minimal cited context for a bounded engineering task.

aif-docs-sync

Synchronize documentation with a verified behavior or interface change.

aif-iteration-handoff

Write a compact handoff for the next bounded iteration.

aif-orchestrator

Coordinate a bounded Intentloom engineering iteration when the user asks to plan or sequence work.

aif-privacy-review

Review data handling for collection, retention, exposure, and minimization concerns.

aif-project-adoption

Assess safe Intentloom adoption for an existing repository.

aif-project-state-sync

Synchronize canonical project state documentation after verified changes.

aif-security-review

Review a bounded change for the Intentloom threat model risks.

aif-specification-review

Review a feature brief for testable behavior and missing decisions.

aif-technical-debt-sync

Record or retire explicit technical debt after a verified decision.

Code & Development Listed

aif-code-review

Review a bounded diff independently against repository standards and the originating specification, then report correctness and verification gaps. Use for branch, pull-request, or work-in-progress review without modifying code.

aif-debugger

Diagnose an observed defect or performance regression through a reproducible feedback loop, ranked hypotheses, and regression evidence. Use when behavior is broken, failing, inconsistent, or unexpectedly slow.

aif-planning-review

Review an implementation plan for scope, dependencies, architecture, risk, rollback, and verification gaps. Use after feature discovery or specification and before implementation begins.

aif-testing-strategy

Design proportionate tests and feedback loops for specified behavior, including red-green-refactor where it provides reliable evidence. Use when acceptance criteria and existing test conventions are known.

grilling

Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.

research

Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.

aif-feature-builder

Implement one approved, bounded feature slice.