Richard
Community@richard-jh-mccrae · Trondheim, Norway
Embedded SW Developer, apline skier, a happy camper. Builder of LEGOs. Pappa of two
Agent Skills by Richard
Showing 23 vetted skills indexed across 1 GitHub repositories.
board-state
Prints the complete board state of a diagnostic frame as plain text.
research
Investigate questions against primary sources and record findings as Markdown files.
domain-modeling
Builds and maintains a project's domain model and ubiquitous language.
auto-grill-with-docs
Conducts repository-grounded design discovery with automatic recommendations and one approval.
explain
Explains issues, pull requests, and code in plain English through conversational follow-ups.
wayfinder
Plan large multi-session work as decision tickets on an issue tracker.
setup-matt-pocock-skills
Configures a repository's issue tracker, triage labels, and domain documentation layout.
writing-great-skills
Provides vocabulary and principles for writing predictable, well-structured skills.
code-review
Reviews code changes since a reference point against standards and spec requirements.
to-tickets
Breaks plans or specs into tracer-bullet tickets with declared blocking edges published to a tracker.
to-spec
Convert conversation context into a spec and publish it to the project issue tracker.
prototype
Builds throwaway prototypes to validate state models, logic, and UI design questions.
open-pr
Creates or updates pull requests with rebasing, ADR finalization, and automated CI monitoring.
issue-sequence
Implements an ordered list of GitHub issues sequentially on one shared branch and PR.
grill-with-docs
Interrogates plans and designs through structured questioning while generating ADRs and glossary documentation.
implement
Implements a piece of work based on a spec or set of tickets.
teach
Teaches the user a new skill or concept within the workspace.
code-as-docs
Enforces a documentation policy where source code serves as the primary documentation.
strategy-ingest
Downloads and distills external Pokémon TCG strategy articles into committed Strategy Digest files.
caveman
Rewrites chat responses into blunt, terse fragments without fluff.
tdd
Guides test-driven development using the red-green-refactor workflow for features and bug fixes.
blunder-buster
Diagnoses and corrects Bellman decision blunders from correction JSON records.
grilling
Stress-tests plans, decisions, and ideas through relentless questioning.
Frequently Asked Questions About Richard
FAQPage SchemaWhat tasks can I accomplish with Richard McCrae's skills?▼
You can turn conversations into specs and tickets, implement specced GitHub issues in sequence on one shared branch, open and maintain PRs with CI auto-fix check-ins, run standards-plus-spec code reviews, practice TDD, build domain models and ADRs, and inspect Pokémon TCG diagnostic frames.
Who are these skills designed for?▼
Software engineers practicing spec-driven, ticket-based development on GitHub-backed repos. The manifest targets developers who plan work as decision tickets, review changes against documented standards, and maintain domain models — plus a niche audience analyzing Pokémon TCG game frames and strategy digests.
How do I set up and run these skills?▼
Run setup-matt-pocock-skills once first — it configures the repo's issue tracker, triage label vocabulary, and domain doc layout. After that, invoke skills by name or trigger phrase: /to-spec publishes a spec, /implement builds from tickets, /open-pr rebases, pushes, and arms a CI check-in cadence.
What prerequisites or dependencies do these skills require?▼
A repository with a configured issue tracker (GitHub issues for issue-sequence and to-tickets), a PR template for open-pr, and documented coding standards for code-review's Standards axis. The board-state skill requires tools/train/frame_view.py in the repo; strategy-ingest uses your already-logged-in browser session.
How does the code review skill work?▼
Code-review examines changes since a fixed point — commit, branch, tag, or merge-base — along two axes: Standards (conformance to the repo's documented coding standards) and Spec (match to the originating issue or PRD). Both reviews run in parallel sub-agents and are reported side by side.