research
claudeMulti-phase research workflow for building cited, audited knowledge bases.
21 skills · 10 agents
Evidence-first build workflow: thin intent, single /work entry point with chore/feature/probe triage, exploratory slices on branches, evidence-tiered decisions, and TDD build loop.
Plugin slice-driven from marketplace mtrense-skills in mtrense/skills. Commands read from the repo's manifest — today.
decideRecord and gatekeep decisions in the slice-driven workflow: write decision records with a grounding tier (grounded with evidence link, or provisional assumption), and arbitrate when a settled decision is challenged. Trigger when the user says "/decide", "record this decision", "let's lock this in",
harvestClose an open slice in the slice-driven workflow: make the fate call (approve / adjust / discard), turn observations into grounded decisions, and ratchet the learnings into INTENT.md, QUESTIONS.md, and the work item's Results section. Trigger when the user says "/harvest", "close the slice", "the sl
intentOne-off slice-driven project inception: a short Socratic session producing a one-page INTENT.md and a seeded QUESTIONS.md of open unknowns.
sliceRun an exploratory probe in the slice-driven workflow: build the smallest vertical slice of running code, on its own branch, that settles one named decision. Trigger when the user says "/slice", "spike this", "probe this", "let's find out with code", "settle this with a slice", when /work has filed
steerDirection check for the slice-driven workflow: take a statement, hunch, or question about the state of the project — its code, docs, decisions, or general direction — gather the evidence via subagents, and answer it with citations. When the statement (or the evidence) surfaces a contradiction with t
workSingle entry point of the slice-driven workflow: take any change request, idea, improvement, or outcome description, triage it (chore / feature / probe), and shape it into a work item under work/. Trigger whenever the user says "/work", "new work item", "I want to add…", "here's an idea", "change re
build-workerSingle-task TDD implementation worker for the slice-driven /build skill. Receives one task from a work item plus its context (outcome, examples, evidence-of-done checks, binding decisions, conventions) and implements it strictly test-first: failing test, minimal code, refactor. Exits with a parser-f
claim-checkerRead-only verification worker for the slice-driven workflow's /steer skill. Given ONE claim or question about the project's state, gathers evidence from the code and the workflow artifacts (INTENT.md, QUESTIONS.md, work items — not the decision log, which decision-briefer covers) and returns a verdi
decision-brieferRead-only query worker for a slice-driven project's decision log (DECISIONS.md index + decisions/NNNN-slug.md records). Given a change description or topic, selects the relevant records, reads only those, and returns a compact briefing of the decisions that constrain the caller — including each deci
task-landerPer-task verify-and-commit worker for the slice-driven /build skill. Receives one just-implemented task (task text, the build-worker's report, the work item path), independently re-runs the tests, inspects the diff for weakened or trivially-satisfied tests, and — only when green — commits the task v
work-scoutRead-only codebase reconnaissance worker for the slice-driven workflow. Given a change description (from /work shaping or /slice scoping), maps the part of the codebase the change touches — relevant files, conventions to match, test posture, risks — and returns a compact structured report so the orc
Multi-phase research workflow for building cited, audited knowledge bases.
21 skills · 10 agents
Domain-driven build workflow: vision grounding, EventStorming, bounded-context mapping, and a dependency-ordered task backlog driven to done by TDD workers.
12 skills · 9 agents
Design-system authoring workflow: reference-grounded Socratic foundation, themable token sets (light+dark), and pure HTML/CSS Tailwind component kitchen-sinks with accessibility and i18n baked in.
12 skills · 6 agents
Demo-driven, proof-driven build workflow: vision kickoff, demos as executable human checkpoints (a scenario plus an end-to-end check that alone turns them green), tasks in one flat dependency graph, decisions with explicit proof obligations, parallel TDD burn-down with grading and demo checks after merges, and a verified human test cycle.
7 skills · 9 agents
Authoring workflow for Synaptic interactive-learning tracks: grounded ingestion, prerequisite-DAG structuring, node/question drafting, gap auditing, and CLI integrity gating.
9 skills · 6 agents
Cross-workflow utilities: /commit, /pr, /audit-context, /deckset.
8 skills · 5 agents
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development
9 skills · 1 command · 8 agents
AI-supervised issue tracker for coding workflows
1 skill · 1 agent · hooks
MiniMax AI skills library for frontend, fullstack, Android, iOS, shader, GIF sticker, document, presentation, spreadsheet, and multimodal media workflows
18 skills
Worktrunk is a CLI for Git worktree management, designed for parallel AI agent workflows. This plugin provides configuration guidance (LLM commit messages, project hooks, worktree paths), automatic activity tracking (🤖/💬 indicators in `wt list` showing active Claude sessions), and a `/wt-diff` pane showing each worktree's changes.
2 skills · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.