mattpocock-skills
claudeMatt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Alex Lapchenko's agent skills.
Plugin ozeron-skills from marketplace ozeron in ozeron/skills. Commands read from the repo's manifest — 8 days ago.
babysitBabysit a PR to merge-ready. Use when asked to babysit, ship, or land a PR, get its CI green, address or resolve review comments, or fix its merge conflicts.
code-reviewReview 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 s
codebase-designShared 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.
deslopRemove AI-generated code slop and clean up code style
implementImplement a piece of work based on a spec or set of tickets.
improve-codebase-architectureSurface architectural friction and propose deepening opportunities — refactors that turn shallow modules into deep ones, for testability and AI-navigability. Use when the user is unhappy with the patterns/design of a module and wants an architectural review.
pr-shipShip your own PR: one push round (commit, sync with the base, fix conflicts, local checks, push once), or end to end: babysit it to merge-ready, wait for a human approval, then merge it yourself. Use when asked to "commit and push", "push please", "sync with development", "fix conflicts", ship, land
pr-statusOne-glance status of PRs: merged or not, CI, open threads, review state, what's left, and a go/no-go to approve or merge. Read-only. Use when asked "merged?", "what's left?", "is it ready?", "can we approve?", "safe to merge?", "what PRs can I merge?", "any updates?", or "status".
review-roundOne review round with several independent reviewers at once (Sonnet subagents, Codex or Claude via acpx), merged into one deduplicated list, with GitHub inline suggestions drafted and posted only on the user's OK. Use when asked "review thoroughly", "review with codex / sol / fable", "use acpx to re
reviewerReview someone else's PR through every round until it is ready to approve: pull the head, run code-review and verify, post findings as threads, then watch for pushes and replies and re-review each round. The reviewer side of babysit. Use when asked to review, own the review of, or keep reviewing a P
shrinkMake a PR or change smaller and simpler: measure the diff by category, list what can be dropped, split out or simplified, then apply what the user picks. Use when asked "too big", "is BIG LOC", "can we simplify?", "are we overengineering?", "smaller PR", "can we drop X?", or "reduce even more".
sim-sweepRun a voice-agent behaviour N times and report the pass rate, the odd replies and the cost. Uses a throwaway Retell chat agent for hosted agents and the retell-sim MCP for local ones, with realistic caller lines. Use when asked to "test 20 more times", "run N chats", "test with a throwaway agent", "
sol-loopRun repeated independent Sol code reviews through headless ACPX, verify findings, make minimal fixes, and check the final diff. Use for “sol loop” or requests for several Codex review rounds before shipping.
tddTest-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
explainExplain a change, bug, diff, concept or plan in plain words: outcome first, one concrete example, five lines. Use when asked "explain", "explain simply", "what does it mean?", "I don't follow", "what's the difference between X and Y?", "is it clear how it works?", or "teach me".
find-contextSearch every place a decision or fact might live — past agent sessions (pond), Slack, Notion, Jira, GitHub PRs and the repo — in one pass and answer with links. Use when asked "find in slack", "search jira and notion", "check pond", "did we decide X?", "any rules about X?", "who said X?", or "invest
grillingGrill 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.
handoffCompact the current conversation into a handoff document for another agent to pick up.
i-have-adhdShape output for a reader with ADHD. Use this skill whenever responding to ANY user message including coding tasks, debugging, explanations, planning, and casual conversation. Output should lead with concrete next actions, number multi-step work, externalize state across turns, suppress tangents, gi
teachTeach the user a new skill or concept, within this workspace.
visualizeTurn a change, PR, plan, bug or flow into a visual Artifact page: what changed, before vs after, how it works, what's proven, what's left. Use when asked "visualize", "visualize changes", "create artifact to explain", "walkthrough", "teach me how it works", "show me the flow", or "attach a visualiza
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
AGENTS.md as project instructions, by one option. Under claude-md-or-agents-md a project with no instruction files of its own gets its AGENTS.md files instead: a prompt.context hook asks $.fs.ancestors for every AGENTS.md and .claude/AGENTS.md from the filesystem root down to the working directory and hands them to the engine as project instruction files, which it renders, announces and withholds from agents exactly as it does CLAUDE.md, skipping any file the engine already loaded by import or link; a tool.call hook on Read attaches the ones under the project root as the engine attaches a nested CLAUDE.md. Under claude-md-and-agents-md every AGENTS.md is loaded beside CLAUDE.md. Under managed-only the project's and the person's instruction files are dropped and the organization's managed ones kept. Under claude-md the engine's walk stands alone. claude-md-or-agents-md is the default.
Production-grade engineering skills covering every phase of software development: spec, plan, build, verify, review, and ship.
25 skills · 4 agents
Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data
9 skills · 9 commands · 11 agents · 1 MCP server
Install the "AAS Security Engineer" workflow plugin from Agentic Awesome Skills.
12 skills
Binary reverse engineering, malware analysis, firmware security, and software protection research for authorized security research, CTF competitions, and defensive security
4 skills · 3 agents
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.