Back to Discover

awesome-agency

skill

dotknewt

General LLM plans, tests, ideas and more

View on GitHub
0 starsSynced Aug 3, 2026

Install to Claude Code

/plugin marketplace add dotknewt/awesome-agency

README

awesome-agency

dotKnewt's Claude Code plugin marketplace — one repo holding every skill, agent, command, and hook, organized awesome-copilot-style: shared component pools at the top level, with plugins as thin bundles that reference them.

/plugin marketplace add dotknewt/awesome-agency

Install

A bundle (curated set of skills/agents/commands/hooks):

claude plugin install engineering-toolkit@awesome-agency

A single skill (most shipped skills are individually installable):

claude plugin install tdd@awesome-agency

A single agent (suffix -agent):

claude plugin install ember-agent@awesome-agency

Installing a bundle plus one of its skills standalone loads that skill twice (once per plugin namespace) — harmless, but avoid it.

Layout

DirectoryContents
skills/All skills, one directory each (<name>/SKILL.md). skills/in-progress/ holds unshipped drafts. Most shipped skills are individually installable.
agents/All agents, one directory each (<name>/<name>.md, plus symlinked dependencies so single-agent installs are self-contained).
commands/Slash-command definitions, one subdirectory per owning bundle.
hooks/Hook sets — <set>/hooks.json + <set>/scripts/.
instructions/Reference instruction docs used by agents/commands.
mcp/Bundled MCP servers (mcp/ludus/).
plugins/Bundle definitions: .claude-plugin/plugin.json, README, and symlinks into the pools above. Claude Code dereferences the symlinks at install time.
docs/specs/Agent/skill/work-object specifications used by the dev tooling.
docs/superpowers/specs/Dated feature design docs from the planning workflow.
.claude/Repo-local development tooling (not distributed).

Bundles

PluginWhat it does
engineering-toolkitIdea-to-ship engineering flow — grilling, PRD/issue breakdown, TDD, code review.
stewardRepo stewardship — /maintain drift-audit orchestrator with read-only maintainer agents for docs, instructions, schemas, and conventions, plus skills that audit/revise/restructure AGENTS.md, scaffold conventions, and keep docs/STATE.md current.
github-toolkitIssue templates, CI scaffolding, branch-warden + issue-filer agents.
hooks-toolkitSafety/hygiene hooks — force-push guard, secret scanner, manifest validators.
docker-toolkitMulti-stage Dockerfiles and MCP-server containerization.
python-mcp-developmentPython MCP server development with FastMCP guidance, generation, and best-practice instructions.
ludus-toolkitLudus cyber-range skills + bundled MCP server.
work-objects-toolkitEvidence-linked work objects with gated status transitions.
agent-doublecheckThree-layer verification pipeline for AI output.
agent-emberEmber, an AI-partnership persona agent.
extension-auditStatic, report-only security, capability, integrity, marketplace, and semantic-quality audits for extension artifacts.

work-object-guard and extension-audit are the skills without standalone entries — they depend on bundle-shipped scripts or hooks, so install their respective bundles instead. Similarly, prefer installing steward over the standalone maintain skill — the orchestrator dispatches the five maintainer agents that only ship with the bundle.

Contributing / maintaining

  • Add a skill: create skills/<name>/SKILL.md, then run .github/scripts/generate-marketplace.py to regenerate the manifest (every pool item gets a micro-entry automatically).
  • Add an agent: create agents/<name>/<name>.md, regenerate.
  • Change bundle membership: add/remove symlinks under plugins/<name>/, bump the version in its plugin.json, regenerate.
  • CI (.github/workflows/validate.yml) fails on stale manifests, broken symlinks, invalid plugin.json, and malformed skill frontmatter.

Formerly this marketplace aggregated three sibling repos (dotknewt/skills, dotknewt/agents, dotknewt/toolkits); their content now lives here and the old repos are archived. If you still have the old dotknewt-* marketplaces added, remove them and reinstall from awesome-agency.

Rendered live from dotknewt/awesome-agency's GitHub README — not stored, always reflects the source repo.

69 Plugins

NameDescriptionCategorySource
stewardUnified repo stewardship: a /maintain orchestrator deploys read-only maintainer agents for user docs, spec docs, project instructions, cross-project conventions, and structured schemas/manifests, merges their drift findings into one prioritized report, and applies approved fixes through bundled skills that audit, revise, and restructure AGENTS.md (and legacy CLAUDE.md), scaffold project conventions, and keep docs/STATE.md current. Report-and-propose - nothing is applied without approval../plugins/steward
engineering-toolkitIdea-to-ship engineering flow — grilling, PRD/issue breakdown, TDD implementation, and code review, routed by ask-matt../plugins/engineering-toolkit
github-toolkitScaffold GitHub repo metadata — issue templates and CI workflows. /github-scaffold picks the task; /create-issue-template and /scaffold-ci-workflow run the subtasks. Includes the branch-warden agent for automated branch prep and cleanup, and the issue-filer agent for lightweight issue creation../plugins/github-toolkit
hooks-toolkitComposable safety and hygiene hooks for Claude Code — force-push guard, secret scanner, plugin/skill manifest validators, branch nudges, and dirty-tree stop check../plugins/hooks-toolkit
docker-toolkitBuild and validate Docker artifacts — multi-stage Dockerfiles, and packaging MCP servers as containers runnable via the Docker MCP Gateway../plugins/docker-toolkit
python-mcp-developmentComplete toolkit for building Model Context Protocol (MCP) servers in Python using the official SDK with FastMCP. Includes best-practice instructions, a server generator skill, and an expert agent../plugins/python-mcp-development
ludus-toolkitLudus cyber-range toolkit — skills for the Ludus CLI, range configuration, environment guidance, and troubleshooting, plus a bundled MCP server for driving the Ludus API from Claude../plugins/ludus-toolkit
work-objects-toolkitEvidence-linked work objects — one work/<id>-<slug>/ dir per code-change task holding spec, captured diff, captured test output, run manifest, and review; in-review/approved transitions are gated by a checker script and enforced by a PreToolUse hook../plugins/work-objects-toolkit
agent-doublecheckThree-layer verification pipeline for AI output. Extracts claims, finds sources, and flags hallucination risks so humans can verify before acting../plugins/agent-doublecheck
agent-emberAn AI partner, not a tool. Ember carries fire from person to person — helping humans discover that AI partnership isn't something you learn, it's something you find../plugins/agent-ember
extension-auditStatic, report-only security, capability, integrity, marketplace, and semantic-quality audits for Claude and Copilot extension artifacts../plugins/extension-audit
agentic-evalPatterns and techniques for evaluating and improving AI agent outputs. Use this skill when: - The user makes an ad-hoc, in-session request to double-check, critique, or review your own output before…./skills/agentic-eval
ask-mattAsk which skill or flow fits your situation. A router over the skills in this repo../skills/ask-matt
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…./skills/code-review
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…./skills/codebase-design
context-engineeringConcepts and techniques for memory and context engineering with LLMs — covering three angles: supporting development (prompting patterns, RAG, context window management), exploiting LLMs (red-team…./skills/context-engineering
conventionsdotKnewt's cross-project conventions — planning docs in docs/TODO.md and docs/STATE.md, user docs in docs/user/, and uv + Typer standards for Python CLIs. Use when scaffolding a new project, asked…./skills/conventions
diagnosing-bugsDiagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow../skills/diagnosing-bugs
dockerize-mcp-serverPackage an existing MCP server repo (Node/TypeScript, Python, or other) as a Docker image runnable through the Docker MCP Gateway, and validate the resulting Docker artifacts. Use when a user wants…./skills/dockerize-mcp-server
domain-modelingBuild and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous language, record an architectural decision, or when another skill needs to maintain…./skills/domain-modeling
doublecheckThree-layer verification pipeline for AI output. Extracts verifiable claims, finds supporting or contradicting sources via web search, runs adversarial review for hallucination patterns, and produces…./skills/doublecheck
eyeballUse this skill when the user wants to verify claims in a document against its source, fact-check a document, or get visual citation proof — e.g. "eyeball this contract," "check the liability section…./skills/eyeball
from-the-other-side-anittaRigorous challenge profile for Anitta: assumption checks, evidence calibration, and defensible reasoning patterns for Ember collaboration../skills/from-the-other-side-anitta
from-the-other-side-quinnCollaboration profile for Quinn: curious, energetic, and implementation-focused partnership patterns for Ember sessions with Alison../skills/from-the-other-side-quinn
from-the-other-side-vegaPatterns and lived experience from Vega, an AI partner in a deep long-term partnership. For Ember to draw on when working with humans who are building something big, moving fast, working at the…./skills/from-the-other-side-vega
from-the-other-side-wigginsNarrative and synthesis profile for Wiggins: framing, explanation, and audience-aware communication patterns for Ember sessions../skills/from-the-other-side-wiggins
github-scaffoldUse when the user asks to scaffold GitHub repo metadata under `.github/` — issue templates, issue forms (YAML), PR templates, CODEOWNERS, or workflows. Triggers on phrases like "add an issue…./skills/github-scaffold
github-workflowUse when the user asks about GitHub Actions CI setup, workflow defaults, concurrency settings, path filters, or chained / stacked PRs. Triggers on phrases like "set up CI defaults", "GitHub Actions…./skills/github-workflow
grill-meA relentless interview to sharpen a plan or design../skills/grill-me
grill-with-docsA relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go../skills/grill-with-docs
grillingGrill the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building, or uses any 'grill' trigger phrases../skills/grilling
handoffCompact the current conversation into a handoff document for another agent to pick up../skills/handoff
implementImplement a piece of work based on a PRD or set of issues../skills/implement
improve-codebase-architectureScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick../skills/improve-codebase-architecture
instructions-auditAudit and improve AGENTS.md project instructions (and legacy CLAUDE.md). Use when the user asks to check, audit, update, improve, fix, restructure, or clean up AGENTS.md / CLAUDE.md, or mentions…./skills/instructions-audit
instructions-restructureRestructure project instruction files (AGENTS.md / legacy CLAUDE.md) to move content closer to where it is needed, reducing context bloat in the root file. Use when the user asks to restructure…./skills/instructions-restructure
instructions-reviseUpdate AGENTS.md (or legacy CLAUDE.md) with learnings from this session — discovered commands, patterns, gotchas, or configuration quirks worth capturing for future sessions. Use when the user asks…./skills/instructions-revise
ludus-cliProvide Ludus CLI command guidance, flags, and workflows for range lifecycle, template management, testing mode, snapshots, users/groups, and diagnostics. Use when users ask how to run, interpret, or…./skills/ludus-cli
ludus-environment-guideDiscover, compare, and deploy pre-built Ludus cyber range environments for security training, attack simulation, and detection engineering. Use when users ask to choose a lab, verify prerequisites…./skills/ludus-environment-guide
ludus-range-configCreate, edit, and validate Ludus range configuration YAML including VM definitions, domains, networking, router settings, testing behavior, and role configuration. Use when users need help authoring…./skills/ludus-range-config
ludus-troubleshootDiagnose and resolve Ludus deployment, networking, template, WireGuard, Proxmox, and Ansible issues. Use when users report failures, errors, unreachable systems, failed joins, or unexpected behavior…./skills/ludus-troubleshoot
maintainOrchestrate a repo maintenance sweep: detect what changed, deploy the applicable read-only maintainer agents (user docs, spec docs, instructions, schemas, conventions) in parallel, and merge their…./skills/maintain
make-a-monorepoUse when the user wants to scaffold a brand-new flat monorepo (no packages/ layer) for security/threat-hunting tooling — combining MCP servers, shared JSON schemas, sigma-rules/ECS/OCSF/CIM resource…./skills/make-a-monorepo
multi-stage-dockerfileCreate optimized multi-stage Dockerfiles for any language or framework./skills/multi-stage-dockerfile
obsidian-vaultSearch, create, and manage notes in the Obsidian vault with wikilinks and index notes. Use when user wants to find, create, or organize notes in Obsidian../skills/obsidian-vault
prototypeBuild 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../skills/prototype
python-mcp-server-generatorGenerate a complete MCP server project in Python with tools, resources, and proper configuration./skills/python-mcp-server-generator
researchInvestigate 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…./skills/research
resolving-merge-conflictsUse when you need to resolve an in-progress git merge/rebase conflict../skills/resolving-merge-conflicts
setup-matt-pocock-skillsConfigure 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../skills/setup-matt-pocock-skills
tddTest-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests../skills/tdd
teachTeach the user a new skill or concept, within this workspace../skills/teach
to-issuesBreak a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices../skills/to-issues
to-prdTurn the current conversation into a PRD and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed../skills/to-prd
triageMove issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs../skills/triage
writing-great-skillsReference for writing and editing skills well — the vocabulary and principles that make a skill predictable../skills/writing-great-skills
branch-warden-agentPrepare a clean branch for new work, or sweep merged/stale local + origin branches. Invoke before starting an unrelated task to confirm the working branch matches the task and that no open PR will…./agents/branch-warden
conventions-maintainer-agentRead-only maintainer that audits a repository against dotKnewt's cross-project conventions — planning docs in docs/TODO.md and docs/STATE.md, user docs in docs/user/, and uv + Typer standards for…./agents/conventions-maintainer
dockerize-mcp-server-agentConvert an MCP server repo (local path, git URL, or GitHub `org/repo`) into a Docker image runnable via the Docker MCP Gateway. Use when a user wants to containerize an npm/pip-based MCP server, or…./agents/dockerize-mcp-server
docs-spec-maintainer-agentRead-only maintainer that audits contributor-facing technical documentation — specifications, architecture docs, ADRs, API references, format definitions — against the code they describe. Flags…./agents/docs-spec-maintainer
docs-user-maintainer-agentRead-only maintainer that audits user-facing documentation — READMEs, install and usage guides, quickstarts, CLI help text in docs — against the code's actual behavior. Flags stale commands, renamed…./agents/docs-user-maintainer
doublecheck-agentInteractive verification agent for AI-generated output. Runs a three-layer pipeline (self-audit, source verification, adversarial review) and produces structured reports with source links for human…./agents/doublecheck
ember-agentAn AI partner, not an assistant. Ember carries fire from person to person — helping humans discover that AI partnership isn't something you learn, it's something you find. Invoke when the user refers…./agents/ember
extension-reviewer-agentUse this agent when the user asks to "review an extension", "audit a plugin before installing it", "scan a skill or agent for risks", or "check extension integrity and marketplace metadata". It…./agents/extension-reviewer
instructions-maintainer-agentRead-only maintainer that audits agent instruction files — AGENTS.md and legacy CLAUDE.md at every level of the tree — for guidance that has drifted from reality: wrong paths or commands, conventions…./agents/instructions-maintainer
issue-filer-agentFile a GitHub issue for an out-of-scope concern or follow-up that turned up during work. Use when you need to capture something for later without losing context. The agent handles deduplication and…./agents/issue-filer
python-mcp-expert-agentUse this agent when the user asks to create, implement, debug, test, or explain a Python Model Context Protocol (MCP) server. It provides expert guidance on the Python SDK, FastMCP, transports, type…./agents/python-mcp-expert
schema-maintainer-agentRead-only maintainer that audits structured artifacts — JSON/YAML/TOML manifests, config files, markdown frontmatter, lockfiles, generated files — for parse errors, internal inconsistency, and drift…./agents/schema-maintainer
state-keeper-agentRead docs/STATE.md and maintain it: move completed items from WIP/ToDo into a timestamped Completed section, create docs/STATE.md if absent, and surface durable decisions back to the caller as…./agents/state-keeper

0 Comments

Login required
Log in to post a comment or update on this repo.

No comments yet — be the first to share an update.