superpowers
claudeCore skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Plugin marketplace
dotKnewt's Claude Code marketplace — one repo of shared skills, agents, commands, and hooks. Install curated plugin bundles or any single skill/agent.
Add this marketplace
Then install any plugin below by name — each page has its exact command.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Durable project memory in a git-native vault/ — atomic knowledge notes, ADRs, docs and provenance-bearing sources with a structural linter, retrieval and curation subagents, /vault-find /vault-save /vault-session /vault-review commands, and vault-audit / vault-research workflows. Backed by the mcpvault MCP server.
6 skills · 3 agents · 1 MCP server · hooks
Unified 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.
7 agents
Scaffold 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.
2 agents
Patterns 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…
1 skill
Use when deciding which model an agent or subagent should run on, or reviewing an existing assignment. Triggers on "which model should this agent use", "assign a model", "is haiku enough for this…
1 skill
Ask which skill or flow fits your situation. A router over the skills in this repo.
1 skill
Change keyboard input languages and layouts in Ludus Packer OS templates. Use when converting a Windows, Debian, Kali, or Ubuntu template from one keyboard locale to another, including template…
1 skill
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…
1 skill
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…
1 skill
Concepts and techniques for memory and context engineering with LLMs — covering three angles: supporting development (prompting patterns, RAG, context window management), exploiting LLMs (red-team…
1 skill
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 Python CLIs. Use when scaffolding a new project, asked…
1 skill
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
1 skill
Package 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…
1 skill
Build and validate Docker artifacts — multi-stage Dockerfiles, and packaging MCP servers as containers runnable via the Docker MCP Gateway.
1 agent
Build 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…
1 skill
Three-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…
1 skill
Static, report-only security, capability, integrity, marketplace, and semantic-quality audits for Claude and Copilot extension artifacts.
1 agent
Use 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…
1 skill
Rigorous challenge profile for Anitta: assumption checks, evidence calibration, and defensible reasoning patterns for Ember collaboration.
1 skill
Collaboration profile for Quinn: curious, energetic, and implementation-focused partnership patterns for Ember sessions with Alison.
1 skill
Patterns 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…
1 skill
Narrative and synthesis profile for Wiggins: framing, explanation, and audience-aware communication patterns for Ember sessions.
1 skill
Use 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…
1 skill
Use 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…
1 skill
Grill 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.
1 skill
A relentless interview to sharpen a plan or design.
1 skill
A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
1 skill
Use when an existing VM must be reached over SSH, guest access is refused or unreachable, a project must be copied or synchronized into a guest, or commands and tests must run inside the guest. Do…
1 skill
Compact the current conversation into a handoff document for another agent to pick up.
1 skill
Implement a piece of work based on a PRD or set of issues.
1 skill
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
1 skill
Audit 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…
1 skill
Restructure 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…
1 skill
Update 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…
1 skill
Safe libvirt lifecycle and provider handoff for publishing QCOW2 templates, managing qemu:///session VMs, and continuing into verified guest access.
1 MCP server
Provide 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…
1 skill
Discover, 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…
1 skill
Create, 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…
1 skill
Use when naming, renaming, reviewing, or validating Ludus Packer OS templates, especially when legacy names have ambiguous locale, role, edition, release, or feature tokens such as no or…
1 skill
Diagnose and resolve Ludus deployment, networking, template, WireGuard, Proxmox, and Ansible issues. Use when users report failures, errors, unreachable systems, failed joins, or unexpected behavior…
1 skill
Orchestrate a repo maintenance sweep: detect what changed, deploy the applicable read-only maintainer agents (user docs, spec docs, instructions, schemas, conventions, marketplace release notes) in…
1 skill
Use 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…
1 skill
Create optimized multi-stage Dockerfiles for any language or framework
1 skill
Search, 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.
1 skill
Scans AGENTS.md, the knowledge base, the skill set, and guardrails/hooks for gaps relevant to a spec'd-out idea, and drafts hook configs for any risky action found — the third of three…
1 skill
Orchestrates a spec-gap-closing interview before any code, docs, or planning begins on a new idea, feature, task, project, extension, or enhancement. Use this whenever the user expresses real intent…
1 skill
Interviews the user to draft the Goal, Scope, Non-goals, and Constraints of a new idea, feature, task, or project into specs/SLUG/spec.md — the first of three spec-gap-closing layers, run before any…
1 skill
Defines precise, measurable evaluation criteria and identifies any external signal that would prove success for an idea already spec'd out — the second of three spec-gap-closing layers, run before…
1 skill
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.
1 skill
Complete 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.
1 agent
Generate a complete MCP server project in Python with tools, resources, and proper configuration
1 skill
Write and maintain a plugin's RELEASE-NOTES.md — one entry per released version, stating what changed and why it changed. Use when the user asks to "update the release notes", "add a changelog…
1 skill
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…
1 skill
Use when you need to resolve an in-progress git merge/rebase conflict.
1 skill
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.
1 skill
Use when asked to write, simplify, refactor, or review Tailscale ACLs, grants, or tailnet HuJSON policies; make access rules leaner or easier to read; investigate overlapping permissions or bypassed…
1 skill
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
1 skill
Teach the user a new skill or concept, within this workspace.
1 skill
Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices.
1 skill
Turn the current conversation into a PRD and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed.
1 skill
Move issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.
1 skill
Use when asked to "update local plugin skills", "pull plugin skills", "sync plugin skills to OpenCode", "rsync skills to .opencode", or refresh skills from a locally checked-out plugin repository.
1 skill
Clone and update Ludus Packer templates for a new OS release. Use when a new Debian, Ubuntu, Kali, Windows, or Windows Server release needs a template based on the latest existing template, including…
1 skill
Reference for writing and editing skills well — the vocabulary and principles that make a skill predictable.
1 skill
Prepare 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…
Read-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…
Convert 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…
Read-only maintainer that audits contributor-facing technical documentation — specifications, architecture docs, ADRs, API references, format definitions — against the code they describe. Flags…
Read-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…
Interactive 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…
An 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…
Idea-to-ship engineering flow — grilling, PRD/issue breakdown, TDD implementation, and code review, routed by ask-matt.
Use 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…
Composable safety and hygiene hooks for Claude Code — force-push guard, secret scanner, plugin/skill manifest validators, branch nudges, and dirty-tree stop check.
Read-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…
File 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…
Ludus cyber-range toolkit — skills for CLI use, range configuration, environment guidance, troubleshooting, and OS template maintenance with canonical template naming, plus a bundled MCP server for driving the Ludus API from Claude Code or OpenCode.
Read-only maintainer that audits release discipline in a Claude Code plugin marketplace repo — whether bundles whose content changed also bumped their version and recorded a RELEASE-NOTES.md entry…
Persistent knowledge-graph memory for Claude — packages the official MCP reference Knowledge Graph Memory Server as a Docker image, run through the Docker MCP Gateway, so entities, relations, and observations persist across sessions.
Close the spec gaps before any code is written: a project-manager orchestrator runs three interview layers in sequence — project-spec (Goal, Scope, Non-goals, Constraints), project-verify (measurable evaluation criteria and external success signals), and project-environment (AGENTS.md, knowledge-base, skill, and guardrail gaps, with drafted hook configs) — each writing to specs/<slug>/ behind an explicit human sign-off at every checkpoint.
Use 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…
Read-only maintainer that audits structured artifacts — JSON/YAML/TOML manifests, config files, markdown frontmatter, lockfiles, generated files — for parse errors, internal inconsistency, and drift…
Read 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…
Evidence-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.
Shows how many plugins this repo ships, and links here.