Every Claude Code tool you need :)

stm

Your API keys in the OS keychain. Your AI coding agent uses them — without ever seeing them. The model writes {{stm:openai:default}}. The real key is swapped in at the moment the command runs.

4

@matterhornsoView Plugin→

divide-task

Divide a specced pastiche task into sub-task GitHub issues with autonomy and dependency labels, mirror them into `_dev/TODO.md`, and update the parent issue.…

frompastiche4

@retz8View Skill→

advisor

High-intelligence strategic advisor (emulates Anthropic's advisor-tool pattern). Consult BEFORE committing to an approach on a multi-step task, BEFORE…

fromoperating-core3

@josherauView Agent→

dashboard

Launch the local Rebound dashboard (React) to visualize your job-search progress.

fromrebound4

@snehag01View Command→

search-mesh

fromsearch-mesh3

@jamestkellyView MCP→

investor-update-skill

Write investor updates your investors actually read — with Claude Code (or any agent that supports skills).

1 skill4

@pitchdriveView Plugin→

init

Stand up a kraken coordination repo end to end — verify or create the private repo, install the bundled task template, remove everything an earlier release…

fromkraken4

@rafael-adcpView Skill→

agent-factory

Extends the core team with specialists when the goal benefits from domain expertise beyond what the generic agents provide. Runs once after the planner. Never…

fromloop-engineer3

@vibhasduttaView Agent→

audit

Run security audit checklist on current smart contract project

fromclaude-codex-crypto-devkit3

@arcticwolfxzView Command→

adamlinscott-claude-sk…

Each skill lives under skills//SKILL.md and is the single source of truth; an install script links them into the global skills directory (~/.claude/skills/) so Claude loads them in every session, on every machine.

19 skills3

@adamlinscottView Plugin→

attio-deepline-enrich

Enrich records inside Attio with a clear cost gate before any credit is spent. Pull a chosen object (companies, people, or custom) from Attio, fill chosen…

from5050-gtm3

@nacholafuenteView Skill→

build-doctor

Native build failure specialist for React Native projects. Delegate when an iOS or Android build fails and the fix may take several investigation rounds, or…

fromclaude-code-react-native3

@anilburcuView Agent→

check

Full repo scan — duplicates / unused / oversized / unfinished work, then a subagent verifies every candidate

fromhi-vibe3

@jx-hxxxView Command→

sketchloop

Sketchloop is an agent skill that lets your coding agent create beautiful, hand-drawn-looking diagrams.

1 skill3

@alexander-posztosView Plugin→

batch

Dispatch a night's batch of Todo tickets — one worktree and one pull request each — and leave a morning summary. Run explicitly; never inferred.

fromcsw3

@mikestankavichView Skill→

cloud-troubleshooter

Use when inspecting, diagnosing, or validating the actual state of running systems — pods, services, logs, cloud resources, network connectivity, SSH access —…

frommetraton-gaia3

@metratonView Agent→

deploy-rw

Deploy remote-workstreams on this Mac — tmux + Tailscale, Deepgram/Cartesia keys into the Keychain, pairing PIN, launchd service, tailscale serve, pairing QR,…

fromremote-workstreams3

@ryan-scheinbergView Command→

icode-skill

6-step workflow: Plan → Review → Finalize → Code → Deep Check → Audit. Run all at once, or step-by-step and switch models between steps.

1 skill3

@ayukyoView Plugin→

build-discipline

A language- and domain-agnostic engineering discipline for building non-trivial software that actually survives real use — services, parsers, CLIs, data…

frombuild-discipline3

@rohansxView Skill→

e2e-runner

Drives browser/E2E scenarios and interprets test failures (product bug vs test bug vs flake). Costlier than test-runner - use test-runner for plain…

frommodel-routing3

@aquegenView Agent→

mind-clone-ask

Ask a mind-clone of an author — advice, or their likely view on a topic

frommind-clone3

@mrgnfndr-drView Command→

living-manual

A Claude Code plugin that builds and maintains a branded, interactive user's manual for any codebase. The manual is one self-contained HTML file: Click any heading to make a note (idea, feedback, bug).

2 skills3

@dougstanfordView Plugin→

calibrate-my-voice

Build or refresh the local voice-layer profile used by write-in-my-voice from user-approved evidence. Use only when the user explicitly asks to calibrate,…

fromvoice-layer3

@ymeiriView Skill→

verifier

Independent grader for loopcraft loop-tasks. Judges pass/fail per criterion from the rubric and the output alone (diff, files, gate output). Never receives the…

fromloopcraft3

@hiphapisView Agent→