🔌
Plugins
Loading...
Showing 30 of 27329 results
wf Node/TypeScript stack pack: the node-ts capability owning a dependency-free unit-test harness for pure TS helpers (parsers, formatters, coercion helpers) that need no Angular runtime. Ships /wf-node-ts:test-node; the implement phase aggregates its test-authoring guidance when registered. Tracker-agnostic (requires: git only). Ships /wf-node-ts:init for one-command self-registration.
wf PR-review feature pack: the pr-review feature capability shipping the user-invoked /wf-review:address-pr and /wf-review:review-pr skills. Reads/verifies/addresses review comments and CI failures and posts verified findings entirely through the delivery provider's PR-interaction operations (pr-comments-read/pr-comment-post/checks-read/review-thread-resolve), treating review-tool output as hypothesis. Composes natively on install for its two skills; ships /wf-review:init for one-command self-registration of the pr-review capability ahead of its first contribution fragment.
wf skill-eval harness pack: the sandbox-testing feature capability. Runs real headless wf:* skill invocations hermetically in a fingerprinted container (runner/), judges the runner's structural outputs — terminal block, workspace file set, invoked contract-op set — statistically over N runs and emits a variance-aware report separating drift from regression (assert/), ships the SMOKE/STATISTICAL tier commands and the baseline-comparison primitive, the behavioral-regression corpus mined retrofit-first from observed failures (corpus/), and the findings-loop procedure that turns a new observed failure into an assertion. Owns no provider surface and attaches no phase fragment; downstream fixtures that script a provider pair with the wf-fake pack (enforced loudly at run time, not via requires:). Ships /wf-sandbox-testing:new-experiment, an interview-driven scaffolder that emits a runnable experiment kit — manifest, kit-root files, and an engine-derived runbook — for the shared experiment engine, plus /wf-sandbox-testing:init for one-command self-registration.
Provenance-tracked research assistant over a Neo4j knowledge graph.
Pixel-retro whack-a-mole that auto-opens when Claude takes a while to respond.
Streamable-HTTP MCP access to whagent-net's Agent API (start_session/send_turn/stop_session/get_session/read_transcript) across tilt/dev/prod
Monitor large crypto transactions and whale wallet movements in real-time
Claude skill for Feishu (Lark) platform integration and workplace automation.
Turn your Copilot sessions into proof of impact — research-grounded HTML reports with effort estimation, skills analysis, and ROI metrics from local session logs.
WhatsApp Agent Builder by Jack Vidal — guides non-technical users through building a Wasender-powered WhatsApp AI agent in Hebrew.
WhatsApp channel for Claude Code — linked-device messaging bridge with built-in access control, pairing, allowlists, and group policy.
Personal WhatsApp MCP server built directly on whatsmeow. Local-only Go bridge with SQLCipher-encrypted storage, Python FastMCP layer, Whisper voice-note transcription, accent-insensitive Spanish search, LID name resolution, vault-native CRM auto-injection, prompt-injection scrubbing, and mandatory draft+confirm on every send.
WhatsApp Plus: your personal WhatsApp as MCP — 65 tools with self-managed QR login.
Use when someone needs word-level timestamps from audio — lyric alignment, cut-safe line boundaries, or caption source timing before burn-in with video-editing.
Wispr Flow voice-to-text MCP (HTTP). OAuth on first connect.
Bootstraps a repo's release discipline end to end: repo init, Conventional Commits enforcement, semver-driven version bumps, and CHANGELOG-driven GitHub Releases — plus an inspect skill to audit and retrofit existing repos.
Analyze your environment and recommend official marketplace plugins to make Claude Code smarter
Unified code + memory + knowledge estate graph tools for LLM agents. Single binary (wicked-estate-mcp v0.13.0) serves 23 tools across three domains: estate (code graph), memory, and knowledge.
Your coding agent already plans and swarms — Wicked Garden is the curated toolkit for what it can't: proof-not-claims gates, code links grep can't see, deterministic refactor, cross-session memory, real multi-model second opinions. Don't fight the harness; fill its gaps. The gate needs wicked-vault (a self-contained infra peer, installed directly) and re-derives through garden's built-in engine; estate/bus are opt-in layers (wicked-testing and wicked-brain are retired — QE ships in-catalog as the qe domain, memory lives in wicked-estate).
Standalone QE library for AI coding CLIs — 5-core testing surface (plan/authoring/execution/review/insight), SQLite ledger with fixed-SQL oracle, 3-agent acceptance pipeline, optional wicked-bus + wicked-brain integration.
Unified AI-native Vibe Coding plugin: PRD generation, digging analysis, screen-spec (IA / User Flow / Wireframe HTML / Dev Handoff), team-based parallel implementation, quality-gated auto-commit, 20 design styles, frontend (React/Next.js), backend (NestJS/Prisma), mobile (React Native/Expo), AI integration (STT/LLM), DevOps (Docker/CI-CD). 13 agents, 5 commands, 6 skills.
Opinionated, template-driven wiki maintenance — the wiki-author authoring/learning skill, the documenter agent, the diataxis-evaluator, recent-wiki-changes, and the check-wiki.py linter. Maintains a wiki in the operator's voice; enhances developer-workflows' phase-boundary documentation when both are installed.
Maintain a Karpathy-style LLM wiki on Obsidian using the native obsidian CLI — Claude synthesizes, the CLI does links/search/graph-health, Ollama does drift.
Skills implementing Karpathy's LLM Wiki pattern: wiki-init, wiki-ingest, wiki-query, wiki-lint, wiki-audit, wiki-update, wiki-merge
Project LLM wiki: ingest, query, process queue, lint, plus proactive research hook.