48 plugins from public Claude Code marketplaces. Each one bundles skills, slash commands, agents, hooks or MCP servers that install together.
Showing 48 plugins that match these filters.
butterbase-skillsbutterbase-ai/butterbase-skills1
agentii-investment-intelligenceagentii-ai/agentii-investment-intelligence1
wasp-nestlegioncodeinc/vibe-coding-tools1
zetetic-marketplacecdeust/zetetic-team-subagents1Submit the repo with .claude-plugin/marketplace.json and we list every plugin.
Submit marketplaceEval-gated LLM fine-tuning lifecycle (LoRA/QLoRA, DPO, GRPO/RLVR, vision SFT, quantized export). Use when fine-tuning an open-weights model end-to-end: building the eval harness first, selecting method and model, preparing data, training with Unsloth or TRL, gating checkpoints, and exporting GGUF/FP8.
Build, launch, grade, and schedule Claude Managed Agents (CMA) in your own Anthropic account — a plugin re-implementation of Anthropic's launch-your-agent reference skill (Apache-2.0; independent, not a fork). Every session starts with a goal (./my-agent/goal.json, opt-in SessionStart hook, driven by /cs-goal); loop_compiler.py compiles it into a bounded grade->iterate loop (max_iterations 1..20), a recurring cron scheduled-deployment loop, or a single-pass interview->stage->launch workflow. 6 skills: orchestrator (context: fork goal router) + interview + stage-launch + grade-iterate + run-without-you + wrap-up. 18 stdlib-only deterministic scaffolders (no network/API calls; live launches emitted as BYOK curl that never prints the key), 4 agents, 8 commands, hooks, 5 references, 4 assets. Validators enforce CMA limits. Distinct from engineering/agent-harness (generic domain loop) and write-a-skill (authors Claude Code skills, not CMAs).
Email-workflow skill pair: inbox-setup builds your taxonomy/KB; inbox-triage classifies + drafts (drafts-only, never auto-send). KB-file contract between them. Path-B from megaprompts 06+07.
Build full-stack apps with Butterbase — AI-Native Backend-as-a-Service. Skills for app creation, schema design, frontend deployment, RLS debugging, serverless functions, and contributing.
Gate a UI before it is called done: check the build, not the design file. Three deterministic stdlib scripts: a finish linter that blocks on controls that do nothing, dead links, placeholder copy and removed focus rings, and warns on template defaults; an interaction-state checker that derives loading, empty, error, busy and focus states from each surface's kind and blocks when they are missing or unevidenced; and a rendered audit that reads a browser snapshot and blocks on WCAG 2.2 AA failures in contrast, focus visibility, focus obscured, reflow at 320 px, accessible names and target size. Ships a read-only snapshot collector, an optional Playwright keyboard pass, cs-design-qa agent, /cs-design-qa and /cs-ui-finish-lint commands, 3 cited references and a finish sign-off.
Marc Andreessen-mode decision and productivity skill. Market-first operator that pressure-tests ventures/ideas/features/bets (market > team > product; product/market fit is the only milestone; bias to build) and runs the 3x5-card + Anti-Todo routine. Fixed anti-sycophancy operating prompt: counterargument first, no disclaimers, explicit confidence levels, no capitulation. Issues hard verdicts backed by deterministic stdlib tools.
Deep Work day planner. Classifies tasks deep vs shallow with a shallow-work budget verdict (plus the recent-graduate forcing question), builds a time-blocked schedule (deep blocks of 90+ minutes first, shallow batched, buffers, refuses more than 4 hours of deep demand), and logs focus sessions against a weekly deep-hours target with streaks. Fills the time/attention-management gap from audit/productivity-2026-07.
Meeting discipline. Cost-gates every meeting before it exists (MEET / ASYNC / NOT-READY verdicts with real dollar cost incl. optional refocus overhead), builds timeboxed agendas that refuse topics without a desired outcome (decision topics first), and extracts owned action items from raw notes with ORPHAN / NO-DUE flags. Fills the meeting-hygiene gap from audit/productivity-2026-07.
Turn a tangled working tree into a clean, reviewable commit series. Three deterministic stdlib scripts over git: a series planner that groups changes into commits in build-safe order (manifest with lockfile, pure moves, formatting, each module's change with its tests, docs, CI), holds back .env and key files, and flags mixed formatting and moves whose callers would break; a secret gate that scans staged or pushed lines for provider tokens, high-entropy secrets, sensitive files and conflict markers and blocks before the commit exists, with redacted output and reasoned waivers; and a message linter that blocks vague subjects, missing why on large changes and pending fixup commits, matching the repo's own convention. Ships pre-commit, commit-msg and pre-push hooks, cs-commit-craft agent, /cs-commit-craft and /cs-commit-check commands and 3 cited references.
Run a faster, provable month-end close. Three deterministic stdlib scripts: a close calendar planner that orders tasks by dependency, finds the critical path and slack, maps WD+n deadlines to dates and blocks on missing owners, missing or self-review of key controls and a critical path past the target workday; a reconciliation matcher that matches GL to bank or sub-ledger by reference then amount and date, builds the proof, ages reconciling items and blocks on any unexplained difference or preparer-as-reviewer; and a flux analyzer that applies your materiality rule and refuses material fluctuations explained with boilerplate or without a quantified driver. Ships cs-close-controller agent, /cs-month-end-close and /cs-flux-review commands, 3 references citing COSO 2013 and PCAOB AS 2201 / AS 2305 / SAPA 11, and a reconciliation sign-off template.
Company Architect: builds a business from scratch as an OKF (Open Knowledge Format) bundle — a tree of versionable .md files with a frontmatter type, links forming a graph, and reserved index.md/log.md, readable by humans and agents alike. Guides the founder through a 12-phase interview (foundation, strategy, market, financial, sales, marketing, product, operations, tech, people, legal, governance), one phase at a time, and generates conformant markdown concepts. 3 stdlib tools: scaffold_bundle (bundle scaffold), okf_linter (validates type/reserved files/links), index_generator (regenerates the index.md files). Standalone-installable; also bundled in c-level-skills. In English.
Workflow-builder skill: design and write deterministic multi-agent workflow scripts (.js files in .claude/workflows/) for Claude Code's Workflow tool (CLAUDE_CODE_WORKFLOWS=1, /workflows). Every session opens with an intake question set; when the user is vague, a stdlib recommendation engine infers and proposes a topology with rationale instead of stalling. Ships 3 stdlib Python tools (intake recommendation engine, .js validator enforcing pure-literal-meta / no-non-determinism / guarded-loop / parallel-thunk rules, topology scaffolder), 3 references citing 7-8 authoritative sources each (API surface, orchestration patterns, decision + intake guide), templates + a runnable example, cs-workflow-architect persona agent + /cs-workflow-build slash command. Use when building, scaffolding, or running a custom Claude Code workflow or orchestrating sub-agents (fan-out, pipeline, loop, judge-panel).
Turn any domain folder of skills into a bounded agentic loop: a manifest builder inventories a domain's skills/tools/checks, a goal compiler turns a goal into a verifiable task plan (refusing vague goals with forcing questions), and a JSON-backed loop controller drives execute->verify->close with retry caps, controller-run verification (no verification theater), human escalation on exhausted budgets, and a close gate that refuses while any task is unverified or unwaived. Ships 3 stdlib Python tools, 18 committed per-domain harness manifests + JSON schema, 3 references citing the 2024-2026 agent-harness canon (Anthropic long-running harnesses, verifier's law, SWE-agent, Ralph loop, Cognition), harness-runner agent + /cs-harness command. Use when an agent or subagent should pick up a goal, define its tasks, complete and verify them, and close the loop.
Grade an agent setup from real conversation history — a rebuild of warpdotdev/common-skills' skill-doctor (MIT). Harvests recent local Claude Code and Codex sessions scoped to one repo, condenses and secret-redacts transcripts (12-pattern redactor, chmod-0600 artifacts, nothing uploaded), has the agent judge each transcript against two verbatim-preserved rubrics (efficiency, code quality — labels only), then runs a deterministic aggregation gate that derives every number from the label tables, refuses scores for unsampled sessions and suggestions that cite no scored session, and renders one self-contained zero-JS HTML report (dark-mode, print-to-PDF). Proposed skill edits stay staged as diffs until an explicit per-skill yes; zero suggestions is a valid, reportable success. Ships cs-skill-retro agent, /cs-skill-retro command, 3 stdlib tools, 3 references citing 7 sources each.
Pressure-test a business idea before you build it. Convenes a 5-angle adversarial panel — The Critic (what kills this?), The Champion (the 10x upside?), The Analyst (does the logic hold?), The Investigator (what does the market say?), The Customer (would I actually pay?) — fired in parallel as independent reviewers, then a Judge synthesizes one GO / RESHAPE / KILL verdict with explicit confidence and the cheapest 48-hour test to de-risk it. Never averages the scores: a weighted synthesizer with demand/fatal-flaw/logic veto gates produces the call, backed by deterministic stdlib tools.
Human-verification gate for an agent loop: builds a single-file review page (the page itself makes no network request; a reviewed HTML artifact's own https: assets still load), collects batched feedback as structured batch.v1 data instead of chat prose, and refuses to close while a BLOCKER is open, the reviewer is unnamed, or nobody has reviewed. Non-blocking, headless-guarded, round-capped. Stdlib-only.
Convert a rambling description of a desired outcome into one polished, autonomous /goal prompt ready to paste into a fresh session. Extracts deliverable/quantity/stakes/tools/destination, asks at most one question batch, verifies every named resource against the live environment, writes a 150-350 word prose prompt with the seven-part anatomy, and self-checks six binary criteria before delivering. The output is a single copy-paste prompt, never the build itself.
9 financial-modeling + presentation skills: DCF, comps, 3-statement, LBO, SOTP-valuation, audit-xls, xlsx-financials, earnings-preview, and pitch-deck. All Excel-producing skills follow the FR-044 4-step office protocol (spec → build → recalc → audit).
Build web interfaces and sites with React, Svelte, design systems and accessible components.
Complete system: 15 problem-shaped skills backed by 97 genius agents, 86 skills total, 30 commands, 71 tools, 36 hooks, authoritative coding-standards rules, goal-driven and autonomous build loops, and the shared Claude Code and Codex gates
