13 plugins from public Claude Code marketplaces. Each one bundles skills, slash commands, agents, hooks or MCP servers that install together.
Showing 13 plugins that match these filters.
claude-fable-5-skillskpab/claude-fable-5-skills1
build-itDevOtts/build-it1Submit the repo with .claude-plugin/marketplace.json and we list every plugin.
Submit marketplaceConvert 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.
Vision-first skills: point a camera or screenshot at the work and get the structured artifact — whiteboard photos become specs, competitor screenshots become teardowns, slide photos become board pre-reads, chart images become data tables. Built for multimodal models (Fable 5, Sonnet, Gemini); attach images in the playground or paste them in Claude Code.
The Fable Workflow: think (fable-method), act (fable-loop), prove (fable-judge), grow (fable-domain). A problem-solving loop, its orchestration, an adversarial work-verifier, and a domain-adapter generator, with the eval that keeps them honest.
10 Fable 5-native Agent Skills, updated for Fable 5.1 — over-planning, gold-plating and test bloat, fabricated progress, unrequested actions, stalled autonomous runs, and a skill-refactorer for migrating pre-Fable-5 skills.
developmentSingle-command autonomous delivery orchestrator — the build stage of the *-it lifecycle (plan-it plans it, build-it builds it); formerly fable-it. Model-adaptive for Sonnet 5 and Opus 4.8. Hand it a goal and a numbered Definition of Done and it runs the whole job to completion, conducting launch/iterate/full-qa/chrome-cdp with a 5-gate catalog, disk-backed run state, an evidence ledger (VERIFIED = lookup), a fresh-context verifier, and an honest per-criterion report.
Find your unknowns before, during, and after implementation: field-guide (router), blindspot-pass, design-directions, interview-me, reference-hunt, implementation-plan, implementation-notes, pitch-explainer, change-quiz
workflowModel/effort router: delegate a task you CAN do but is large+cheap DOWN to a lower tier to save tokens; escalate a task beyond the current tier UP for quality — up to the fable rung, the top of the ladder (a consent-gated, real-money spawn). Two-knob routing (tier × effort, effort-before-tier), an alias-floor tier ranking (haiku<sonnet<opus<fable + modelTiers pins) the platform resolves at spawn-time, a validity-gated ranking Lock that never routes on broken state, and git-optional damage control. Advise-only Phoenix-pure hook; the model performs the routing. Claude Code only.
Turns your top-tier model into a tech lead: it keeps decomposition, architecture and final synthesis, routing work to a role roster — an implementer for feature-sized coding, a worker for mechanical edits, a read-only investigator for long digs, and an independent reviewer for finished work. Every role's model is overridable from CLAUDE.md.
productivityUIKit MVVM architecture with Combine (iOS 13+). Use when refactoring MVC to MVVM, setting up Coordinators, implementing Combine bindings, or adopting DiffableDataSource.
Emulates the reasoning habits of Claude Fable 5: plan before executing, evidence over memory, self-refutation, iterative verification until it passes, lead with the result, and scope discipline.
10-80-10 token discipline for Fable 5 sessions: plan at full power, delegate the verbose middle 80% to cheaper Claude subagents, review at full power. Includes the report-only stale-config audit. Needs only a Claude subscription.
Adds a Codex reviewer (default gpt-5.6-sol, fallback gpt-5.5, via the OpenAI Codex CLI) as an independent deterministic critic: tri-state verdict bridge (approved/findings/codex_unavailable), probe mode, union rule, critique log. Requires fable-god-mode plus a paid ChatGPT plan with Codex CLI.
Pause a heavy session at a natural boundary and resume in a fresh session via an audited handoff doc + one paste-able one-liner: natural-pause discipline, dated handoff with a self-contained resume prompt, a mandatory clean-context audit (cross-model via Codex preferred when installed and consented; local clean-context subagent otherwise) applied append-only to minimize context loss, and a one-line resume command. Project-agnostic; works standalone (no Codex required).
