Find plugins

by Andrew Maston

Alternative-model fan-out engine. Manifest-driven parallel runs across capable :cloud models and Claude — background execution, digest compression, worktree isolation, and a governance-gated provider path.

by Syafiq

Personal workflow toolkit - commits, summaries, docs, invoicing, journals

by SylphxAI

Reusable Agent Skills for product, engineering, operations, design, and research work

by Ivan-WG

System-level design: service boundaries on data ownership, scaling paths, cache placement, sync vs async integration and its failure modes, single points of failure, plus domain modeling (bounded contexts, aggregates, ubiquitous language) and an event-driven skill (delivery semantics, outbox, sagas, DLQ) — firing system-design, domain-modeling, and event-driven skills, a /system-design:review command, and a system-architect worker + system-design-reviewer pair. Complements code-architecture (code-level structure) without overlapping it.

by Nery Samuel Murillo

Read-only macOS operational baseline audit workflow for local-machine diagnostics.

by 0xfauzi

The map your coding agent draws of your system: the systemap skill, which extracts the facts, drafts the model, checks it until every module is mapped, renders the page, makes a second pass with the judgement until nothing changes, and hands back the answers.

by souliane

Personal code factory for multi-repo projects

by Jason Templeton

Personal agentic development workbench with role-named agents (software-engineer, code-reviewer, product-manager, project-manager, research-librarian, ux-product-designer) backed by action-named skills for code, planning, research, product strategy, design, and ASO work

by Jordan Richlen

Set up and troubleshoot secretless GitHub Actions -> Tailscale auth via Workload Identity Federation (WIF): GitHub OIDC exchanged for short-lived Tailscale tokens, with no stored API keys or OAuth secrets.

by Anselm Hahn

Enforces declared beat order at the tool-call layer: denies an edit or a dispatch that runs ahead of the step it depends on, so cross-plugin sequencing is a runtime gate rather than a sentence a model may skip. Inert until a repository declares its beats.

by Fixture Author

Totals a ledger directory by record kind into analysis/tally/report.json. Writes only that directory.

by Tamir Cohen

27 bundled skills, smart worktree hooks, statusline, and MCP server stubs — plan, implement, review, debug, multi-agent setup, and audit code from one plugin.

by VlDubr

Bidirectional bridge between Claude Code and Codex (ChatGPT): code review, adversarial review, task delegation, background jobs, models consulting each other, and image generation via Codex's built-in tool. Runs on your existing ChatGPT subscription, no API keys.

by Tapproval

Tapproval Base — answer Claude Code's permission prompts from your Apple Watch. Nothing is ever approved automatically: a person taps Allow or Deny on the watch, or the usual terminal prompt appears exactly as before. Open source, standard-library Python only, no servers, no accounts.

by TargetBay

38 skills that decide how a store should plan, target, sequence and optimise its email and SMS marketing. Vendor-neutral reasoning; the TargetBay Email & SMS MCP supplies the capabilities.

by TargetBay

Skills that decide whether a store should run a loyalty programme, what shape it takes, what points are worth, where tier thresholds go, how a referral programme should pay, and which members are quietly leaving. Vendor-neutral reasoning; the TargetBay Loyalty MCP supplies the capabilities.

by TargetBay

Skills that turn a newly signed-up store into a store-specific programme across all three TargetBay products — auditing what the platform actually knows about this store, asking only what it cannot observe, setting up the onsite capture that must go in first, sequencing the first ninety days so the three products do not compete for the same customer, and provisioning the result behind explicit approval. Vendor-neutral reasoning; the TargetBay MCP supplies the capabilities.

by TargetBay

Skills that decide when a store should ask for a review, which products are short of proof, how to answer a falling rating, where proof belongs on the storefront, and where existing proof earns its place. Vendor-neutral reasoning; the TargetBay Reviews MCP supplies the capabilities.

by FlyingTarta

Arma 3: skills para misiones y mods, referencia offline de comandos con localidad y categorías, y linter SQF.

by Ivan-WG

Disciplined task execution: one task at a time, scope locked to the task, bounded verify-fix inner loop per task, no drift, no unbounded outer loop. Completion means every check passed with evidence — held at Stop by candor's gate (clause 4) when candor is installed; without it a run can end by narration. Ships the shared task-executor agent — the delegatable 'apply the fixes' sink every review routes to — a PostToolUse scope-lock tripwire, parallel-planning (/task-runner:plan), and the subagent discipline (the orchestration plugin was merged in on 2026-09-14): delegation contracts, verification panels, scripts/dispatch-lint.sh, and the ultra-assess boost hook.

by Ivan-WG

Idea-to-execution clarification: brainstorm fuzzy ideas into approved designs, grill requirements until zero ambiguity, deliberate the implementation approach with a blind four-persona round (via the approaches plugin when installed; inline 2-3 approaches otherwise), decide visual choices with mockups, validate whole experiences with an interactive clickable demo, then emit milestone-grouped single-prompt task cards. Outputs live under taskmaster-docs/ (no collision with a project's own docs/).

by Ivan-WG

Meta-bundle (10 plugins): the clarification-to-execution pipeline and only what it dispatches into — taskmaster planning, task-runner execution, orchestration, code-architecture, approaches, stack-scan, skill-router, plus the ui-ux, testing and security lanes its cards route to. Trimmed from 32 on 2026-08-31 to fit the host's skill-listing budget: over that cap the host drops descriptions name-only and the surviving set varies per reload, so the extra members cost reachability for every member. Install the rest individually. Uninstall cleanly with /taskmaster-suite:uninstall. 200k-window installs: see the README's context-window requirement first.

Tasks channel — comments on your claimed work and knocks at your door as in-session <channel source="tasks"> events. Binds to one session via TASKS_SESSION; read-only over the tasks server /ws.

by Devrik

Deterministic task tracking for Claude Code: persists tasks the model registers via the CLI, reminds of open tasks on a message counter, and lists active tasks on session start.