Recently added
Plugins grouped by the day they were added to the directory, newest first.
Aug 25, 2026
- human-gate27.6kstars
The human-verification lane for an agent loop. Builds a single-file HTML review page for a Markdown or HTML artifact (opens over file://, makes no network request of its own, and sanitizes reviewed HTML -- on* handlers, javascript: URLs and iframes are dropped so a draft cannot execute inside the page), collects batched feedback as a structured batch.v1 artifact instead of chat prose, and runs a gate that refuses to close while a BLOCKER is open, the reviewer is unnamed, the sidecar changed after collection, the round carries unresolved integrity problems (a mistyped severity silently downgrades to NIT, so a real blocker can be lost to a typo), or nobody has reviewed at all. Non-blocking by design: no poll loop, a headless guard, a round cap, and escalation on exhaustion. Feedback lands in a hand-writable Markdown sidecar, so the loop still works over SSH and in CI where no browser exists. Use before shipping a plan, spec, RFC, report, or any irreversible action, or when the user says 'let me review that', 'get sign-off', or 'don't ship until I've seen it'. The human counterpart to agent-harness's machine verification -- NOT a content humanizer (see content-humanizer / behuman).
Claude Code1 skill - agent-memory27.6kstars
A four-tier memory ladder for Claude Code where promotion is earned by recurrence, not asserted by confidence. L0 raw transcripts are never injected; L1 candidate atoms are gitignored and recalled on lexical relevance per prompt; L2 project context loads once per session; L3 stable persona is always loaded. Promotion from L1 to L2 requires at least three distinct sessions spanning at least two distinct calendar days (a stated claim needs two sessions, still spread across days; a deterministically verified claim is the only single-observation path), and L2 to L3 requires two distinct projects and thirty days. Two gates refuse rather than guess: a claim whose text was altered by the seventeen-pattern redaction pass never promotes on evidence alone, and a claim with an open contradiction freezes until a human resolves it, found by reverse join because the newer atom carries no flag. Three hooks run the loop unattended and every one fails open. Nothing reaches a committed CLAUDE.md without an explicit human adopt that backs both files up first. Ships five stdlib scripts, three hooks, a cs-memory-curator agent, a /cs:memory command, a JSON schema, a sixty-nine-check example validator, and a design document with its open decisions ranked by what they gate.
Claude Code1 skill - c-level-agents27.6kstars
Founder-mode executive team plugin: 13 cs-* C-suite agents (CFO, CMO, CRO, CPO, COO, CHRO, CISO, Chief of Staff, General Counsel, Chief Data Officer, Chief AI Officer, Chief Customer Officer, VP of Engineering) plus 21 /cs:* slash commands for forcing-question office hours (incl. /cs:vpe-review), multi-role boardroom deliberation, strategic sprint pipeline, and meta routing. Wraps the 33 c-level skills (including vpe-advisor with delivery throughput DORA analyzer + eng hiring funnel calculator + eng team structure designer) with cognitive gearing and artifact handoffs.
Claude Code22 skills - agent-launcher-skills27.6kstars
Turn Anthropic's launch-your-agent reference skill into a full domain plugin for building Claude Managed Agents (CMA). Every session starts with a goal (./my-agent/goal.json, surfaced by an opt-in AGENT_LAUNCHER_SESSION=1 SessionStart hook and driven by /cs:goal); a deterministic loop_compiler.py compiles that goal into a grade->iterate loop (CMA user.define_outcome self-grading, bounded by max_iterations), a recurring cron scheduled-deployment loop (run without you), or a single-pass interview->stage->launch workflow. 6 skills: agent-launcher-orchestrator (context: fork goal router) + interview (build sheet: primitives table + v1/v2 deferrals + eval plan) + stage-launch (validated env/agent/session/kickoff payloads + resumable BYOK curl launch script that never prints the key) + grade-iterate (outcome/rubric + verdict reader + held-back eval scaffold) + run-without-you (POSIX-cron deployment + NEXT-DIRECTIONS) + wrap-up (primitive inventory + regenerated overview HTML + next upgrades). 18 stdlib-only deterministic scaffolder tools (no network/API calls; live launches emitted as BYOK curl), 4 agents (orchestrator + interviewer + grader + deployer), 8 commands, opt-in SessionStart/SessionEnd hooks, 5 shared references, 4 assets. Validators enforce CMA limits (<=20 skills/session, <=8 memory stores, <=20 roster / 25 threads / depth-1 multiagent, max_iterations 1..20, <=20 creds/vault, <=1000 deployments/org). Inspired by anthropics/launch-your-agent (Apache-2.0); independent re-implementation, not a fork.
Claude Code6 skills - apijack7stars
Jack into any OpenAPI spec — full CLI with AI-agentic workflow automation
Claude Code2 skills1 MCP server - token-cost0stars
Records token usage for every completed task into a private per-project ledger, and shows it as a table with /token-cost.
Claude Code - trailhead0stars
Start and drive large projects as a map of tickets on GitHub Issues, resolving one at a time. Map-based onboarding + a discuss→plan→execute→verify engine with atomic commits, all on the Issues. Ships as a dispatcher plus cohesion-clustered skills over a shared core; depends on nothing beyond an authenticated gh CLI.
Claude Code6 skills - v12x-scan0stars
Auditoria de segurança em profundidade: determinística, verificada, com veredito de publicação. Método v12x.
Claude Code - v12x-design-audit0stars
Auditoria de conformidade ao design system, com aplicação das trocas. Método v12x.
Claude Code1 skill - v12x-agent-audit0stars
Auditoria de confiança de agentes, servidores MCP e skills antes de instalar ou publicar. Método v12x.
Claude Code - dex24stars
Analytics engineering for Claude Code and any agent: data warehouse exploration, dbt transformation and semantic modeling, and schema-drift maintenance on dbt.
Claude Code - julianleiss-portfolio0stars
Agent skill for reading Julián Leiss's portfolio (julianleiss.com): projects, services, availability, pricing and contact, all in markdown.
Agent Plugins3 skills - school-leader0stars
Toolkit for principals, deputies, and school administrators — draft whole-school and community communications in a consistent voice, explain curriculum changes to families, and keep an eye on the school's assessment calendar.
Claude CodeAgent Plugins3 MCP servers - relief-teacher0stars
Toolkit for casual and relief teachers covering an unfamiliar class — build or adapt a day pack, put together a lesson and student task sheet on short notice, check a plan for support needs, and run a quick end-of-lesson check.
Claude CodeAgent Plugins3 MCP servers - learning-support-teacher0stars
Toolkit for learning support, inclusion, and EAL/D specialists — generate and audit differentiation options, adapt task sheets and checks for individual students, and draft report comments and family communications for a support caseload.
Claude CodeAgent Plugins3 MCP servers - curriculum-coordinator0stars
Toolkit for curriculum coordinators, heads of department, and instructional designers — map scope and sequence, design inquiry and project units, build assessment schedules and rubrics for cross-marker consistency, catalogue resources for a repository or LMS, and explain curriculum to families.
Claude CodeAgent Plugins3 MCP servers - classroom-teacher0stars
Full-time generalist teacher toolkit — plan lessons and units, build assessments and rubrics, differentiate for mixed-readiness classes, run inquiry/project units, and draft parent- and report-facing communications in your own voice.
Claude CodeAgent Plugins3 MCP servers - coco-sf-solutions1stars
Snowflake industry solution accelerator skills bundled with Snowflake Cortex Code (CoCo).
Agent Plugins1 skill - coco-databricks1stars
Databricks development skills bundled with Snowflake Cortex Code (CoCo).
Agent Plugins12 skills - coco-bundled-skills1stars
Snowflake Cortex Code (CoCo) bundled skills, redistributed with written permission from Snowflake.
Agent Plugins50 skills - coco-blueprints1stars
Snowflake Blueprint Manager bundled with Snowflake Cortex Code (CoCo).
Agent Plugins1 skill - coco-airflow1stars
Astronomer data-engineering and Airflow skills bundled with Snowflake Cortex Code (CoCo).
Agent Plugins18 skills - bro1stars
Restate the assistant's previous response in plain, concise language.
Agent Plugins1 skill - ojiman-skills0stars
A small personal collection of Agent Skills, each written up from something that actually went wrong on a real project.
Claude CodeAgent Plugins1 skill - ai-driven-dev-principles0stars
AI駆動開発ガイドラインを実装するスキル群（start-work, decision-log, session-handoff, feature-block-design, retrospective ほか）。導入先プロジェクトの AGENTS.md と組み合わせて使用する。
CodexClaude Code13 skills - ai-driven-dev-principles0stars
AI駆動開発ガイドラインを実装するスキル群（start-work, decision-log, session-handoff, feature-block-design, retrospective ほか）。導入先プロジェクトの AGENTS.md と組み合わせて使用する。
Claude Code13 skills AI coding delivery trust layer for governance-aware coding agents. Tracks goals, evidence, risks, quality budgets, and release readiness without making broad runtime claims.
CodexClaude Code26 skills- eric-agent-skills0stars
Portable skills for educational documents, PDF design, presentations, websites, video production, and reliable agent workflows.
Codex50 skills Australian public-practice workflow skills: BAS tie-out, FBT, Division 7A, STP finalisation, and workpapers. Prep-only. Not lodgment. Not tax advice.
CodexClaude Code- july-ai-workflow0stars
显式调用的 July/Luban Unity 研发流程：分步生成 GDD、MDD，并严格实施一份指定 MDD
Codex1 skill - chatcut-desktop919stars
Install, open, and connect the signed ChatCut Desktop app from Codex.
Codex1 skill - l3a019stars
l3a0's Claude Code skills. Currently: kindle-highlights — extract a book's Kindle highlights into one verbatim, location-cited Markdown file, recovering everything Amazon's export limit truncates or hides.
Claude Code1 skill - dely0stars
An automation-first, Orca-supervised delivery protocol for coding agents.
CodexClaude Code2 skills - flutter-styleguide0stars
Mandatory Flutter/Dart architecture and code style: pub workspace, flutter_bloc, go_router, injectable, dart_mappable.
Claude Code3 skills - ach-memory0stars
Durable memory for Codex through the ach-memory service.
Codex1 MCP server - ach-memory0stars
Durable memory for Claude through the ach-memory service.
Claude Code1 MCP server - webster2stars
Production documentation for an app you built, in a fixed layout modelled on Harvester: subject-first directories and a Docusaurus site whose navigation is the filesystem. Every page declares both what it is and who it is for, with sections from The Good Docs Project and quality checks from the ISO/IEC/IEEE 26514 characteristics: type mixing, alt text, heading order, and reading grade measured against that page's own reader. Extracts the reference material, anchors every claim to a file and line, measures drift against a recorded manifest, and refuses to state what it could not check.
Claude Code9 skills - weave2stars
Generate really good dynamic Workflow scripts on demand. /weave:make <task> classifies the task into an orchestration archetype (understand / design / review / research / migrate / generic), picks the right fan-out topology (pipeline by default, barrier only when a stage genuinely needs all prior results), and authors a self-contained Workflow script that obeys the Workflow tool's hard rules — pure-literal meta block, schema'd agent returns instead of text parsing, .filter(Boolean) after fan-out, adversarial-verify for findings, loop-until-dry / loop-until-budget for unknown-size work, isolation:'worktree' only for parallel file mutation, no Date.now/Math.random. Every script is validated with `node --check` and a 12-point self-audit before it is saved to .claude/workflows/ or run. Weave writes the orchestration so you don't freehand it.
Claude Code - ux-review2stars
Experiential UX review that drives the RUNNING app as a real user — not a code read. Reading source is a code review and structurally cannot find experience defects (a mode that doesn't do what its label claims, an overlay anchored to the wrong thing, a feature that silently breaks in one state, a table-stakes affordance that's simply absent). /ux-review:run launches the app, self-configures by discovering what the product is, who it's for, and what it promises, then builds a coverage grid (every screen × state × variant × viewport × input modality) and drives real jobs-to-be-done end-to-end through five sharp lenses — promise-vs-delivery, default-vs-buried, anchor/subject, every-state-not-the-happy-one, and what's-missing — plus the classic heuristics framed experientially. Adversarial states (empty/error/offline/slow/denied/first-run), a keyboard + screen-reader + mobile sweep, and console/network watching catch silent failures. A completeness critic loops until a full pass finds nothing new, and every finding is logged as job → expected → actual (+screenshot) → why-it-hurts → severity, ranked by user harm, with an auditable coverage report. Drives real browsers via Playwright MCP; the persona-driver subagent fans out one driver per persona × surface for exhaustive parallel coverage.
Claude Code1 skill - tldr2stars
Always-on response shaping. A SessionStart hook loads a 10-rule ruleset into every new session — first line is the action, numbered multi-step work, restate where we are each turn, one concrete next action, concrete time estimates, visible wins, flat tone on failure, lists capped at 5, no preamble/recap/sign-off — plus six break-glass exceptions (depth requested, destructive action, debug spiral, real ambiguity, rule-would-delete-the-answer, harness outranks) and a pre-send delete pass. A UserPromptSubmit hook re-reads the state file every turn, so /tldr:off suspends the loaded ruleset immediately mid-session instead of next session. /tldr:verbose exempts a single turn and auto-reverts. /tldr:off, /tldr:on, /tldr:status, /tldr:help.
Claude Code - tidy2stars
Careful low-risk codebase cleanup across 7 focused tracks: deduplication, type consolidation, dead code removal, circular dependency untangling, type strengthening, error-handling cleanup, and deprecated/AI-slop removal. Each track inspects, writes a critical assessment, ranks proposed changes by confidence, and auto-applies ONLY HIGH-confidence LOW-risk changes per batch — running language-appropriate type checks, tests, and lints after each batch. MEDIUM and LOW confidence changes get surfaced for explicit human approval. Atomic commits per batch so any failing check is one git revert away. Designed for the conservative cleanup pass — never merge code that just LOOKS similar, never remove dynamically-imported code, never break legitimate boundary types, never silence real errors. Refuses to use comments as a source of truth.
Claude Code - holmes2stars
Macro-architecture / design-cohesion review — the senior-engineer 'is this shaped right or accreted?' critique, not bug-hunting or lint. Reads a codebase like Holmes reads a room: deduces the real design problem from the detail that's out of place. /holmes:review <target> runs a Workflow engine that builds a grounded structural map of the target (a path, the diff, a subsystem, or a described piece of logic), then runs 7 blind design lenses — package/module proliferation, missed sharing & reuse, helper sprawl & abstraction fit, flow & layering, cohesion, naming/structural consistency, accretion markers — each a separate agent hunting one class of design problem. Every candidate finding is adversarially verified by a skeptic that tries to refute it as intentional, so plausible-but-wrong smells get dropped; a completeness critic then re-lenses any in-scope area no finding touched. The result is synthesized into a per-subsystem deliberate/mixed/accreted verdict with file:line evidence and an ordered, concrete reshaping plan. Report only — never edits code. Forbidden from style nits, correctness bugs, or treating comments as source of truth ('everybody lies'); an empty result is a valid honest outcome for a well-shaped target.
Claude Code - foundry2stars
Autonomous build-verify-fix loop for Claude Code. Reads a Forge spec, decomposes it into castings with pre-authored teammate prompts, validates through an 11-dimension F0.9 gate (including F0.7 intent-carrier coverage), builds in parallel waves with server-side evidence re-execution and per-requirement-ID binding, runs up to 8 verification streams (TRACE, FLOW_TRACE, PROVE, RESEARCH_AUDIT, COVERAGE_DIFF, SIGHT, TEST/PROBE, TEST_OBSERVATIONS), grinds defects to zero, then assays with fresh eyes. Brownfield runs consume a flow delta; greenfield and cosmetic runs use the end-state pipeline. Forge plans. Foundry builds.
Claude Code4 skills1 MCP server - forge2stars
Codebase-aware specification engine for Claude Code. Runs parallel codebase research, then a grounded interview that captures implicit facts as A-AUTO-NNN entries, emits typed Global Invariants / State Transitions / Contracts tables, runs an adversarial spec review at R3.5, then writes a foundry-ready spec with version frontmatter (v2.1) — locked, classified, citation-backed. Detects brownfield, greenfield, and cosmetic modes; brownfield runs produce a flow delta against the existing system. Forge plans. Foundry builds.
Claude Code - e2e2stars
End-to-end test authoring and maintenance for web apps via Playwright + Playwright MCP. Claude drives a real browser, reads the accessibility tree, and emits *.spec.ts files that pass — then keeps them passing. /e2e:init scaffolds Playwright in the cwd and registers the MCP server. /e2e:write <flow> drives the browser to perform the flow and emits a green spec. /e2e:crawl discovers every route and generates a smoke spec per route. /e2e:matrix produces a routes × roles coverage suite with reused storageState. /e2e:audit runs the suite, reads trace.zip files, and triages failures by root cause. /e2e:record wraps playwright codegen for manual capture. The author skill enforces selector hygiene (getByRole over CSS), auto-wait discipline, and idempotent test design; the diagnose skill drives trace-driven flaky-test triage. The spec-writer subagent isolates MCP-driven spec authoring from the main context.
Claude Code2 skills - damu2stars
De-AI My UI — strips the tells that make an interface read as 'made by an AI in Tailwind.' Two modes, one shared catalog of ~19 slop signatures (font chaos, the purple-on-black AI palette, gratuitous parallax, weird hovers, default/neon gradients, neon gradient borders, recycled stock icons, everything-is-a-24px-card, over-rounded corners, huge drop shadows, the AI-startup serif, out-of-box shadcn, forced monochrome, icon/emoji overuse and mismatch, empty filler copy, tiny/low-contrast text). /damu:prevent renders the catalog's fixes into a copy-pasteable anti-slop ruleset, lightly tailored to the detected stack, for you to adjust and drop into CLAUDE.md or memory so Claude stops generating slop in the first place. /damu:remediate drives Playwright MCP to capture per-route screenshots plus extracted CSS facts (font counts and sizes, color clusters, WCAG contrast, radius/shadow distributions, gradient and parallax signals, shadcn/Tailwind-default signatures), then runs a holmes-style Workflow engine — a context pass that fixes what's legitimate for this product, nine blind per-tell lenses (typography, color, gradients & borders, shape & depth, layout soul, motion, iconography, copy, readability) that each hard-respect those legitimate patterns and self-rate confidence (HIGH only for unmotivated, uniform choices) so nothing is silently dropped, a completeness critic, and synthesis into a per-page deliberate/mixed/slop verdict with a ranked, file-anchored change list. Report first; --apply commits only HIGH-confidence low-risk fixes atomically and refuses a dirty tree. Governing principle: every tell is sometimes correct, so a finding is HIGH-confidence only when the choice looks unmotivated and uniform.
Claude Code1 skill - crucible2stars
A mini-foundry — the build-verify-fix engine without the MCP server or the planning interview. You bring a structured spec (requirement IDs + acceptance criteria); crucible builds it and refuses to let it drift. /crucible:build <spec-file> decomposes the spec into units with DISJOINT file ownership, shows you the split for one approval, then runs a Workflow engine: CAST (parallel deliberate-engineering builders, each handed its unit prompt verbatim, each producing re-executable evidence bound to requirement IDs) -> INSPECT (blind orthogonal verification streams — wiring exists/substantive/wired, spec-before-code assay, and server-side re-execution of every evidence command) -> GRIND (every non-passing verdict is a defect; fix and full-re-inspect, loop until zero or a cycle cap) -> ASSAY (fresh-eyes agents read the spec first, form expectations, then confirm each requirement). Refuses a dirty tree; edits the shared working tree under disjoint ownership; commits per-unit only on your say-so so any unit is one revert away. Drops what needs the heavy machinery: no MCP gates/hashing, no isolated-worktree evidence, no brownfield flow-graph interview. Keeps the load-bearing principles: the engine routes and verifies, it never re-narrates the spec or judges the code itself.
Claude Code - crew2stars
Throw an AI dev at a problem and have it own the outcome. Five Opus agents (router, scout, worker, critic, fresh-eyes) collaborate to investigate, plan, execute, and verify — SSH into systems, spin up infra, edit code, ship features, debug deploys, get airgap bundles working. Worker self-switches between investigating, planning, executing, and verifying modes. Bounded scout budget, multi-agent reflexion on stuck (N=2-3 parallel variants + judge), critic and fresh-eyes must produce evidence ledgers of commands they actually ran. One checkpoint (plan approval) for side-effecting tasks, zero for pure investigation. Plan and debrief render in chat; state files exist in .crew/runs/ for resume. /crew:goal runs the worker→critic→fresh-eyes loop unattended until critic and fresh-eyes both return pass — enforced by a Stop hook, bounded by cycle and time caps.
Claude Code - adhoc2stars
Stops Claude from racing on ad-hoc work. Methodical-mode pre-response checklist injected every turn (Restate, Verified/Unverified assumptions, Read Floor, Approach Deliberation, Blast Radius, Stall Check, Competing Hypotheses, Goal-Driven Execution). Stop hook enforces four gates: file:line citation verifier, uncertainty-tell scanner, zero-tool-call grounding audit, and an iterative two-tier critic-dialog (Haiku fast-critic rounds 1-2, opus pre-stop-critic rounds 3-5, HARD block at round 5 until /adhoc:trust-me bypass). Each critic runs a 10-item rule compliance audit and sees the prior round's feedback to verify Claude actually addressed flagged issues. /adhoc:casual (one turn skip), /adhoc:trust-me (one-turn strict bypass), /adhoc:off (session disable). /adhoc:deep for heavier analysis, /adhoc:second-opinion for independent critique.
Claude Code1 skill - foursday15stars
Operate the local Foursday work twin from Codex without a second dashboard state machine.
Codex1 skill1 MCP server