81 Plugins aus öffentlichen Claude Code marketplaces. Jedes bündelt Skills, Slash-Commands, Agents, Hooks oder MCP servers, die zusammen installiert werden.
Zeige 81 Plugins, die diesen Filtern entsprechen.
pm-claude-skillsmohitagw15856/pm-claude-skills2
awesome-journal-skillsbrycewang-stanford/Awesome-Journal-Skills2
pskoett-skillspskoett/pskoett-ai-skills1
claude-code-workflowswshobson/agents1Reiche das repo mit .claude-plugin/marketplace.json ein und wir listen jedes plugin auf.
Marketplace einreichenSkills for using AI itself well — picking the right tool, delegating to it, briefing it with context, designing AI workflows, verifying its output, and catching its mistakes.
Process discipline for professional work — the difference between an agent that produces output and one that produces outcomes. Interview the requester before building, brainstorm divergent-then-convergent, write and execute real plans, verify before declaring done, orchestrate subagents, work incrementally, and simplify what you built.
Two-loop skill pipeline for Claude Code. Inner loop (plan-interview, intent-framed-agent, session-context, context-surfing, verify-gate, self-healing, simplify-and-harden) catches failures in-session — including active runtime recovery via self-healing when a command, test, build, helper, env, or external service fails mid-task. Outer loop (learning-aggregator, self-improvement, eval-creator, pre-flight-check) captures recurring patterns, promotes them to CLAUDE.md as permanent rules with human approval, and turns failures into regression tests. The harness gets stronger with every cycle.
Twelve-skill bundle covering the International Organization (IO) manuscript lifecycle for international-relations research, centered on IR theory, IPE/security scope, and IO's verify-before-publication transparency policy.
academicCross-journal author workflow toolkit (11 skills): pick the venue (journal-match runs tools/match_venues.py over a generated index of 743 venues with a resubmission-ladder graph, and is measured against a held-out gold set), cost the submission ladder in months and probability of placing, verify an unfamiliar venue against primary sources before submitting, reframe a manuscript from one venue to another, run the analysis through the StatsPAI / Stata MCP execution bridge, self-check submission readiness, score desk-reject risk against the target's own documented triggers, rehearse a calibrated referee panel, draft the point-by-point response, and assemble a Data-Editor replication package. Venue-neutral; reads each target pack's skills + official-source-map for the venue bar and live facts.
academicTurn 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.
Disciplined multi-source meta-research for high-stakes questions — the heavyweight alternative to the fast research router. 9-phase pipeline (reframe into falsifiable hypotheses, plan, capability discovery, parallel sub-agent fan-out, score & triangulate, synthesize + adversarial pass, verify, refresh targets). Triangulates every thesis against >=3 independent differently-typed sources; per-source files with verbatim quotes; never fabricates a citation. Auditable, reusable folder + delta-update refresh protocol. Contributed via PR #851.
PreToolUse hook that prevents AI agents from using --no-verify, --no-gpg-sign, and other bypass flags that skip git hooks
Engineering discipline for AI coding agents: question the request, verify against current docs instead of memory, plan, build test-first on the cheapest capable model, review with a second model family, prove it before saying done
Production-ready skills and agents for Craft CMS 5 development. 14 skills (including a name-routed plugin-reference index, Pest testing, plugin release mechanics, Craft Cloud, Servd, and fortrabbit hosting), 6 specialized agents with explicit build-verify gates, 24 plugin references, project scaffolding.
Establish and verify project technical foundations using native stack mechanisms, explicit contracts and safe recovery.
A disciplined coding pipeline that grounds code in verified structure before a line is written: Discuss -> Map -> Decompose -> Execute -> Verify, with a lazy-senior-dev YAGNI ladder that deletes unnecessary code first. No invented APIs, no assumed imports, no placeholder code. Opt-in for high-stakes, complex, or multi-file work; not for trivial edits. Synthesizes four MIT/open-source projects (Ralph atomic loop, GSD Core context engineering, Graphify KNOWN/INFERRED/UNKNOWN mapping, Ponytail lazy-senior hierarchy). Contributed via PR #854.
Loops (a file-based knowledge base) + a codebase harness (dev-local, e2e, crabbox cloud boxes, verify-before-ship) so agents can run, test, and ship code autonomously.
engineeringAnalyze DWARF debug information: parse and search DIEs with dwarfdump and readelf, verify debug info integrity, and write DWARF parsing code
Review authentication declarations and verify explicit local JWT profiles
Mutation testing to validate test quality by introducing code changes and verifying tests catch them
Quick smoke test suites to verify critical functionality after deployments
AI with a harness. Agent skills, rules, CI and security gates for AI-assisted development — a diagnose → issue → plan → resolve ⇄ verify loop, shipped as one harness.
Itqan — engineering skills suite (إتقان: mastery of the craft). 12 model-agnostic skills running the full software-engineering lifecycle: a resumable orchestrator (engineer), six phases (define, blueprint, construct, verify, inspect, release), and five specialists (discover, design, harden, assess, learn), with auto-detected discipline packs for backend, frontend, mobile, AI/ML, and any language. Approval gates before code, test-first builds, evidence before "done". Invoked explicitly, never auto-triggered.
Verify a running web app from the inside. Installs the Reticle skill and registers the Reticle MCP server.
testing
