53 plugins issus de marketplaces Claude Code publiques. Chacun regroupe des skills, des commandes slash, des agents, des hooks ou des MCP servers qui s'installent ensemble.
53 plugins correspondent à ces filtres.
claude-code-plugins-plusjeremylongshore/tons-of-skills-marketplace2
claude-code-skillsalirezarezvani/claude-skills1
claude-code-workflowswshobson/agents1
capgo-skillsCap-go/capgo-skills1Soumettez le dépôt avec .claude-plugin/marketplace.json et nous listerons chaque plugin.
Soumettre une marketplaceThe Chinese workplace pack: weekly and monthly reports (周报), the year-end review (述职 / 年终总结), the promotion defence (晋升答辩), the 复盘 project review, PRD reviews (需求评审), job-level comparison (职级对标), official documents to GB/T 9704 (公文), a jargon translator that turns 互联网黑话 into plain words (and back, for fun), and Feishu docs, DingTalk logs and WeCom announcements, written in Chinese to the conventions managers expect
12 Claude Cowork-native skills that act on your real data through connectors and the sandbox — Gmail/Calendar inbox triage, meeting prep and follow-up sweeps; Drive/Docs/Sheets audits, restructures and decks; Notion/Slack decision logs, DB hygiene and async standups; GitHub/Linear issue triage, PR descriptions and changelogs. Each drives real tools and returns an artifact — not a framework you run by hand.
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.
Audit and rewrite prose that reads as machine-generated, across READMEs, changelogs, PR descriptions, docs, and blog copy, with detect-only, rewrite, and edit-in-place modes.
The restaurants & hospitality pack: menu costing and pricing, health-inspection self-audits, demand-matched shift schedules, front-of-house training, and defensible guest-incident logs
Debug REST API failures using OpenAPI specs and HTTP logs (HAR) - root cause analysis with cURL generation
Capacitor quality skills for testing, debugging, logs, performance, accessibility, security, and Xcode build hardening.
All 30 maintainer skills and 9 agent profiles: humanize and localize prose, triage, reproduce and verify bugs, review PRs, debug ML training, profile performance, bisect regressions, audit CVEs, generate changelogs, evaluate SemVer version bumps, isolate scratchpads, fix type errors, isolate faults, conduct adversarial reviews, route architect-editor edits, generate conventional commits, resolve merge conflicts, prune context, and prepare releases.
productivityLive web search, full-page content extraction, and cited research for Claude. Look up current docs, API references, changelogs, error fixes, and web data while you code, plus finance data and guided You.com API integration.
Turn screen recordings into ready-to-file bug drafts, specs, backlogs and meeting actions — local Whisper transcript + keyframes + OCR + wall-clock evidence via the talkthrough MCP server.
Jam recordings (video, console, network, logs) as context for your coding agent.
Analyze logs for performance insights and issues
When your bar comes asking "show me how you billed AI-assisted work" — and ABA 512, Florida 24-1, California, New York, and DC all have opinions out — you need an artifact that survives review. billable-time produces it. From your Claude Code session logs, it drafts reviewable time entries plus a printable HTML audit packet with: SHA-256 chain of evidence (source files + matter.yml + active disclosure pack + verifiable artifact self-hash), attorney identity and signature block, a bar-opinion disclosure pack with starter language for five jurisdictions, and content-aware deterministic narratives derived from filename and tool shape — never from prompt text by default. The tool refuses to bill on its own. --strict mode refuses to ship the artifact if any audit invariant fails (broad routes, missing attorney, missing/unverified disclosure). Comes as a Node CLI and a self-contained browser version (no backend; JSONL never leaves the page). 15 invariant tests verify the contract. AGPL-3.0.
Reviews outside counsel invoices and related billing data for an in-house legal department, including LEDES or e-billing exports, OCGs, approved rates, discounts, budgets, AFAs, and staffing rules. Starts with internal comparisons before bringing in external data. Produces invoice review findings, MBR/QBR scorecards, dispute logs, and management reports. For demonstration purposes only and not professional advice.
Build, test, and ship voice agents with LiveKit. Skills for the LiveKit Agents SDK (Python and Node.js) covering voice AI architecture, live debugging, turn-level tests, simulations, and deployment, plus the LiveKit Docs MCP server for current docs, SDK code search, and changelogs.
Authentication flow testing: OAuth 2.0 with PKCE, multi-factor authentication, and session management, plus Keycloak, Auth0 and Okta integration tests. Anchored on RFC 7636, RFC 9700 and OWASP ASVS V3. A critic agent (token-storage-security-critic) flags tokens in localStorage, auth cookies missing httpOnly / Secure / SameSite, and tokens leaking into logs or URLs.
integrations-protocolsExpert HIPAA compliance assistant for healthcare and software contexts. Use this skill whenever the user mentions HIPAA, PHI (Protected Health Information), ePHI, covered entities, business associates, healthcare data privacy, medical records, health information security, BAA (Business Associate Agreements), or any compliance review involving patient data. Also trigger for requests to draft privacy notices, HIPAA policies, consent forms, security risk assessments, or breach notification letters. Use for developers building healthcare software who need technical safeguard guidance (encryption, access controls, audit logs), compliance officers reviewing documents or procedures.
Product requirements and prioritization, market and customer research, business model and pricing, and technical writing (READMEs, API docs, tutorials, runbooks, changelogs).
Observability suite — metrics: Prometheus, Grafana Mimir, and Grafana reference for agents querying metrics, writing PromQL, building and fixing dashboards, and reasoning about SLOs, KPIs, and burn-rate alerting, plus the community, air-gapped mimir-distributed Helm upgrade methodology (chart↔app co-pinned ladder, the classic-vs-ingest-storage/Kafka decision, the nginx→gateway rename that silently moves the proxy's DNS name, rollout-operator sequencing and abort levers, per-hop verification, and air-gap image/CRD/egress staging); and logs: the kube-logging logging-operator (16-CRD Fluent Bit→fluentd/syslog-ng pipeline, JSON/CRI parsing, routing, buffers, upgrade floor 6.7.0) plus rancher-logging-exit — the air-gap-first migration off Rancher's frozen bundled rancher-logging chart (CVE-2026-54680, release-secret cutover, CR compatibility); and hardware metrics: snmp-exporter — Prometheus snmp_exporter v0.30.x best practices (generator.yml module curation, the never-walk-a-whole-enterpri
observabilityProject progress ledger written automatically. A Stop hook logs the working-tree delta each turn that touched files (ship, rfc, or plain conversation), so what moved is recorded without remembering to log; next reads it.
memory
