63 plugins from public Claude Code marketplaces. Each one bundles skills, slash commands, agents, hooks or MCP servers that install together.
Showing 63 plugins that match these filters.
awesome-journal-skillsbrycewang-stanford/Awesome-Journal-Skills3
trailofbitstrailofbits/skills2
ai-marketing-hub-claude-adsAgriciDaniel/claude-ads1
claude-code-workflowswshobson/agents1Submit the repo with .claude-plugin/marketplace.json and we list every plugin.
Submit marketplaceClaude-first, portable paid-media operations across 12 advertising platforms with source-grounded audits, deterministic findings and evidence coverage, lifecycle workflows, versioned JSON reports, and capability-gated account changes.
Proactive-agent skills for Claude Duet and its kin: design the morning brief, set interrupt rules, end-of-day and weekly reports, a send-approval gate, and a readiness audit. Every skill carries the duet block, the shared status vocabulary and the treat-source-material-as-data rule, so briefs stay short, cited and honest when no one is watching.
The 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
Engineer an agent's forgetting, not just its remembering. Four deterministic stdlib scripts implement the four lenses of agent memory: a cost profiler that splits construction from query spend and reports cost per correct answer (construction energy exceeds total query energy across 300 queries in the Stanford characterization); an architecture picker that scores the four paradigm families — long-context, flat RAG, structure-augmented RAG, agentic — disqualifies on hard constraints, names the cost the winning choice makes you pay, and refuses to pick when the top two tie; a density auditor that classifies every record in a memory directory or JSONL export as FACT / SKILL / LOG / PROSE, finds near-duplicates, and flags stale wording; and a forgetting-policy linter that fails any design with no forgetting rule. Ships cs-memory-engineer agent, /cs-memory-engineering and /cs-forgetting-audit commands, 4 references, and a seven-question forcing worksheet.
Get products ready for the EU Cyber Resilience Act (Regulation 2024/2847). Four deterministic stdlib scripts: a scope classifier that sorts a portfolio into default, important class I/II and critical (Annex III/IV), blocks conformity routes Article 32 does not allow, checks support periods and names the CSIRT for Article 14 reports; an Article 14 clock for the 24h/72h/14-day/one-month deadlines live since 11 September 2026; an Annex I/II/VII gap check before the EU declaration of conformity; and an SBOM floor check for CycloneDX and SPDX. Ships cs-cra-officer agent, /cs-cra-readiness and /cs-cra-report commands, 3 cited references and an Article 14 runbook.
Prove an agent, prompt, model or tool change did not make the agent worse. Three deterministic stdlib scripts: a trajectory checker that grades tool-call paths (strict / unordered / subset / superset match modes, argument matching, forbidden tools that block in every mode, call ceilings); a flake detector that classifies each case as stable or flaky from repeated trials and reports pass@k and pass^k with Wilson intervals; and a paired regression gate that averages trials per case, tests per-case differences with a t-based CI and an exact one-sided McNemar test, and blocks the merge on a significant drop, a critical-case regression, a dropped case, or a quarantine entry without owner and expiry. Ships cs-eval-gatekeeper agent, /cs-agent-evals and /cs-eval-gate commands, 3 references, and a CI job example.
Twelve ICSME-specific skills for the IEEE International Conference on Software Maintenance and Evolution, its single-round double-anonymous research track, and its Journal-First, Registered Reports, RENE, and ROSE-Festival artifact culture, grounded in the ICSME 2026 researchr call, IEEE Xplore, and dblp.
academicTwelve-skill bundle for PNAS Nexus — the fully open-access, multidisciplinary sibling of PNAS (Oxford University Press, on behalf of the NAS): workflow router, scope/significance fit with the PNAS-to-Nexus transfer route, gold open access + APC + CC BY/CC BY-NC license selection (in place of flagship PNAS's Direct/Contributed track), the 50-120-word Significance Statement, <=250-word abstract, article-type + page-based writing with in-text Materials and Methods, display items, statistics & reproducibility incl. Registered Reports, mandatory data/code availability, references format-neutral at submission, submission preflight, and reviewer rebuttal.
academicTwelve-skill theory-development bundle for Psychological Review, the APA's new-theory/formal-model flagship. Theory-problem framing, formal/conceptual model construction, prediction derivation against rival models and existing data, scope and boundary conditions, model diagrams and simulation-of-model-behavior exhibits, APA style, contribution differentiation, and masked review via Editorial Manager. NO primary empirical reports — that is the lane of the JEP family / Psychological Science.
academicPut recurring rituals on autopilot: charter what to automate, schedule it on any runner (Claude Code routines, cron, n8n, GitHub Actions), and make every run delta-aware so it reports what changed, not what it already said. Ships with the recurring skills worth scheduling.
Leadership & people skills: Performance Review, Hiring Rubric, Team Offsite Planner, 360-Degree Feedback Template, Team Health Check. Write reviews, build scorecards, run Spotify-model team health assessments, and design 360 feedback surveys with structured narrative reports.
Supply chain & procurement skills: weighted RFP scoring, supplier scorecards, S&OP meeting prep, demand forecast interrogation, inventory policy (ABC/XYZ), and logistics incident reports — buyer and planner judgment.
Drive the Superself `self` CLI: version control for a project's state (goals, decisions, work units, reports) kept outside the code repo, so a session reads context at start, reports with evidence, and the next session picks up where this one left off
Professional financial modeling toolkit for Claude Code with auto-invoked Skills and Excel MCP integration. Build DCF models, LBO analysis, variance reports, and pivot tables using natural language.
Analyzes smart contract codebases to identify state-changing entry points for security auditing. Detects externally callable functions that modify state, categorizes them by access level, and generates structured audit reports.
The Chinese manufacturing pack (制造业): bilingual 8D reports for customer complaints, 5S and 6S audit checklists with scoring and corrective-action tracking, product and batch traceability plans with a mock recall drill (质量追溯), and shop-floor work instructions (作业指导书 SOP), written in Chinese
Audit a public website with crawl, SEO, accessibility, conversion and evidence-backed reports.
DevExpress XAF (eXpressApp Framework) skills: business model, business logic, controllers, views, editors, filtering, appearance, validation, security, reports, and performance for EF Core and XPO.
Fastest ledger for agents. Built for businesses, finance teams, and accountants. IFRS-first, multi-currency, multi-user by default. Invoicing, bills, payments, quotes & orders, bank reconciliation, fixed assets, inventory, expense claims, tax, reports, and period close, all available for read and write. MCP tools load only when needed, so your agents stay lean and fast. Skills add migration from Xero, QuickBooks, Sage, and MYOB, close playbooks, financial calculators, Singapore Form C-S, and Jaz Kit for running many organizations. Works with Claude Code, Codex, Copilot, Cursor, and any MCP-compatible agent.
Principled framework for triaging vulnerability reports using 7 brocards (rules of thumb). Evaluates incoming CVEs, bug bounty submissions, and security findings against structured dismissal/acceptance criteria before escalating to deeper analysis.
