14 plugins from public Claude Code marketplaces. Each one bundles skills, slash commands, agents, hooks or MCP servers that install together.
Showing 14 plugins that match these filters.
coalmineTheColliery/CoalMine1
atklamngockhuong/aiteamkit1Submit the repo with .claude-plugin/marketplace.json and we list every plugin.
Submit marketplaceA 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 each session start; L3 stable persona is always loaded. L1 to L2 needs three distinct sessions spanning two distinct calendar days (a stated claim needs two; a verified claim is the only single-observation path); L2 to L3 needs two projects and thirty days. Two gates refuse rather than guess: a claim altered by the redaction pass never promotes on evidence alone, and a contradicted claim freezes until a human resolves it. Three hooks run the loop unattended and every one fails open. Nothing reaches a committed CLAUDE.md without an explicit human adopt. Ships 5 stdlib scripts, 3 hooks, a cs-memory-curator agent, /cs-memory, a JSON schema, and a 69-check validator. Concept from TencentCloud/TencentDB-Agent-Memory (MIT); no upstream code
Database architecture, schema design, and SQL optimization for production systems
Turn 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.
Schema validation, data quality monitoring, streaming validation pipelines, and input validation for backend APIs
Firestore database specialist for schema design, queries, and real-time sync
Generate ORM models from database schemas or create database schemas from models for TypeORM, Prisma, Sequelize, SQLAlchemy, and more
Generate realistic test data including users, products, orders, and custom schemas for comprehensive testing
9 quality-canary skills: rot-canary (code-health), gold-standard (world-class completeness), source-grounding (anti-hallucination), supply-chain-audit (deps/build/artifact), resilience-audit (failure-mode FMEA), telemetry-canary (observability), testability-canary (decoupling/DI), scale-canary (perf scaling), drift-canary (contract/schema drift). rot-canary adds cross-platform auto-cadence hooks. Served conformed from the committed plugin/ dist (built by scripts/build-plugin.mjs).
AI Team Kit - 25 skills covering the software delivery lifecycle of a company project team: choosing the next skill from the project's state, carrying several pieces of work through the lifecycle at once, project profile setup, per-team skill overrides, requirement intake, catching up on work in flight, estimation, technical design, reference specs for API, schema and feature, task breakdown, conventions, implementation planning, implementation, bug fixing, runtime verification, code review, QA, test case execution on a deployed environment, security review, version control, release, incident response, retrospective, onboarding, and handover
Data quality testing for analytical pipelines: dbt tests, Great Expectations, Soda checks, data contracts, and a go / no-go release gate. Extracts data contracts from data-product specs and covers tool choice and severity conventions. Agents (schema-diff-reviewer, data-anomaly-triager) review schema diffs for breaking changes and classify failed checks by anomaly type and likely owner.
quality-engineeringAPI testing with Postman and Newman, REST Assured and Karate, plus Schemathesis and RESTler fuzzing and API tests run under injected network chaos. An authoring agent (api-test-author) picks the tool from observable project facts and writes one functional test per endpoint and scenario.
functional-testinggRPC testing: buf lint and breaking-change gates, ghz load tests, grpcurl, mock servers, and streaming RPC test suites. Includes the protobuf versioning catalog, interceptor test patterns, and a status-code catalog. A review agent (grpc-service-reviewer) flags missing status-code assertions and deadline handling. Distinct from qa-contract-testing/protobuf-compat-checking (schema-level breaking detection).
integrations-protocolsDatabase migration testing for Flyway, Liquibase and Atlas: classify every schema change by risk and review blast radius and locking before it ships. Sorts DDL and DML into an eight-category operation taxonomy. A review agent (migration-blast-radius-reviewer) covers blast radius plus DDL performance: CONCURRENTLY index builds, ACCESS EXCLUSIVE rewrites, post-migration ANALYZE, and lock-time estimates.
backend-distributedCoverage-guided fuzzing with libFuzzer, AFL++, cargo-fuzz, Go native fuzzing, Atheris and Jazzer, plus sanitizer crash triage. Covers fuzzer choice, corpus management, sanitizer integration, and ASan / UBSan / MSan crash classification with bulk triage. A builder agent (fuzz-target-author) scaffolds a fuzz harness from a function signature. Binary and system-level fuzzing, distinct from qa-property-based and qa-api-testing/schemathesis-fuzzing.
security-compliance
