semctx
claudeTrace repository impact, authored intent and fail-closed migration plans in Claude Code.
4 skills · 1 MCP server · hooks
Claude Code and Codex plugins their authors filed under "development". All categories.
Trace repository impact, authored intent and fail-closed migration plans in Claude Code.
4 skills · 1 MCP server · hooks
Six skills: fullstack-architect, nextjs-frontend, python-fastapi, postgresql, expo-react-native, swift-ios.
6 skills
Agent Skills that design minimalist app and OSS package icons from a text brief or project context - symmetric logos on dark grey, Apple-style rounded-rectangle backgrounds.
6 skills
A Claude Code hook that ends your session at a token/$ ceiling and flags fake "done" against the git diff — model-free, and it can't loop doing it.
1 skill · 2 commands · 1 agent · hooks
Senior-engineer skills for shipping: prodcheck reviews changes for security, tenant data isolation, N+1 and DB problems before they reach production; prodtest writes unit, integration and Playwright E2E tests for a new feature with screenshots; mergemain merges main into the current branch and resolves conflicts with full context; shipit writes clean commits and PRs, with or without AI attribution; adonis-next-monorepo scaffolds a verified AdonisJS + Next.js monorepo with enforced conventions.
5 skills
Manage marketplace plugins, validate manifests, and regenerate registry indices.
1 skill · 4 commands
A Claude Code hook that ends your session at a token/$ ceiling and flags fake "done" against the git diff — model-free, and it can't loop doing it.
1 skill · 2 commands · 1 agent · hooks
DWG/DXF to GeoPackage, QGIS delivery and source-preserving CAD tools for AI agents.
2 skills · 1 agent · 1 MCP server
STM32 hardware debugging for AI agents: the stm32-gdb-mcp server plus the stm32-debug and stm32-instrument skills, with a SessionStart hook that locks the golden rules in at conversation start.
2 skills · 1 MCP server · hooks
Run, test and debug Android apps from Claude Code with a live, interactive emulator/device viewer in the Claude Desktop browser pane, Apply Changes, annotations and a status line.
2 skills · 1 MCP server · hooks
Delegate tasks from Claude to any OpenCode model while Claude stays the orchestrator.
1 skill · 1 command · 1 agent · 1 MCP server
Run, test and debug Android apps from Claude Code with a live, interactive emulator/device viewer in the Claude Desktop browser pane, Apply Changes, annotations and a status line.
2 skills · 1 MCP server · hooks
Use MCP servers through the mcporter CLI and saved scripts instead of native MCP tools: a setup agent that moves your servers into mcporter, a session hint, and a hook that points native MCP calls at mcporter.
2 skills · 1 agent · hooks
Telegram development, split by the API each surface actually speaks. telegram-bots covers the official HTTP Bot API — update_id as the only idempotency key, the allowed_updates default that drops three types in silence, the webhook secret header, rate limits as a design constraint, and Telegram Stars with its ten-second pre-checkout window. telegram-userbots covers MTProto and Telethon — the session file as a credential equal to the password, FloodWaitError as the API working rather than failing, and the account-ban risk a bot token does not carry. telegram-miniapps covers initData verification, the algorithm shipped as a runnable fixture, and the SDK package whose name moved.
3 skills
Frontend skill pack for React 19 + Next.js 15 (App Router): code architecture/placement, React best practices, and Next.js patterns.
3 skills
Blaxel agent skills bundle: SDK skill for creating cloud sandboxes (microVMs) to run code, start dev servers and generate live preview URLs, CLI skill for managing Blaxel resources (agents, sandboxes, jobs, MCP servers) from the command line, and the hosted Blaxel MCP server for managing workspace resources.
2 skills · 1 MCP server
Idiomatic Rust development guidance: a Rust best-practices skill, a facet-ecosystem skill, an auto-formatting hook, and an advisory edit-time tenet guard (stringly-typed dispatch, identifier-shaped String fields, Display-logged errors, lint hygiene)
2 skills · hooks
mise toolchain manager guidance with task runner, monorepo patterns, project onboarding, and SessionStart hook for toolchain detection
2 skills · hooks
Typst authoring guidance plus a markdown-to-pdf workflow: convert Markdown to branded PDF or HTML through a pure Typst pipeline with pluggable, per-document theming
2 skills · 1 command
Skills for building gRPC servers in Julia with gRPCServer.jl's codegen interface, and for developing the package itself.
3 skills
Turning Kiva designs into compliant code: the Kiva Tailwind preset, plus audits/migrations that bring consuming repos into design-system alignment.
3 skills
Systematic workflow for processing CodeRabbit code review feedback with MCP-powered analysis and fixes
1 skill · 2 MCP servers
The self-improving framework for Claude routines: conventions, a linter, templates, approval gates and a mobile Desk.
2 skills · 1 MCP server
Strict Python formatter hook, plus a subagent that absorbs the lint-fix loop
1 agent · hooks
Collaborative specification building with iterative Q&A before implementation
2 commands
Audit and rewrite error messages to be helpful and actionable
1 skill · 1 agent
Execution agents usable with or without a spec-driven workflow: `implementer` and `test-writer`.
2 agents
Chrome, Brave, Edge, Chromium, and Vivaldi automation through CDP with full CLI/MCP capability parity, diagnostics, memory analysis, extensions, and WebMCP.
1 skill · 1 command
Lean 4 language server with automatic Lake project-root detection (works even when the session root is above the project), elan toolchain resolution, and multi-project routing. Bundles the lean-goal CLI for proof-goal state, sorry inventory, and fast diagnostics — plus a skill teaching the interactive proving workflow.
1 skill · LSP
Autonomous experiment loop — iteratively optimize any metric with git-tracked experiments
1 skill · 1 command