Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 388,308 indexed, measured the same four ways as everything else here.
Development Driven Spec - reverse-engineer an Arc42-informed specification from legacy code through bottom-up excavation with LLM-as-Judge fidelity verification. Inverts the spec-driven-development direction: code -> spec.
Claude Code plugin for Kotlin development with kotlin-language-server integration, 12 automated hooks for Gradle builds, linting (detekt, ktlint), formatting, and testing.
★not rated 2 2d agoA
tokens not measured
originalMIT
Provides the /llm-wiki-init:wiki-init and /llm-wiki-init:wiki-status commands for scaffolding and inspecting a persistent, LLM-maintained knowledge base on any topic.
★not rated 2
changed 21d agoA
tokens not measured
originalMIT
Drives a GitHub milestone to completion: triages each issue for design gaps + dependency order up front, then for each buildable issue finds the root cause (or parks it), dispatches a TDD implementer subagent, runs unit + E2E tests + code review, opens a PR, and auto-merges issues on CI green. The whole loop sits…
★not rated 2
changed 6d agoA
tokens not measured
originalMIT
Teach the user a topic through a genuine Socratic dialogue, then distill the shared understanding into a copyable markdown takeaway they keep — no file access needed, works in any chat surface including claude.ai. Domain-open — cooking, law, music theory, statistics, infrastructure, anything — the fit comes from…
A structured critique of proposals to create an AI imitation of a colleague from their chat messages. It explains why chat history may not capture a person’s knowledge, decisions, or changing behavior.
Ships a feature only when a test that actually ran proves every requirement in its spec. Free-text requirement -> spec (you sign it off) -> plan -> review -> implement per milestone, gated by a lint/test/spec-trace loop that runs outside the model. For Node projects; your repo declares its test and lint commands in…
★not rated 2
changed 24d agoA
tokens not measured
originalMIT
One-time setup — scan the Flutter project for existing design patterns, ask UX questions, and write a .klamben.md design context file that all other commands reference.
Read, search, and download email over IMAP from the command line using the myl CLI client. Use this skill whenever the user wants to interact with their mailbox from a terminal — checking the inbox, listing or searching messages, reading a specific email, opening HTML or raw source, or saving attachments. Trigger on…
When the user wants to write or plan the everyday emails a summer camp sends families — enrollment and nurture emails, re-enrollment and retention, the season newsletter and in-season parent updates, lifecycle reminders (deposits, balances, forms, packing), and the email calendar across the camp year. Use for camp…
Production conventions for TanStack Query (React Query): a five-file feature folder (types/requests/keys/queries/mutations), queryOptions() key factories with a single all() root per feature for hierarchical invalidation, QueryConfig/MutationConfig type helpers, optimistic updates with rollback, and useInfiniteQuery…
Comprehensive guide for building integrations with Israel's Pikud HaOref (Home Front Command) alert system — rocket alerts, earthquake warnings, and civil defense notifications.
★not rated 2 8mo agoA
tokens not measured
originalMIT
The anti-sycophant reviewer. Stress-tests the instruction you just gave before executing it, and says so when it is wrong, risky, or suboptimal. Flags in one line, then does the work anyway. Stops only for what cannot be undone.
★not rated 2 2mo agoA
tokens not measured
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: