Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 375,722 indexed, measured the same four ways as everything else here.
Distill Herd commander memory, clean stale MEMORY.md entries, promote durable commander lessons into LONGTERMMEM.md, and propose shared-knowledge updates through a review gate. Use for periodic commander memory cleanup.
Find Korean job postings for a target role with minimal user input — pass a short --seed keyword like "Problem Solver" or "Forward Deployed Engineer" and the skill expands it to the full family of equivalent titles used at different companies (FDE / Applied AI Engineer / Generalist / Solutions Engineer / etc.)…
Profile a ClickHouse cluster via MCP and emit a per-cluster "analyst" Skill the user can save in claude.ai. Activate when the user asks to "profile this ClickHouse", "generate an analyst skill", "build a schema guide", "map the data in this cluster", or regenerate an existing cluster-analyst Skill after schema…
Investigate every bug as if it were intentional. Ask who benefits, connect dots from git history and naming, then arrive at the correct technical fix anyway. Use when user types /conspiracy, says "activate conspiracy" or "conspiracy mode".
Check Claude Code changelog for lintable changes and implement cclint updates. Use when a new Claude Code version ships, when CLAUDE.md claudecodelastupdated is stale, or for version gap detection, domain classification, and parallel agent dispatch across CUE schemas, hook events, known tools, and lint rules.
Keep Claude Code's 5-minute prompt cache warm across idle pauses by injecting cheap keepalive turns from a Stop hook. Saves real money on API-billed sessions with normal thinking gaps.
★not rated 17 5mo agoA
tokens not measured
originalMIT
Self-improving skills toolkit that watches real agent sessions, detects missed triggers, grades execution quality, and improves skill packages through evals, replay, baselines, review, and post-deploy watch. Use when verifying or publishing a skill, improving instructions or routing, checking skill health, grading…
Use when the user wants to buy CDs from their Discogs wantlist — the cheapest listing for each album, whether any eBay seller has several worth bundling, whether eBay or the Discogs marketplace is cheaper, or what a NAMED Discogs seller has from the wantlist. Triggers e.g. "what do my wantlist CDs cost", "cheapest…
Agentic DFIR orchestrator that autonomously investigates security incidents by chaining forensic skills (IOC extraction, Windows artifact triage, timeline correlation, YARA generation) with an autonomous reasoning loop, persistent case state, and human-in-the-loop approvals. Use this skill whenever the user mentions…
Manage Raindrop.io bookmarks with AI assistance. Save and organize bookmarks, search your collection, manage reading lists, and organize research materials. Use when working with bookmarks, web research, reading lists, or when user mentions Raindrop.io.
A reference for answering questions in the style and from the documented viewpoints of a person called Shannon. It covers topics such as coworkers, product management, internal communities, and people-finding tools.
Use when the user wants to protect their workspace from credential theft, prompt injection, or data exfiltration — even if they don't mention "canaries" or "honeytokens" directly. Covers deploying Tracebit security canaries (fake decoy credentials that alert on use), detecting when they're triggered via the user's…
Use when classifying or explaining authorized Active Directory attack techniques—Kerberos and NTLM paths, coercion awareness, delegation and RBCD, ACL and DCSync concepts, LAPS and shadow credentials, GPP, trust paths, AD-joined SQL pivots, and lateral movement by protocol. Use as a reference when writing findings or…
MCP server and CLI that gives Claude full access to Proton Drive — upload, download, share, and manage your end-to-end encrypted files without leaving the conversation. Runs locally from the proton-drive-mcp npm package.
★not rated 17 6mo agoA
tokens not measured
originalMIT
MCP server for Moodle — give Claude access to your courses, files, grades, and more. Build Obsidian study vaults from lecture notes in one command. Runs locally from the moodle-mcp npm package.
★not rated 17 5mo agoA
tokens not measured
originalMIT
A specialist agent team plus an enforced, proportional workflow: role agents that self-route to deep references, cross-cutting process skills for the gate contract, work-item lifecycle, proving a change landed, review tiering, model selection, research method, grounded-answer audit and pull-request completion, and…
★not rated 17 1mo agoA
tokens not measured
originalMIT
A legal intelligence toolkit for parents navigating family court — build evidence vaults, analyse documents forensically, track lawyer accountability, and develop case strategy.
★not rated 17 24d agoA
tokens not measured
originalMIT
Orchestrate full delivery of a beads epic through polecats, refinery, and integration branches. The final stage of the design-to-delivery pipeline: gt-toolkit formulas produce the spec and plan, design-to-beads converts the plan into beads issues, and this skill delivers those issues through Gas Town infrastructure.
★not rated 17 6mo agoA
tokens not measured
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: