lib
claudecodexCLI wrapper skills: Slack, Jira, GitHub, TestRail, vault operations, log analysis, and file utilities
18 skills · hooks
Knowledge-work verbs as standalone compositional primitives: frame, gather, understand, synthesize, interrogate, experiment, teach. NotebookLM + Workflow fan-out; preflight-first input contracts; no orchestrator
Plugin research-lab from marketplace local in cosmicdreams/claude-plugins. Commands read from the repo's manifest — today.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
consultTrigger this if the user says "research this end to end", "full research pipeline", or "ask the librarian". Not for only sharpening a question (research-lab:frame).
experimentTrigger this if the user says "hill climb", "climb this", or "run an experiment". Not for scoring a single claim (research-lab:interrogate).
frameTrigger this if the user says "frame this", "sharpen this question", or "scope this research". Not for collecting sources (research-lab:gather).
gatherTrigger this if the user says "gather sources", "build a notebook", or "literature review". Not for digesting material already gathered (research-lab:understand).
interrogateTrigger this if the user says "interrogate this", "tear this apart", or "peer review". Not for an unformed idea (ideate:reality-check).
synthesizeTrigger this if the user says "synthesize this", "form a position", or "decision table". Not for an audience that was not there (research-lab:teach).
teachTrigger this if the user says "teach this", "make a briefing", or "audio overview". Not for insiders who share the context (research-lab:synthesize).
understandTrigger this if the user says "help me understand", "walk me through", or "digest this". Not for challenging a claim (research-lab:interrogate).
experimentalistExecutes the iterative experiment loop — proposes changes, runs cheap gates, implements via git commits, measures results, and decides keep/discard using the ratchet pattern. Includes correctness validation.
librarianRuns one research job, or one part of a split job, by following research-lab:consult. Start it as its own session with the args engagement=<record folder> part=<part>, or with a new goal. It is the user's single point of contact for that job and stops only at the user's gates.
researcherGathers and curates knowledge from NotebookLM notebooks following research-lab:gather, answers focused facet queries against a curated notebook, and answers one question from one corpus (notebook, vault folder, local files or past agent threads) for research-lab:consult. Spawnable N times for parall
python3 "${CLAUDE_PLUGIN_ROOT}/hooks/keepgoing.py" stop
python3 "${CLAUDE_PLUGIN_ROOT}/hooks/keepgoing.py" start
CLI wrapper skills: Slack, Jira, GitHub, TestRail, vault operations, log analysis, and file utilities
18 skills · hooks
Build and maintain a verified Figma component library from real code. Resumable, schema-validated extraction and planning; Figma is one renderer.
14 skills · 2 commands · hooks
Drupal-specific development skills and agents (DDEV, Analysis, Validation, Scaffolding)
13 skills · 1 agent · hooks
Passive knowledge capture pipeline — Karpathy-derived LLM Wiki with Monitor-driven multi-domain ingest. Feeds land in raw/, agents compile them into a cross-linked Obsidian wiki, memory evolves via confidence decay and graph-aware consolidation.
12 skills · 2 agents
Process automation skills: prioritize, scout, knowledge-check, deploy checklist, Obsidian maintenance, and personal productivity
12 skills
Plugin, agent, and skill management tooling: bump-version, scaffold, new-agent, optimize-agents, update-plugins, create-worktree
9 skills · hooks
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.
5 commands
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.