MCP servers and skills: search, filter by where they run, and compare.
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This wor
OfficialSkillApache-2.0★ 1.1k in collectionNo key
Captures conversations and supplied notes as Notion wiki pages, how-to guides, FAQs, decision records, or retrospectives. Use when saving or updating durable knowledge from existing context; use resea
in the skill textand outcome.** Use the conversation or supplied notes. Separate agreed decisions from proposals; do not invent owners, dates, consensus, or missing steps. Ask only for missing
OfficialSkillMIT★ 218 in collectionNo key
Local-first game design OS for AI agents: turn sessions into evidence, experiments, reviewable decisions, and durable project memory—Human Gates and rollback.
in the skill textidea, gameplay sample, research trail, or workflow problem; get reviewable evidence, experiments, proposals, decisions, and project memory—without handing commitment-changing judgment to the agent. 简体中文
SkillMIT★ 417No key
the agent experience layer · observability + memory for AI coding agents (Claude Code + Codex) · local-first, typed, yours
in the skill textstructured retro (*tried · worked · failed · next*) and turns repeated friction into proposals you review. Accepted proposals become experiments with verdicts after 3, 10, and 30 sessions
SkillAGPL-3.0★ 116No key
Andrej Karpathy's LLM Wiki pattern as a skill & Claude Code plugin — turn accumulated sources into a self-maintaining, scalable markdown knowledge base.
in the skill textevidence into tested procedures.** `/wiki:evolve` runs training, evidence consolidation, whole-skill proposals, validation, and independent final testing, retaining rejected attempts. Adapters for nine supported agent
SkillMIT★ 119No key
Portable, evolving context and workflow layer that works across Claude Code, Codex, Hermes Agent, OpenClaw, Cursor, Devin and other compatible coding agents. All backed by Git.
in the skill textkernel that turns reviewed setup, checkpoint, and close requests into hash-checked proposals and receipts. Host-native memory stays separate. | What you need | How Context
SkillMIT★ 29No key
Local-first, evidence-led security knowledge base with a model-neutral JSON CLI, immutable sources, and human-reviewed proposals.
SkillMIT★ 10No key
AI proposal generator creating hyper-personalized sales proposals predicting win rate lift (G2 AI Proposal Generators)
SkillLink only★ 8
Who stands behind it
Who stands behind it
