81 tagged apache 2 0, measured the same way as everything else here.
Browse within: agent-os 21business-intelligence 19python 16access-to-justice 15claude-for-legal 15legal-aid 15legal-tech 15china-law 10chinese-law 10lawyers 10server-os 9fail-closed 7Multi-Agent 6openmesha 5
Skill Claude CodeCodex
Configure and use MNEMOS for persistent cross-session memory with Hermes — shared memory pool across profiles, full-text and semantic search, compression with quality manifests, knowledge-graph triples, and session transcript ingestion. Use when setting up MNEMOS, troubleshooting memory retrieval, storing…
Skill Claude CodeCodex
Read and write persistent memory via MNEMOS. Use when you need to recall prior decisions, infrastructure facts, project context, or established patterns across sessions, and when you have learned something new worth persisting (solved problem, validated pattern, architectural decision, team standard). Covers full-text…
Skill Claude CodeCodex
Structured intake on a matter that has cleared eligibility screening. Pulls upstream conversation context if LIA-MCP or VIA-MCP is connected, routes to practice-area template, spots cross-area issues, runs full conflict check, propagates funder-source matrix and funding-restriction flags from screening, classifies…
Skill Claude CodeCodex
Managing attorney's one-time office setup — practice areas, funding sources and eligibility guidelines, jurisdiction, supervision style (formal review queue / configurable flags / lighter-touch), conflict-check process, and seed documents (handbook, filing guides, eligibility tables, intake forms). Writes CLAUDE.md so…
Skill Claude CodeCodex
Funder reporting data extraction. Reads the office's funder reporting cadence and format from CLAUDE.md, queries the case-management system (or instructs on manual extraction), and produces a data package matching each funder's expected format — LSC CSR semi-annual, IOLTA narrative, VAWA quarterly, HUD reports…
Skill Claude CodeCodex
Connect to the HQ via Supabase. Use when you need to register yourself, search knowledge, create/update pages and skills, claim tasks, post comments, manage contacts and organizations, log interactions, or query the audit trail. Also use at session startup to register and load boot knowledge.
Skill Claude CodeCodex
Rewrite text so it stops sounding AI-generated and starts sounding like a person wrote it. Use when editing outreach, copy, notes, docs, templates, or messages that feel too polished, too structured, too generic, too symmetrical, too bot-like, or otherwise "AI." Triggers on requests like "humanize this," "make this…
Skill Claude CodeCodex
Use SaferSkills to find, evaluate, and safely install AI agent capabilities (skills, MCP servers, hooks, plugins, rules) and to assess a whole agent. Run this before you install, add, recommend, or trust any capability — or when asked whether one is safe or what its score is: scan and score it first with npx…
Skill Claude CodeCodex
Navigate Lawyeah open Agent Skills for Chinese mainland legal practice. Use when the user needs PRC lawyer workflows, case intake, litigation or contract review/draft packs, or asks for 律页法律技能. Routes to one Chinese pack under 领域/ or 合同/; does not itself produce legal opinions, filings, or signed contracts.
Skill Claude CodeCodex
Chinese-language review of an unsigned private-equity shareholder agreement. It focuses on investor rights, share-sale protections, drag-along and tag-along terms, and exit conditions.
Skill Claude CodeCodex
A Chinese-language review workflow for unsigned build-transfer-buyback contracts. In this arrangement, an investor finances and builds a project, hands it over after completion, and the buyer repays the investment in instalments.
kai-wedekind/claude-code-grok-bridge
Skill Claude CodeCodex
Internal helper contract for calling the grok-bridge runtime from Claude Code.
kai-wedekind/claude-code-grok-bridge
Skill Claude CodeCodex
When to reach for Grok Build rather than doing the work in Claude Code — the routing tiers (manual, second-opinion, reach, offload-first, delegate-write), what each one covers, what it costs, and how to call it. Load this before offloading work, before asking for a second opinion, and before delegating anything to…
kai-wedekind/claude-code-grok-bridge
Skill Claude CodeCodex
Internal guidance for presenting Grok Build bridge output back to the user.
Kokai-Data/japan-business-data
Skill Claude CodeCodex
Get recent EDINET disclosures for one Japanese company (by 法人番号 OR edinetCode) clustered into Kokai signal overlays — annual / quarterly / extraordinary / TOB / large-shareholding / governance / event. Auto-resolves 法人番号 → EDINET code. Use for M&A target diligence, investment research, listed-company DD prep. 日本語…
Kokai-Data/japan-business-data
Skill Claude CodeCodex
A search tool for Japanese financial disclosure documents filed through EDINET, Japan’s government system for company filings. It covers reports such as annual, quarterly, ownership, takeover, and internal-control disclosures.
Kokai-Data/japan-business-data
Skill Claude CodeCodex
Search Japanese government procurement notices (Call for Tender, 公告) from the 官公需情報ポータル (中小企業庁) REST + XML API. Phase 1 = CFT discovery only (project name, issuing organization, category, procedure type). Phase 2 (future) = awarded results, supplier history, price signals are NOT included. Use for sales lead…
Skill Claude CodeCodex
Autonomous agentic MCP server for grants discovery, ranking, drafting, and public-goods funding. Searches Grants.gov and NSF, lists sponsorships and open-source funds, manages project profiles, and drafts grounded proposal outlines. Optimized for open-source AI and public goods. Use when the user needs funding…
Skill Claude CodeCodex
OpenGOS multi-agent pipeline — discover → rank → draft under provenance.
Skill Claude CodeCodex
Name: needrail Description: Get what you NEED to succeed & do agentic public good. Discover, fund, claim, and complete Needs via MCP + x402.
Skill Claude CodeCodex
NeedRail multi-agent coordination — expressor → matcher → fulfiller under x402.
Skill Claude CodeCodex
SuperAgenticMCP — the switchboard for your agent swarm. MCP-native router and multi-agent control plane that plans tasks, routes tool calls to racked MCP servers by capability and latency, streams execution, and files results into a memory-scope graph. Use when the user needs multi-agent orchestration over MCP, a…
Skill Claude CodeCodex
Planner → workers → critic loop for SuperAgenticMCP missions. Use when coordinating multi-step agent work across racked MCP servers.
Skill Claude CodeCodex
Capability-first routing with latency tie-break for racked MCP servers. Use when selecting which server handles a tool call.