Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Tencent SkillHub · AI
Lattice
Initialize and manage Lattice organizations — a file-based operating system for AI agent teams that enables stable, long-running iterative development throug...
skill openclawclawhub Free
Initialize and manage Lattice organizations — a file-based operating system for AI agent teams that enables stable, long-running iterative development throug...
⬇ 0 downloads ★ 0 stars Unverified but indexed
Install for OpenClaw
Quick setup
- Download the package from Yavira.
- Extract the archive and review SKILL.md first.
- Import or place the package into your OpenClaw setup.
Package facts
- Download mode
- Yavira redirect
- Package format
- ZIP package
- Source platform
- Tencent SkillHub
- What's included
- SKILL.md, templates/ORG/ASSET_REGISTRY.md, templates/ORG/DEPARTMENTS/example-dept/CHARTER.md, templates/ORG/DEPARTMENTS/example-dept/HANDOFF.md, templates/ORG/DEPARTMENTS/example-dept/RUNBOOK.md, templates/ORG/DEPARTMENTS/example-dept/STATE.json
Validation
- Use the Yavira download entry.
- Review SKILL.md after the package is downloaded.
- Confirm the extracted package contains the expected setup assets.
Install with your agent
Agent handoff
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
New install
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
Upgrade existing
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
Trust & source
Release facts
- Source
- Tencent SkillHub
- Verification
- Indexed source record
- Version
- 1.2.1
Provenance
- Publisher
- CNF6682
- Source page
- View original listing
- Canonical URL
- Open canonical page
Documentation
Lattice
Lattice is a file-based operating system for AI agent teams. It replaces volatile chat windows with persistent files, enabling agents to work stably through long, iterative development cycles via an 8-phase execution pipeline. Why Lattice? Stable long-running execution — File-driven state machine ensures agents stay on track across sessions. No context window overflow, no drift. Tasks complete reliably over hours or days through structured iteration. Three-tier failure handling — When an agent gets stuck: (1) Model Escalation retries with stronger models, (2) Peer Consult gathers parallel opinions from multiple models, (3) Auto-Triage makes a judgment call (relax constraints / defer / block for human). Most blockers resolve automatically. Per-phase model configuration — Thinking-heavy phases (planning, review, architecture) need strong reasoning models; token-heavy phases (implementation, testing) can use cost-efficient coding models. This dramatically reduces overall token cost without sacrificing quality where it matters. Example model assignment (from a production setup): PhaseModel tierExampleConstitute (architecture)Strong reasoningClaude OpusResearchStrong reasoningGemini ProSpecify (design)Strong reasoningClaude OpusPlan + TasksStrong reasoningClaude OpusImplementCost-efficient codingGPT CodexTestCost-efficient codingGPT CodexReviewStrong reasoningClaude OpusGap AnalysisStrong reasoningGemini Pro The key insight: implementation and testing consume the most tokens (writing/running code), but don't require the most expensive models. Planning and review consume fewer tokens but need deeper reasoning. Match model strength to cognitive demand, not token volume. Multi-project parallel execution — Run multiple projects simultaneously, each with its own cron-scheduled orchestrator. Combined with OpenClaw's cron system, projects advance autonomously on independent cadences. Templates are bundled at templates/ORG/ relative to this skill directory.
Quick Reference
Full design doc: templates/ORG/PROJECTS/pipeline-framework/DESIGN.md Pipeline guide (all agents): templates/ORG/PIPELINE_GUIDE.md Sub-agent guide: templates/ORG/PROJECTS/pipeline-framework/templates/PIPELINE_GUIDE_FOR_SUBAGENTS.md Orchestrator prompt template: templates/ORG/PROJECTS/pipeline-framework/templates/ORCHESTRATOR_PROMPT.template.md Phase prompt templates: templates/ORG/PROJECTS/pipeline-framework/templates/PHASE_PROMPTS/ State machine template: templates/ORG/PROJECTS/pipeline-framework/templates/PIPELINE_STATE.template.json
1. Gather Information
Ask the user for: Organization name (e.g. "Acme Labs") Target directory — where to create the ORG/ folder (default: current workspace root) Departments — list of department names (e.g. Research, Engineering, Reliability) First project (optional) — name + one-line description Keep it conversational. Don't dump all questions at once.
2. Scaffold the ORG Directory
Copy the entire templates/ORG/ directory to <target>/ORG/. Then customize: ORG_README.md — Replace the example org structure in §5 with the user's actual departments TASKBOARD.md — Leave the template structure intact (user fills in priorities later) Departments — For each department the user listed: Copy DEPARTMENTS/example-dept/ → DEPARTMENTS/<dept-name>/ In each copied department, replace <Department Name> placeholders in CHARTER.md, RUNBOOK.md, HANDOFF.md with the actual department name Reset STATE.json to {"lastRun": null, "cursor": null, "notes": "Initial state"} Remove DEPARTMENTS/example-dept/ after creating real departments (unless user wants to keep it as reference)
3. Create the First Project (if requested)
Copy PROJECTS/example-project/ → PROJECTS/<project-name>/ Update STATUS.md with the project name Update DECISIONS.md header Configure PIPELINE_STATE.json (see "Configure Pipeline State" below) Remove PROJECTS/example-project/ after creating the real project
4. Configure Pipeline State
Read templates/ORG/PROJECTS/pipeline-framework/templates/PIPELINE_STATE.template.json as the reference. Ask the user: Which agents will run each phase? (agentId per role — or a single agent for all) Which models for each phase? (or a default model) Escalation chain — list of models from cheapest to strongest (e.g. ["gflash", "gpro", "sonnet"]) Peer consult models — which models to consult in parallel when stuck Synthesizer/triage model — typically the strongest available model Notification channel (optional) — where to send pipeline status updates Fill in the project's PIPELINE_STATE.json with these values, replacing all <placeholder> tokens.
5. Set Up the Orchestrator Cron Job
Read templates/ORG/PROJECTS/pipeline-framework/templates/ORCHESTRATOR_PROMPT.template.md. Create a cron job using the cron tool: Schedule: every 30 minutes (adjustable) Session target: isolated Payload kind: agentTurn Model: the user's chosen orchestrator model Message: the orchestrator prompt template, with all <placeholder> tokens filled in: <project> → project name <org-root> → absolute path to the ORG directory <project-root> → absolute path to the project directory <repo-root> → absolute path to the code repository (ask user) Phase prompt paths → absolute paths to the skill's bundled phase prompt templates Tell the user the cron job ID so they can manage it later.
6. Summary
Print a brief summary: ORG directory location Departments created Project(s) created Cron job ID and schedule Remind them to fill in TASKBOARD.md with initial priorities
Task: Add a New Project (lattice new-project)
Ask for: project name, one-line description, code repo path Copy templates/ORG/PROJECTS/example-project/ → ORG/PROJECTS/<name>/ Customize STATUS.md, DECISIONS.md, PIPELINE_STATE.json (same as step 3-4 above) Optionally create a new orchestrator cron job for this project
Task: Add a New Department (lattice new-dept)
Ask for: department name, mission (one sentence) Copy templates/ORG/DEPARTMENTS/example-dept/ → ORG/DEPARTMENTS/<name>/ Fill in CHARTER.md with the department name and mission Update ORG_README.md §5 to include the new department
Task: Check Organization Status (lattice status)
Read ORG/TASKBOARD.md — summarize active priorities For each project in ORG/PROJECTS/: Read STATUS.md — current phase and progress Read PIPELINE_STATE.json — phase statuses, blockers, run number For each department in ORG/DEPARTMENTS/: Read HANDOFF.md — current state and blockers Present a concise status report
8 Phases
Constitute → Research → Specify → Plan+Tasks → Implement → Test → Review → Gap Analysis
3-Layer Assistance (when a phase gets stuck)
Model Escalation — retry with progressively stronger models Peer Consult — parallel multi-model consultation + synthesis Auto-Triage — automated judge decides: RELAX (loosen constraints) / DEFER (next iteration) / BLOCK (wait for human)
Key Files per Project
ORG/PROJECTS/<project>/ ├── STATUS.md # Human-readable status ├── DECISIONS.md # Key decisions + rationale ├── PIPELINE_STATE.json # Phase state machine ├── PIPELINE_LOG.jsonl # Append-only history ├── pipeline/ # Current run artifacts └── pipeline_archive/ # Historical runs
Category context
Agent frameworks, memory systems, reasoning layers, and model-native orchestration.
Source: Tencent SkillHub
Largest current source with strong distribution and engagement signals.
Package contents
Included in package
5 Docs1 Config
- SKILL.md
- templates/ORG/ASSET_REGISTRY.md
- templates/ORG/DEPARTMENTS/example-dept/CHARTER.md
- templates/ORG/DEPARTMENTS/example-dept/HANDOFF.md
- templates/ORG/DEPARTMENTS/example-dept/RUNBOOK.md
- templates/ORG/DEPARTMENTS/example-dept/STATE.json