# Send Skill Priority Setup to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - 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. ## Suggested prompts ### New install ```text I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete. ``` ### Upgrade existing ```text 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "skill-priority-setup", "name": "Skill Priority Setup", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/halfmoon82/skill-priority-setup", "canonicalUrl": "https://clawhub.ai/halfmoon82/skill-priority-setup", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/skill-priority-setup", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=skill-priority-setup", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "README.md", "SKILL.md", "clawhub.yaml", "scripts/generate_docx.py", "scripts/generate_docx_cn.py", "scripts/setup.py" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "skill-priority-setup", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-09T00:03:06.178Z", "expiresAt": "2026-05-16T00:03:06.178Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=skill-priority-setup", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=skill-priority-setup", "contentDisposition": "attachment; filename=\"skill-priority-setup-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "skill-priority-setup" }, "scope": "item", "summary": "Item download looks usable.", "detail": "Yavira can redirect you to the upstream package for this item.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/skill-priority-setup" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] } }, "links": { "detailUrl": "https://openagent3.xyz/skills/skill-priority-setup", "downloadUrl": "https://openagent3.xyz/downloads/skill-priority-setup", "agentUrl": "https://openagent3.xyz/skills/skill-priority-setup/agent", "manifestUrl": "https://openagent3.xyz/skills/skill-priority-setup/agent.json", "briefUrl": "https://openagent3.xyz/skills/skill-priority-setup/agent.md" } } ``` ## Documentation ### Skill Priority Setup Automated skill tiering and injection policy configuration for OpenClaw. ### What This Skill Does Discovery Phase: Scans all installed skills across standard directories Analysis Phase: Suggests L0-L3 tier assignments based on skill characteristics Configuration Phase: Applies the tiered architecture to your setup Validation Phase: Verifies configuration and estimates token savings ### Quick Start # Run the interactive setup wizard python3 ~/.openclaw/workspace/skills/skill-priority-setup/scripts/setup.py # Or non-interactive mode with defaults python3 ~/.openclaw/workspace/skills/skill-priority-setup/scripts/setup.py --auto ### When to Use New Setup: Just installed multiple skills and want optimal configuration Performance Issues: High token usage or slow responses Migration: Upgrading from flat skill structure to tiered architecture Audit: Reviewing and optimizing existing skill priorities ### Architecture Overview This skill implements a 4-tier priority system: ### L0 - ROM Core (Always Active) semantic-system: Semantic routing (message injector) agent-evolution: Self-improvement behaviors (SOUL.md) config-modification: Config safety (on-demand) skill-safe-install: Installation safety (on-demand) ### L1 - Routing Layer (Task-Triggered) browser-automation: Web automation find-skills: Skill discovery teamtask: Multi-agent coordination ### L2 - Domain Skills (Keyword-Triggered) Document: word-docx, tesseract-ocr Media: youtube-transcript Platform: discord, wechat-suite, evomap Automation: automation-workflows ### L3 - Extensions (Manual/On-Demand) Third-party integrations: notion, slack, github, etc. ### Workflow ┌─────────────────┐ │ 1. Scan Skills │ → Find all SKILL.md files └────────┬────────┘ ▼ ┌─────────────────┐ │ 2. Analyze │ → Detect skill types & dependencies └────────┬────────┘ ▼ ┌─────────────────┐ │ 3. Suggest Tiers│ → Propose L0-L3 assignments └────────┬────────┘ ▼ ┌─────────────────┐ │ 4. User Review │ → Confirm or modify suggestions └────────┬────────┘ ▼ ┌─────────────────┐ │ 5. Apply Config │ → Update AGENTS.md, SOUL.md, etc. └────────┬────────┘ ▼ ┌─────────────────┐ │ 6. Validate │ → Check JSON, test injection └─────────────────┘ ### Token Budget L0 Core: ≤300 tokens/round (minimal rules) L1 Triggered: ≤400 tokens per injection Total Budget: ≤900 tokens/round Overflow Strategy: Inject summary + file path only ### Safety Features Backup before any configuration changes JSON validation before applying Dry-run mode (--dry-run) Rollback capability ### Files Created SKILL_PRIORITY_POLICY.md: Your custom policy document AGENTS.md updates: Core constraints added SOUL.md updates: Agent evolution behaviors Backup files: .backup/*.timestamp ### Configuration Edit ~/.openclaw/workspace/skills/skill-priority-setup/config.yaml to customize: # Default tier assignments (override per skill) default_tiers: semantic-router: L0 browser: L1 word-docx: L2 # Token budgets token_budget: l0_max: 300 l1_max: 400 total_max: 900 # Safety settings backup_before_change: true validate_json: true auto_rollback: true ### Gateway Won't Start Check if message injector content exceeds limit Run with --diagnose flag ### Skills Not Loading Verify allowBundled list in openclaw.json Check file permissions ### High Token Usage Review L0 assignments (should be minimal) Consider moving skills to lower tiers ### References Original Implementation: SKILL_PRIORITY_POLICY.md OpenClaw Docs: https://docs.openclaw.ai/skills ## Trust - Source: tencent - Verification: Indexed source record - Publisher: halfmoon82 - Version: 1.0.0 ## Source health - Status: healthy - Item download looks usable. - Yavira can redirect you to the upstream package for this item. - Health scope: item - Reason: direct_download_ok - Checked at: 2026-05-09T00:03:06.178Z - Expires at: 2026-05-16T00:03:06.178Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/skill-priority-setup) - [Send to Agent page](https://openagent3.xyz/skills/skill-priority-setup/agent) - [JSON manifest](https://openagent3.xyz/skills/skill-priority-setup/agent.json) - [Markdown brief](https://openagent3.xyz/skills/skill-priority-setup/agent.md) - [Download page](https://openagent3.xyz/downloads/skill-priority-setup)