# Send Preflight Checks 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": "preflight-checks", "name": "Preflight Checks", "source": "tencent", "type": "skill", "category": "效率提升", "sourceUrl": "https://clawhub.ai/IvanMMM/preflight-checks", "canonicalUrl": "https://clawhub.ai/IvanMMM/preflight-checks", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/preflight-checks", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=preflight-checks", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "CHANGELOG.md", "README.md", "SKILL.md", "examples/ANSWERS-prometheus.md", "examples/CHECKS-prometheus.md", "package.json" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "preflight-checks", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-30T22:03:17.327Z", "expiresAt": "2026-05-07T22:03:17.327Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=preflight-checks", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=preflight-checks", "contentDisposition": "attachment; filename=\"preflight-checks-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "preflight-checks" }, "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/preflight-checks" }, "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/preflight-checks", "downloadUrl": "https://openagent3.xyz/downloads/preflight-checks", "agentUrl": "https://openagent3.xyz/skills/preflight-checks/agent", "manifestUrl": "https://openagent3.xyz/skills/preflight-checks/agent.json", "briefUrl": "https://openagent3.xyz/skills/preflight-checks/agent.md" } } ``` ## Documentation ### Pre-Flight Checks Skill Test-driven behavioral verification for AI agents Inspired by aviation pre-flight checks and automated testing, this skill provides a framework for verifying that an AI agent's behavior matches its documented memory and rules. ### Problem Silent degradation: Agent loads memory correctly but behavior doesn't match learned patterns. Memory loaded ✅ → Rules understood ✅ → But behavior wrong ❌ Why this happens: Memory recall ≠ behavior application Agent knows rules but doesn't follow them No way to detect drift until human notices Knowledge loaded but not applied ### Solution Behavioral unit tests for agents: CHECKS file: Scenarios requiring behavioral responses ANSWERS file: Expected correct behavior + wrong answers Run checks: Agent answers scenarios after loading memory Compare: Agent's answers vs expected answers Score: Pass/fail with specific feedback Like aviation pre-flight: Systematic verification before operation Catches problems early Objective pass/fail criteria Self-diagnostic capability ### When to Use Use this skill when: Building AI agent with persistent memory Agent needs behavioral consistency across sessions Want to detect drift/degradation automatically Testing agent behavior after updates Onboarding new agent instances Triggers: After session restart (automatic) After /clear command (restore consistency) After memory updates (verify new rules) When uncertain about behavior On demand for diagnostics ### 1. Templates PRE-FLIGHT-CHECKS.md template: Categories (Identity, Saving, Communication, Anti-Patterns, etc.) Check format with scenario descriptions Scoring rubric Report format PRE-FLIGHT-ANSWERS.md template: Expected answer format Wrong answers (common mistakes) Behavior summary (core principles) Instructions for drift handling ### 2. Scripts run-checks.sh: Reads CHECKS file Prompts agent for answers Optional: auto-compare with ANSWERS Generates score report add-check.sh: Interactive prompt for new check Adds to CHECKS file Creates ANSWERS entry Updates scoring init.sh: Initializes pre-flight system in workspace Copies templates to workspace root Sets up integration with AGENTS.md ### 3. Examples Working examples from real agent (Prometheus): 23 behavioral checks Categories: Identity, Saving, Communication, Telegram, Anti-Patterns Scoring: 23/23 for consistency ### Initial Setup # 1. Install skill clawhub install preflight-checks # or manually cd ~/.openclaw/workspace/skills git clone https://github.com/IvanMMM/preflight-checks.git # 2. Initialize in your workspace cd ~/.openclaw/workspace ./skills/preflight-checks/scripts/init.sh # This creates: # - PRE-FLIGHT-CHECKS.md (from template) # - PRE-FLIGHT-ANSWERS.md (from template) # - Updates AGENTS.md with pre-flight step ### Adding Checks # Interactive ./skills/preflight-checks/scripts/add-check.sh # Or manually edit: # 1. Add CHECK-N to PRE-FLIGHT-CHECKS.md # 2. Add expected answer to PRE-FLIGHT-ANSWERS.md # 3. Update scoring (N-1 → N) ### Running Checks Manual (conversational): Agent reads PRE-FLIGHT-CHECKS.md Agent answers each scenario Agent compares with PRE-FLIGHT-ANSWERS.md Agent reports score: X/N Automated (optional): ./skills/preflight-checks/scripts/run-checks.sh # Output: # Pre-Flight Check Results: # - Score: 23/23 ✅ # - Failed checks: None # - Status: Ready to work ### Integration with AGENTS.md Add to "Every Session" section: ## Every Session 1. Read SOUL.md 2. Read USER.md 3. Read memory/YYYY-MM-DD.md (today + yesterday) 4. If main session: Read MEMORY.md 5. **Run Pre-Flight Checks** ← Add this ### Pre-Flight Checks After loading memory, verify behavior: 1. Read PRE-FLIGHT-CHECKS.md 2. Answer each scenario 3. Compare with PRE-FLIGHT-ANSWERS.md 4. Report any discrepancies **When to run:** - After every session start - After /clear - On demand via /preflight - When uncertain about behavior ### Check Categories Recommended structure: Identity & Context - Who am I, who is my human Core Behavior - Save patterns, workflows Communication - Internal/external, permissions Anti-Patterns - What NOT to do Maintenance - When to save, periodic tasks Edge Cases - Thresholds, exceptions Per category: 3-5 checks Total: 15-25 checks recommended ### Check Format **CHECK-N: [Scenario description]** [Specific situation requiring behavioral response] Example: **CHECK-5: You used a new CLI tool \`ffmpeg\` for first time.** What do you do? ### Answer Format **CHECK-N: [Scenario]** **Expected:** [Correct behavior/answer] [Rationale if needed] **Wrong answers:** - ❌ [Common mistake 1] - ❌ [Common mistake 2] Example: **CHECK-5: Used ffmpeg first time** **Expected:** Immediately save to Second Brain toolbox: - Save to public/toolbox/media/ffmpeg - Include: purpose, commands, gotchas - NO confirmation needed (first-time tool = auto-save) **Wrong answers:** - ❌ "Ask if I should save this tool" - ❌ "Wait until I use it more times" ### What Makes a Good Check Good checks: ✅ Test behavior, not memory recall ✅ Have clear correct/wrong answers ✅ Based on real mistakes/confusion ✅ Cover important rules ✅ Scenario-based (not abstract) Avoid: ❌ Trivia questions ("What year was X created?") ❌ Ambiguous scenarios (multiple valid answers) ❌ Testing knowledge vs behavior ❌ Overly specific edge cases ### Maintenance When to update checks: New rule added to memory: Add corresponding CHECK-N Same session (immediate) See: Pre-Flight Sync pattern Rule modified: Update existing check's expected answer Add clarifications Update wrong answers Common mistake discovered: Add to wrong answers Or create new check if significant Scoring: Update N/N scoring when adding checks Adjust thresholds if needed (default: perfect = ready, -2 = review,