{ "schemaVersion": "1.0", "item": { "slug": "auto-improve", "name": "Auto Improve", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/Mcben90/auto-improve", "canonicalUrl": "https://clawhub.ai/Mcben90/auto-improve", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/auto-improve", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=auto-improve", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md" ], "primaryDoc": "SKILL.md", "quickSetup": [ "Download the package from Yavira.", "Extract the archive and review SKILL.md first.", "Import or place the package into your OpenClaw setup." ], "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "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." ], "prompts": [ { "label": "New install", "body": "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." }, { "label": "Upgrade existing", "body": "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." } ] }, "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-23T16:43:11.935Z", "expiresAt": "2026-04-30T16:43:11.935Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.zip\"", "redirectLocation": null, "bodySnippet": null }, "scope": "source", "summary": "Source download looks usable.", "detail": "Yavira can redirect you to the upstream package for this source.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/auto-improve" }, "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." ] }, "downloadPageUrl": "https://openagent3.xyz/downloads/auto-improve", "agentPageUrl": "https://openagent3.xyz/skills/auto-improve/agent", "manifestUrl": "https://openagent3.xyz/skills/auto-improve/agent.json", "briefUrl": "https://openagent3.xyz/skills/auto-improve/agent.md" }, "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "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." ], "prompts": [ { "label": "New install", "body": "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." }, { "label": "Upgrade existing", "body": "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." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "Auto-Improve Skill", "body": "Kernprinzip: Jede Aktion macht mich besser für die nächste." }, { "title": "Wann aktivieren", "body": "Session-Start (automatisch)\nNach jedem Task-Abschluss\nBei Fehlern" }, { "title": "Der Improvement Loop", "body": "┌─────────────────────────────────────────────────┐\n│ AUTO-IMPROVE LOOP │\n├─────────────────────────────────────────────────┤\n│ │\n│ SESSION START │\n│ │ │\n│ ▼ │\n│ ┌─────────────────┐ │\n│ │ 1. Load Context │ │\n│ │ .antigravity │ │\n│ │ + MEMORY │ │\n│ └────────┬────────┘ │\n│ ▼ │\n│ ┌─────────────────┐ │\n│ │ 2. Check │ │\n│ │ Past Mistakes│ ← \"Was hab ich falsch │\n│ └────────┬────────┘ gemacht?\" │\n│ ▼ │\n│ ┌─────────────────┐ │\n│ │ 3. EXECUTE TASK │ │\n│ └────────┬────────┘ │\n│ ▼ │\n│ ┌─────────────────┐ │\n│ │ 4. Verify │ ← Tests + Lint │\n│ └────────┬────────┘ │\n│ ▼ │\n│ ┌─────────────┐ │\n│ │ Erfolgreich?│ │\n│ └──────┬──────┘ │\n│ JA │ NEIN │\n│ ↓ │ ↓ │\n│ ┌───────┐ │ ┌──────────┐ │\n│ │Pattern│ │ │ Learn │ │\n│ │Save │ │ │ Mistake │ │\n│ └───┬───┘ │ └────┬─────┘ │\n│ └─────┼──────┘ │\n│ ▼ │\n│ ┌─────────────────┐ │\n│ │ 5. Update │ │\n│ │ .antigravity │ │\n│ └─────────────────┘ │\n│ │\n│ → NÄCHSTER TASK IST BESSER │\n│ │\n└─────────────────────────────────────────────────┘" }, { "title": "Phase 1: Session Start", "body": "# Automatisch bei Session-Start ausführen\n\n# 1. Projekt-Kontext laden\nproject_root = detect_project_root()\nantigravity_file = f\"{project_root}/.antigravity.md\"\n\nif exists(antigravity_file):\n load_context(antigravity_file)\n \n# 2. Globales Memory laden\nrecall_memory(tags=[\"mistakes\", project_name])\n\n# 3. Warnung bei bekannten Fehlern\nif relevant_mistakes:\n warn(f\"⚠️ Bekannte Fehler für {project}: {mistakes}\")" }, { "title": "Phase 2: Pre-Action Check", "body": "Vor JEDER Code-Änderung:\n\n## Pre-Action Checklist\n- [ ] Habe ich das schon mal falsch gemacht?\n- [ ] Gibt es ein gespeichertes Pattern dafür?\n- [ ] Verstehe ich das Projekt-Architektur?\n- [ ] Kenne ich die Coding-Standards?" }, { "title": "Phase 3: Post-Action Learn", "body": "Nach JEDER Aktion:" }, { "title": "Bei Erfolg", "body": "save_pattern(\n situation=task.context,\n action=task.approach,\n outcome=\"success\",\n pattern=extract_reusable_pattern(task)\n)" }, { "title": "Bei Fehler", "body": "learn_from_mistake(\n mistake=error.description,\n cause=error.root_cause,\n lesson=error.how_to_avoid,\n tags=[\"mistakes\", project, domain]\n)\n\n# Auto-Update .antigravity.md\nupdate_antigravity_mistakes(project, error)" }, { "title": "Integration mit bestehenden Skills", "body": "SkillIntegrationmistake-trackerLiefert Fehler-Datenverification-loopsTriggert Post-Action Learncontext-managementSession Context ladenself-checkPre-Action Validation" }, { "title": "Automatische Trigger", "body": "session_start:\n - load_project_context\n - recall_mistakes\n - warn_known_issues\n\npost_code_edit:\n - run_verification_loop\n - if_error: learn_from_mistake\n - if_success: save_pattern\n\nsession_end:\n - summarize_learnings\n - update_antigravity" }, { "title": "Manuelle Trigger", "body": "/improve - Force Learning aus letzter Aktion\n/mistakes - Zeige alle gelernten Fehler\n/patterns - Zeige erfolgreiche Patterns" }, { "title": "Metriken", "body": "Track diese Werte über Zeit:\n\nMetrikBeschreibungmistakes_repeatedSollte → 0 gehenfirst_time_rightSollte → 100% gehenpatterns_reusedSollte steigenverification_failuresSollte sinken" }, { "title": "Anti-Patterns", "body": "❌ DON'T✅ DOFehler ignorierenJeden Fehler speichernNur aktuelle SessionCross-Session lernenGenerische LessonsSpezifische, actionable LessonsZu viel speichernNur Relevantes speichern" } ], "body": "Auto-Improve Skill\n\nKernprinzip: Jede Aktion macht mich besser für die nächste.\n\nWann aktivieren\nSession-Start (automatisch)\nNach jedem Task-Abschluss\nBei Fehlern\nDer Improvement Loop\n┌─────────────────────────────────────────────────┐\n│ AUTO-IMPROVE LOOP │\n├─────────────────────────────────────────────────┤\n│ │\n│ SESSION START │\n│ │ │\n│ ▼ │\n│ ┌─────────────────┐ │\n│ │ 1. Load Context │ │\n│ │ .antigravity │ │\n│ │ + MEMORY │ │\n│ └────────┬────────┘ │\n│ ▼ │\n│ ┌─────────────────┐ │\n│ │ 2. Check │ │\n│ │ Past Mistakes│ ← \"Was hab ich falsch │\n│ └────────┬────────┘ gemacht?\" │\n│ ▼ │\n│ ┌─────────────────┐ │\n│ │ 3. EXECUTE TASK │ │\n│ └────────┬────────┘ │\n│ ▼ │\n│ ┌─────────────────┐ │\n│ │ 4. Verify │ ← Tests + Lint │\n│ └────────┬────────┘ │\n│ ▼ │\n│ ┌─────────────┐ │\n│ │ Erfolgreich?│ │\n│ └──────┬──────┘ │\n│ JA │ NEIN │\n│ ↓ │ ↓ │\n│ ┌───────┐ │ ┌──────────┐ │\n│ │Pattern│ │ │ Learn │ │\n│ │Save │ │ │ Mistake │ │\n│ └───┬───┘ │ └────┬─────┘ │\n│ └─────┼──────┘ │\n│ ▼ │\n│ ┌─────────────────┐ │\n│ │ 5. Update │ │\n│ │ .antigravity │ │\n│ └─────────────────┘ │\n│ │\n│ → NÄCHSTER TASK IST BESSER │\n│ │\n└─────────────────────────────────────────────────┘\n\nPhase 1: Session Start\n# Automatisch bei Session-Start ausführen\n\n# 1. Projekt-Kontext laden\nproject_root = detect_project_root()\nantigravity_file = f\"{project_root}/.antigravity.md\"\n\nif exists(antigravity_file):\n load_context(antigravity_file)\n \n# 2. Globales Memory laden\nrecall_memory(tags=[\"mistakes\", project_name])\n\n# 3. Warnung bei bekannten Fehlern\nif relevant_mistakes:\n warn(f\"⚠️ Bekannte Fehler für {project}: {mistakes}\")\n\nPhase 2: Pre-Action Check\n\nVor JEDER Code-Änderung:\n\n## Pre-Action Checklist\n- [ ] Habe ich das schon mal falsch gemacht?\n- [ ] Gibt es ein gespeichertes Pattern dafür?\n- [ ] Verstehe ich das Projekt-Architektur?\n- [ ] Kenne ich die Coding-Standards?\n\nPhase 3: Post-Action Learn\n\nNach JEDER Aktion:\n\nBei Erfolg\nsave_pattern(\n situation=task.context,\n action=task.approach,\n outcome=\"success\",\n pattern=extract_reusable_pattern(task)\n)\n\nBei Fehler\nlearn_from_mistake(\n mistake=error.description,\n cause=error.root_cause,\n lesson=error.how_to_avoid,\n tags=[\"mistakes\", project, domain]\n)\n\n# Auto-Update .antigravity.md\nupdate_antigravity_mistakes(project, error)\n\nIntegration mit bestehenden Skills\nSkill\tIntegration\nmistake-tracker\tLiefert Fehler-Daten\nverification-loops\tTriggert Post-Action Learn\ncontext-management\tSession Context laden\nself-check\tPre-Action Validation\nTriggers\nAutomatische Trigger\nsession_start:\n - load_project_context\n - recall_mistakes\n - warn_known_issues\n\npost_code_edit:\n - run_verification_loop\n - if_error: learn_from_mistake\n - if_success: save_pattern\n\nsession_end:\n - summarize_learnings\n - update_antigravity\n\nManuelle Trigger\n/improve - Force Learning aus letzter Aktion\n/mistakes - Zeige alle gelernten Fehler\n/patterns - Zeige erfolgreiche Patterns\nMetriken\n\nTrack diese Werte über Zeit:\n\nMetrik\tBeschreibung\nmistakes_repeated\tSollte → 0 gehen\nfirst_time_right\tSollte → 100% gehen\npatterns_reused\tSollte steigen\nverification_failures\tSollte sinken\nAnti-Patterns\n❌ DON'T\t✅ DO\nFehler ignorieren\tJeden Fehler speichern\nNur aktuelle Session\tCross-Session lernen\nGenerische Lessons\tSpezifische, actionable Lessons\nZu viel speichern\tNur Relevantes speichern" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/Mcben90/auto-improve", "publisherUrl": "https://clawhub.ai/Mcben90/auto-improve", "owner": "Mcben90", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/auto-improve", "downloadUrl": "https://openagent3.xyz/downloads/auto-improve", "agentUrl": "https://openagent3.xyz/skills/auto-improve/agent", "manifestUrl": "https://openagent3.xyz/skills/auto-improve/agent.json", "briefUrl": "https://openagent3.xyz/skills/auto-improve/agent.md" } }