{ "schemaVersion": "1.0", "item": { "slug": "memory-self-heal", "name": "Memory Self-Heal", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/Dalomeve/memory-self-heal", "canonicalUrl": "https://clawhub.ai/Dalomeve/memory-self-heal", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/memory-self-heal", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=memory-self-heal", "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", "slug": "memory-self-heal", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-02T09:39:21.240Z", "expiresAt": "2026-05-09T09:39:21.240Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=memory-self-heal", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=memory-self-heal", "contentDisposition": "attachment; filename=\"memory-self-heal-1.1.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "memory-self-heal" }, "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/memory-self-heal" }, "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/memory-self-heal", "agentPageUrl": "https://openagent3.xyz/skills/memory-self-heal/agent", "manifestUrl": "https://openagent3.xyz/skills/memory-self-heal/agent.json", "briefUrl": "https://openagent3.xyz/skills/memory-self-heal/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": "Memory Self-Heal Skill", "body": "Use this skill when the agent starts failing repeatedly, stalls, or keeps asking the user for steps that could be inferred from prior evidence." }, { "title": "Goals", "body": "Recover execution without user micromanagement\nReuse previous fixes from memory/logs/tasks\nEscalate only with minimal unblock input when truly blocked\nLeave reusable evidence for future runs" }, { "title": "When To Trigger", "body": "Trigger when any of these appear:\n\nSame or similar error occurs 2+ times in one task\nTool call fails due to argument mismatch, missing config, auth wall, or context overflow\nAgent claims completion without verifiable artifact\nTask progress stalls (no new artifact across 2 cycles)" }, { "title": "Inputs", "body": "Current task objective\nLatest error/output\nAvailable evidence locations (memory, tasks, logs)" }, { "title": "Portable Evidence Scan Order", "body": "Scan these in order; skip missing paths silently:\n\nmemory/ (or equivalent workspace memory path)\ntasks/ or queue files\nruntime logs / channel logs\nskill docs (skills/*/SKILL.md) for known fallback recipes\ncore docs (TOOLS.md, CAPABILITIES.md, AGENTS.md)\n\nShell examples (use whichever shell is active):\n\n# PowerShell\nGet-ChildItem -Recurse memory, tasks -ErrorAction SilentlyContinue |\n Select-String -Pattern \"error|blocked|retry|fallback|auth|token|proxy|timeout|context\" -Context 2\n\n# POSIX shell\nrg -n \"error|blocked|retry|fallback|auth|token|proxy|timeout|context\" memory tasks 2>/dev/null" }, { "title": "Failure Classification", "body": "Classify first, then act:\n\nsyntax_or_args: command syntax/argument mismatch\nauth_or_config: key/token/env/config missing or invalid\nnetwork_or_reachability: timeout, DNS, handshake, region restrictions\nui_login_wall: page requires manual login/attach\nresource_limit: context window, rate limit, memory pressure\nfalse_done: no artifact/evidence but reported complete\nunknown: no confident class" }, { "title": "Attempt 1: Direct Fix", "body": "Apply best-known fix from memory for same class/signature\nRe-run the smallest validating action\nRecord result" }, { "title": "Attempt 2: Safe Fallback", "body": "Switch to alternate tool/path with lower fragility\nNarrow scope (smaller input, shorter query, one target)\nRe-run validation" }, { "title": "Attempt 3: Controlled Escalation", "body": "Mark blocked with minimum unblock input\nProvide exact next action user must do (one command or one UI step)\nDo not loop further until new input arrives" }, { "title": "Safety Rules", "body": "Never auto-run destructive operations without confirmation\nNever log secrets/tokens in memory files\nMax 3 retries per blocker signature per task\nPrefer deterministic steps over broad speculative retries" }, { "title": "Completion Contract", "body": "Do not claim done unless all are true:\n\nAt least one artifact exists and is readable (file/link/output)\nThe original task objective is explicitly mapped to artifact(s)\nNo unresolved blocker for current objective\n\nRequired output block:\n\nDONE_CHECKLIST\n- Objective met: yes/no\n- Artifact: \n- Validation: \n- Remaining blocker: " }, { "title": "Memory Writeback Template", "body": "Append one concise entry after each self-heal cycle:\n\n## Self-heal: \n- Signature: \n- Class: \n- Attempt1: -> \n- Attempt2: -> \n- Final: \n- Artifact/Evidence: \n- Reusable rule: " }, { "title": "Generic Known Fixes (Seed Set)", "body": "Command mismatch on Windows: prefer native PowerShell cmdlets\nToken mismatch/auth failure: verify active config source and token scope\nWebSocket/timeouts: test reachability + proxy/no_proxy consistency\nContext overflow: split task into smaller units and reduce payload\nFalse completion: enforce artifact validation before final response" }, { "title": "Integration Notes", "body": "Works with autonomy/task-tracker skills but does not depend on them\nIf a project has custom memory paths, adapt scan roots dynamically\nKeep entries short to avoid memory bloat" } ], "body": "Memory Self-Heal Skill\n\nUse this skill when the agent starts failing repeatedly, stalls, or keeps asking the user for steps that could be inferred from prior evidence.\n\nGoals\nRecover execution without user micromanagement\nReuse previous fixes from memory/logs/tasks\nEscalate only with minimal unblock input when truly blocked\nLeave reusable evidence for future runs\nWhen To Trigger\n\nTrigger when any of these appear:\n\nSame or similar error occurs 2+ times in one task\nTool call fails due to argument mismatch, missing config, auth wall, or context overflow\nAgent claims completion without verifiable artifact\nTask progress stalls (no new artifact across 2 cycles)\nInputs\nCurrent task objective\nLatest error/output\nAvailable evidence locations (memory, tasks, logs)\nPortable Evidence Scan Order\n\nScan these in order; skip missing paths silently:\n\nmemory/ (or equivalent workspace memory path)\ntasks/ or queue files\nruntime logs / channel logs\nskill docs (skills/*/SKILL.md) for known fallback recipes\ncore docs (TOOLS.md, CAPABILITIES.md, AGENTS.md)\n\nShell examples (use whichever shell is active):\n\n# PowerShell\nGet-ChildItem -Recurse memory, tasks -ErrorAction SilentlyContinue |\n Select-String -Pattern \"error|blocked|retry|fallback|auth|token|proxy|timeout|context\" -Context 2\n\n# POSIX shell\nrg -n \"error|blocked|retry|fallback|auth|token|proxy|timeout|context\" memory tasks 2>/dev/null\n\nFailure Classification\n\nClassify first, then act:\n\nsyntax_or_args: command syntax/argument mismatch\nauth_or_config: key/token/env/config missing or invalid\nnetwork_or_reachability: timeout, DNS, handshake, region restrictions\nui_login_wall: page requires manual login/attach\nresource_limit: context window, rate limit, memory pressure\nfalse_done: no artifact/evidence but reported complete\nunknown: no confident class\nRecovery Policy (3-Tier)\nAttempt 1: Direct Fix\nApply best-known fix from memory for same class/signature\nRe-run the smallest validating action\nRecord result\nAttempt 2: Safe Fallback\nSwitch to alternate tool/path with lower fragility\nNarrow scope (smaller input, shorter query, one target)\nRe-run validation\nAttempt 3: Controlled Escalation\nMark blocked with minimum unblock input\nProvide exact next action user must do (one command or one UI step)\nDo not loop further until new input arrives\nSafety Rules\nNever auto-run destructive operations without confirmation\nNever log secrets/tokens in memory files\nMax 3 retries per blocker signature per task\nPrefer deterministic steps over broad speculative retries\nCompletion Contract\n\nDo not claim done unless all are true:\n\nAt least one artifact exists and is readable (file/link/output)\nThe original task objective is explicitly mapped to artifact(s)\nNo unresolved blocker for current objective\n\nRequired output block:\n\nDONE_CHECKLIST\n- Objective met: yes/no\n- Artifact: \n- Validation: \n- Remaining blocker: \n\nMemory Writeback Template\n\nAppend one concise entry after each self-heal cycle:\n\n## Self-heal: \n- Signature: \n- Class: \n- Attempt1: -> \n- Attempt2: -> \n- Final: \n- Artifact/Evidence: \n- Reusable rule: \n\nGeneric Known Fixes (Seed Set)\nCommand mismatch on Windows: prefer native PowerShell cmdlets\nToken mismatch/auth failure: verify active config source and token scope\nWebSocket/timeouts: test reachability + proxy/no_proxy consistency\nContext overflow: split task into smaller units and reduce payload\nFalse completion: enforce artifact validation before final response\nIntegration Notes\nWorks with autonomy/task-tracker skills but does not depend on them\nIf a project has custom memory paths, adapt scan roots dynamically\nKeep entries short to avoid memory bloat" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/Dalomeve/memory-self-heal", "publisherUrl": "https://clawhub.ai/Dalomeve/memory-self-heal", "owner": "Dalomeve", "version": "1.1.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/memory-self-heal", "downloadUrl": "https://openagent3.xyz/downloads/memory-self-heal", "agentUrl": "https://openagent3.xyz/skills/memory-self-heal/agent", "manifestUrl": "https://openagent3.xyz/skills/memory-self-heal/agent.json", "briefUrl": "https://openagent3.xyz/skills/memory-self-heal/agent.md" } }