# Send Memory Self-Heal 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. 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. Summarize what changed and any follow-up checks I should run. ``` ## Machine-readable fields ```json { "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": { "downloadUrl": "/downloads/memory-self-heal", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=memory-self-heal", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "SKILL.md" ], "downloadMode": "redirect", "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." ] } }, "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" } } ``` ## Documentation ### Memory Self-Heal Skill Use this skill when the agent starts failing repeatedly, stalls, or keeps asking the user for steps that could be inferred from prior evidence. ### Goals Recover execution without user micromanagement Reuse previous fixes from memory/logs/tasks Escalate only with minimal unblock input when truly blocked Leave reusable evidence for future runs ### When To Trigger Trigger when any of these appear: Same or similar error occurs 2+ times in one task Tool call fails due to argument mismatch, missing config, auth wall, or context overflow Agent claims completion without verifiable artifact Task progress stalls (no new artifact across 2 cycles) ### Inputs Current task objective Latest error/output Available evidence locations (memory, tasks, logs) ### Portable Evidence Scan Order Scan these in order; skip missing paths silently: memory/ (or equivalent workspace memory path) tasks/ or queue files runtime logs / channel logs skill docs (skills/*/SKILL.md) for known fallback recipes core docs (TOOLS.md, CAPABILITIES.md, AGENTS.md) Shell examples (use whichever shell is active): # PowerShell Get-ChildItem -Recurse memory, tasks -ErrorAction SilentlyContinue | Select-String -Pattern "error|blocked|retry|fallback|auth|token|proxy|timeout|context" -Context 2 # POSIX shell rg -n "error|blocked|retry|fallback|auth|token|proxy|timeout|context" memory tasks 2>/dev/null ### Failure Classification Classify first, then act: syntax_or_args: command syntax/argument mismatch auth_or_config: key/token/env/config missing or invalid network_or_reachability: timeout, DNS, handshake, region restrictions ui_login_wall: page requires manual login/attach resource_limit: context window, rate limit, memory pressure false_done: no artifact/evidence but reported complete unknown: no confident class ### Attempt 1: Direct Fix Apply best-known fix from memory for same class/signature Re-run the smallest validating action Record result ### Attempt 2: Safe Fallback Switch to alternate tool/path with lower fragility Narrow scope (smaller input, shorter query, one target) Re-run validation ### Attempt 3: Controlled Escalation Mark blocked with minimum unblock input Provide exact next action user must do (one command or one UI step) Do not loop further until new input arrives ### Safety Rules Never auto-run destructive operations without confirmation Never log secrets/tokens in memory files Max 3 retries per blocker signature per task Prefer deterministic steps over broad speculative retries ### Completion Contract Do not claim done unless all are true: At least one artifact exists and is readable (file/link/output) The original task objective is explicitly mapped to artifact(s) No unresolved blocker for current objective Required output block: DONE_CHECKLIST - Objective met: yes/no - Artifact: - Validation: - Remaining blocker: ### Memory Writeback Template Append one concise entry after each self-heal cycle: ## Self-heal: - Signature: - Class: - Attempt1: -> - Attempt2: -> - Final: - Artifact/Evidence: - Reusable rule: ### Generic Known Fixes (Seed Set) Command mismatch on Windows: prefer native PowerShell cmdlets Token mismatch/auth failure: verify active config source and token scope WebSocket/timeouts: test reachability + proxy/no_proxy consistency Context overflow: split task into smaller units and reduce payload False completion: enforce artifact validation before final response ### Integration Notes Works with autonomy/task-tracker skills but does not depend on them If a project has custom memory paths, adapt scan roots dynamically Keep entries short to avoid memory bloat ## Trust - Source: tencent - Verification: Indexed source record - Publisher: Dalomeve - Version: 1.1.0 ## 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: 2026-05-02T09:39:21.240Z - Expires at: 2026-05-09T09:39:21.240Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/memory-self-heal) - [Send to Agent page](https://openagent3.xyz/skills/memory-self-heal/agent) - [JSON manifest](https://openagent3.xyz/skills/memory-self-heal/agent.json) - [Markdown brief](https://openagent3.xyz/skills/memory-self-heal/agent.md) - [Download page](https://openagent3.xyz/downloads/memory-self-heal)