{ "schemaVersion": "1.0", "item": { "slug": "agent-wal", "name": "Agent Wal", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/bowen31337/agent-wal", "canonicalUrl": "https://clawhub.ai/bowen31337/agent-wal", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/agent-wal", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agent-wal", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "scripts/wal.py", "skill.toml" ], "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/agent-wal" }, "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/agent-wal", "agentPageUrl": "https://openagent3.xyz/skills/agent-wal/agent", "manifestUrl": "https://openagent3.xyz/skills/agent-wal/agent.json", "briefUrl": "https://openagent3.xyz/skills/agent-wal/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": "Agent WAL (Write-Ahead Log)", "body": "Write important state to disk before responding. Prevents the #1 agent failure mode: losing corrections and context during compaction." }, { "title": "Core Rule", "body": "Write before you respond. If something is worth remembering, WAL it first." }, { "title": "When to WAL", "body": "TriggerAction TypeExampleUser corrects youcorrection\"No, use Podman not Docker\"You make a key decisiondecision\"Using CogVideoX-2B for text-to-video\"Important analysis/conclusionanalysis\"WAL/VFM patterns should be core infra not skills\"State changestate_change\"GPU server SSH key auth configured\"User says \"remember this\"correctionWhatever they said" }, { "title": "Commands", "body": "All commands via scripts/wal.py (relative to this skill directory):\n\n# Write before responding\npython3 scripts/wal.py append agent1 correction \"Use Podman not Docker for all EvoClaw tooling\"\npython3 scripts/wal.py append agent1 decision \"CogVideoX-5B with multi-GPU via accelerate\"\npython3 scripts/wal.py append agent1 analysis \"Signed constraints prevent genome tampering\"\n\n# Working buffer (batch writes during conversation, flush before compaction)\npython3 scripts/wal.py buffer-add agent1 decision \"Some decision\"\npython3 scripts/wal.py flush-buffer agent1\n\n# Session start: replay lost context\npython3 scripts/wal.py replay agent1\n\n# After applying a replayed entry\npython3 scripts/wal.py mark-applied agent1 \n\n# Maintenance\npython3 scripts/wal.py status agent1\npython3 scripts/wal.py prune agent1 --keep 50" }, { "title": "On Session Start", "body": "Run replay to get unapplied entries\nRead the summary into your context\nMark entries as applied after incorporating them" }, { "title": "On User Correction", "body": "Run append with action_type correction BEFORE responding\nThen respond with the corrected behavior" }, { "title": "On Pre-Compaction Flush", "body": "Run flush-buffer to persist any buffered entries\nThen write to daily memory files as usual" }, { "title": "During Conversation", "body": "For less critical items, use buffer-add to batch writes. Buffer is flushed to WAL on flush-buffer (called during pre-compaction) or manually." }, { "title": "Storage", "body": "WAL files: ~/clawd/memory/wal/.wal.jsonl\nBuffer files: ~/clawd/memory/wal/.buffer.jsonl\n\nEntries are append-only JSONL. Each entry:\n\n{\"id\": \"abc123\", \"timestamp\": \"ISO8601\", \"agent_id\": \"agent1\", \"action_type\": \"correction\", \"payload\": \"Use Podman not Docker\", \"applied\": false}" } ], "body": "Agent WAL (Write-Ahead Log)\n\nWrite important state to disk before responding. Prevents the #1 agent failure mode: losing corrections and context during compaction.\n\nCore Rule\n\nWrite before you respond. If something is worth remembering, WAL it first.\n\nWhen to WAL\nTrigger\tAction Type\tExample\nUser corrects you\tcorrection\t\"No, use Podman not Docker\"\nYou make a key decision\tdecision\t\"Using CogVideoX-2B for text-to-video\"\nImportant analysis/conclusion\tanalysis\t\"WAL/VFM patterns should be core infra not skills\"\nState change\tstate_change\t\"GPU server SSH key auth configured\"\nUser says \"remember this\"\tcorrection\tWhatever they said\nCommands\n\nAll commands via scripts/wal.py (relative to this skill directory):\n\n# Write before responding\npython3 scripts/wal.py append agent1 correction \"Use Podman not Docker for all EvoClaw tooling\"\npython3 scripts/wal.py append agent1 decision \"CogVideoX-5B with multi-GPU via accelerate\"\npython3 scripts/wal.py append agent1 analysis \"Signed constraints prevent genome tampering\"\n\n# Working buffer (batch writes during conversation, flush before compaction)\npython3 scripts/wal.py buffer-add agent1 decision \"Some decision\"\npython3 scripts/wal.py flush-buffer agent1\n\n# Session start: replay lost context\npython3 scripts/wal.py replay agent1\n\n# After applying a replayed entry\npython3 scripts/wal.py mark-applied agent1 \n\n# Maintenance\npython3 scripts/wal.py status agent1\npython3 scripts/wal.py prune agent1 --keep 50\n\nIntegration Points\nOn Session Start\nRun replay to get unapplied entries\nRead the summary into your context\nMark entries as applied after incorporating them\nOn User Correction\nRun append with action_type correction BEFORE responding\nThen respond with the corrected behavior\nOn Pre-Compaction Flush\nRun flush-buffer to persist any buffered entries\nThen write to daily memory files as usual\nDuring Conversation\n\nFor less critical items, use buffer-add to batch writes. Buffer is flushed to WAL on flush-buffer (called during pre-compaction) or manually.\n\nStorage\n\nWAL files: ~/clawd/memory/wal/.wal.jsonl Buffer files: ~/clawd/memory/wal/.buffer.jsonl\n\nEntries are append-only JSONL. Each entry:\n\n{\"id\": \"abc123\", \"timestamp\": \"ISO8601\", \"agent_id\": \"agent1\", \"action_type\": \"correction\", \"payload\": \"Use Podman not Docker\", \"applied\": false}" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/bowen31337/agent-wal", "publisherUrl": "https://clawhub.ai/bowen31337/agent-wal", "owner": "bowen31337", "version": "1.0.1", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/agent-wal", "downloadUrl": "https://openagent3.xyz/downloads/agent-wal", "agentUrl": "https://openagent3.xyz/skills/agent-wal/agent", "manifestUrl": "https://openagent3.xyz/skills/agent-wal/agent.json", "briefUrl": "https://openagent3.xyz/skills/agent-wal/agent.md" } }