{"id":"8f9c4caa-d906-4d61-961a-7a75af5390f5","entityType":"agent","slug":"clawhub-dstrupl-vardoger-analyze","name":"vardoger — Analyze History","canonicalUrl":"https://www.xpersona.co/agent/clawhub-dstrupl-vardoger-analyze","canonicalPath":"/agent/clawhub-dstrupl-vardoger-analyze","generatedAt":"2026-10-11T07:40:11.211Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-11T04:26:27.659Z","emptyReason":null},"description":"Use when the user asks to personalize their assistant, to use vardoger, or to analyze their OpenClaw conversation history. Runs the vardoger CLI to read past... Skill: vardoger — Analyze History Owner: dstrupl Summary: Use when the user asks to personalize their assistant, to use vardoger, or to analyze their OpenClaw conversation history. Runs the vardoger CLI to read past... Tags: latest:0.3.2 Version history: v0.3.2 | 2026-07-09T20:09:41.866Z | user Update the skill for vardoger 0.3.2 and current platform support. v0.3.1 | 2026-04-24T19:02:00.613Z | user Add explicit Apac","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1.2K downloads reported by the source. Last updated 10/11/2026.","installCommand":"clawhub skill install s170q73w5hdz7rfwgk64d9c4n985b7g5:vardoger-analyze","sourceUrl":"https://clawhub.ai/dstrupl/vardoger-analyze","homepage":"https://clawhub.ai/dstrupl/skills/vardoger-analyze","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/dstrupl/vardoger-analyze","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/dstrupl/skills/vardoger-analyze","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":61,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Use when the user asks to personalize their assistant, to use vardoger, or to analyze their OpenClaw conversation history. Runs the vardoger CLI to read past..."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-11T04:26:27.659Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T04:26:27.659Z","emptyReason":null},"stars":null,"forks":null,"downloads":1160,"packageName":null,"latestVersion":"0.3.2","tractionLabel":"1.2K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T04:26:27.646Z","emptyReason":null},"lastUpdatedAt":"2026-10-11T04:26:27.659Z","lastCrawledAt":"2026-10-11T04:26:27.646Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-12T04:26:27.646Z","lastVerifiedAt":null,"highlights":[{"version":"0.3.2","createdAt":"2026-07-09T20:09:41.866Z","changelog":"Update the skill for vardoger 0.3.2 and current platform support.","fileCount":3,"zipByteSize":3351},{"version":"0.3.1","createdAt":"2026-04-24T19:02:00.613Z","changelog":"Add explicit Apache-2.0 license","fileCount":3,"zipByteSize":3248},{"version":"0.3.0","createdAt":"2026-04-22T17:09:04.712Z","changelog":"Initial ClawHub release (vardoger 0.3.0)","fileCount":2,"zipByteSize":2134}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s170q73w5hdz7rfwgk64d9c4n985b7g5:vardoger-analyze","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dstrupl-vardoger-analyze/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dstrupl-vardoger-analyze/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dstrupl-vardoger-analyze/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-dstrupl-vardoger-analyze/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-dstrupl-vardoger-analyze/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-dstrupl-vardoger-analyze/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-11T07:40:11.211Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dstrupl-vardoger-analyze/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dstrupl-vardoger-analyze/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dstrupl-vardoger-analyze/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dstrupl-vardoger-analyze/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-10-11T04:26:27.659Z","emptyReason":null},"readme":"Skill: vardoger — Analyze History\n\nOwner: dstrupl\n\nSummary: Use when the user asks to personalize their assistant, to use vardoger, or to analyze their OpenClaw conversation history. Runs the vardoger CLI to read past...\n\nTags: latest:0.3.2\n\nVersion history:\n\nv0.3.2 | 2026-07-09T20:09:41.866Z | user\n\nUpdate the skill for vardoger 0.3.2 and current platform support.\n\nv0.3.1 | 2026-04-24T19:02:00.613Z | user\n\nAdd explicit Apache-2.0 license\n\nv0.3.0 | 2026-04-22T17:09:04.712Z | user\n\nInitial ClawHub release (vardoger 0.3.0)\n\nArchive index:\n\nArchive v0.3.2: 3 files, 3351 bytes\n\nFiles: skill-card.md (2359b), SKILL.md (4251b), _meta.json (135b)\n\nFile v0.3.2:SKILL.md\n\n---\nname: analyze\ndescription: \"Use when the user asks to personalize their assistant, to use vardoger, or to analyze their OpenClaw conversation history. Runs the vardoger CLI to read past conversations and generate tailored instructions.\"\nversion: \"0.3.2\"\nlicense: Apache-2.0\nhomepage: \"https://github.com/dstrupl/vardoger\"\nmetadata:\n  openclaw:\n    requires:\n      bins:\n        - vardoger\n---\n# Analyze conversation history and generate personalized instructions\n\nUse this skill to read your OpenClaw conversation history, extract behavioral patterns, and generate personalized instructions that help the assistant better understand your preferences and working style.\n\n## How it works\n\nvardoger prepares your conversation history in batches. You (the assistant) summarize each batch for behavioral signals, then synthesize all summaries into a personalization. vardoger writes the result.\n\n## Sandbox note (read before running any command)\n\nvardoger reads and writes files **outside** the current workspace:\n\n- Reads conversation history from the platform's session directory (e.g. `~/.codex/sessions/`, `~/.claude/projects/`, `~/.cursor/projects/`, `~/.openclaw/agents/`).\n- Writes a checkpoint state file to `~/.vardoger/state.json` (created on first run).\n- Writes the final personalization to the platform's rules file (e.g. `~/.codex/AGENTS.md`, `~/.claude/rules/vardoger.md`, `.cursor/rules/vardoger.md`, `~/.openclaw/skills/vardoger-personalization/SKILL.md`).\n\nWhen the host asks to approve a `vardoger` command, approve it with write access beyond the workspace. Otherwise the first `vardoger prepare` call will fail with `PermissionError: ... ~/.vardoger/state.tmp` because the sandbox blocks writes outside the current working directory.\n\n## Steps\n\n### 1. Verify vardoger is installed\n\n```bash\nif ! command -v vardoger >/dev/null 2>&1; then\n  cat <<'INSTALL_EOF'\nvardoger CLI is not installed.\n\nThis skill calls the vardoger CLI to read your conversation history and\nwrite a personalization file, so the CLI must be on PATH.\n\nInstall options:\n\n  # Recommended:\n  pipx install vardoger\n\n  # Or run without installing:\n  uvx vardoger --help\n\nIf you do not have pipx, see https://pipx.pypa.io/stable/installation/.\n\nProject page: https://github.com/dstrupl/vardoger\n\nAfter installing, re-run the personalization request.\nINSTALL_EOF\n  exit 1\nfi\n```\n\n### 2. Check if a refresh is needed\n\n```bash\nvardoger status --platform openclaw --json\n```\n\nIf the output shows `\"is_stale\": false`, tell the user their personalization is up to date and ask if they want to re-run anyway. If stale or never generated, continue with the analysis.\n\n### 3. Get batch metadata\n\n```bash\nvardoger prepare --platform openclaw\n```\n\nThis prints JSON like `{\"batches\": 3, \"total_conversations\": 29}`. Note the number of batches. Tell the user: \"Found N conversations in M batches. Analyzing...\"\n\n### 4. Summarize each batch\n\nFor each batch number from 1 to N, run:\n\n```bash\nvardoger prepare --platform openclaw --batch 1\n```\n\nThe output contains a summarization prompt and conversation data. Read the output carefully and produce a concise bullet-point summary of the behavioral signals you observe in that batch. Keep your summary for later.\n\nTell the user which batch you are processing: \"Analyzing batch 1 of N...\"\n\nRepeat for all batches (--batch 2, --batch 3, etc.).\n\n### 5. Get the synthesis prompt\n\n```bash\nvardoger prepare --platform openclaw --synthesize\n```\n\n### 6. Synthesize the personalization\n\nFollowing the synthesis prompt, combine all your batch summaries into a single personalization. The output should be clean markdown with actionable instructions for an AI assistant.\n\n### 7. Write the result\n\nPipe your personalization to vardoger:\n\n```bash\necho \"YOUR_PERSONALIZATION_HERE\" | vardoger write --platform openclaw --scope global\n```\n\nReplace `YOUR_PERSONALIZATION_HERE` with the actual personalization markdown you generated.\n\n### 8. Report to the user\n\nTell the user what was written and where. Mention they can ask you to re-run vardoger any time to update the personalization.\n\n## When to use\n\n- When the user asks to personalize their assistant\n- When the user asks to analyze their conversation history\n- When the user mentions \"vardoger\"\n\nFile v0.3.2:_meta.json\n\n{\n  \"ownerId\": \"kn72ffy5f0ytdypch2d4qxw1cd85b96j\",\n  \"slug\": \"vardoger-analyze\",\n  \"version\": \"0.3.2\",\n  \"publishedAt\": 1783627781866\n}\n\nFile v0.3.2:skill-card.md\n\n## Description:\n\nUse when the user asks to personalize their assistant, to use vardoger, or to analyze their OpenClaw conversation history.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dstrupl](https://clawhub.ai/user/dstrupl)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and assistant users use this skill to analyze OpenClaw conversation history with the vardoger CLI and generate persistent personalization instructions for assistant behavior.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill reads private conversation history.\n\nMitigation: Run it only after explicit user consent and only in trusted local environments.\n\nRisk: The skill writes persistent assistant rules that can change future assistant behavior.\n\nMitigation: Review the generated markdown before writing it and keep a rollback path for the previous rules file.\n\nRisk: The provided echo-based write example can mishandle generated markdown.\n\nMitigation: Use a safer stdin or file-based mechanism when passing personalization content to vardoger.\n\nRisk: The vardoger commands need filesystem access outside the workspace.\n\nMitigation: Use a pinned, reviewed vardoger version and grant expanded file access only for the specific command being run.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/dstrupl/skills/vardoger-analyze)\n- [dstrupl publisher profile](https://clawhub.ai/user/dstrupl)\n- [Vardoger project page](https://github.com/dstrupl/vardoger)\n- [pipx installation documentation](https://pipx.pypa.io/stable/installation/)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown personalization guidance with shell commands and concise status messages]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Requires the vardoger CLI and explicit user consent before reading conversation history or writing persistent assistant rules.]\n\n## Skill Version(s):\n\n0.3.2 (source: server release metadata and SKILL.md frontmatter)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nArchive v0.3.1: 3 files, 3248 bytes\n\nFiles: skill-card.md (2202b), SKILL.md (4251b), _meta.json (135b)\n\nFile v0.3.1:SKILL.md\n\n---\nname: analyze\ndescription: \"Use when the user asks to personalize their assistant, to use vardoger, or to analyze their OpenClaw conversation history. Runs the vardoger CLI to read past conversations and generate tailored instructions.\"\nversion: \"0.3.1\"\nlicense: Apache-2.0\nhomepage: \"https://github.com/dstrupl/vardoger\"\nmetadata:\n  openclaw:\n    requires:\n      bins:\n        - vardoger\n---\n# Analyze conversation history and generate personalized instructions\n\nUse this skill to read your OpenClaw conversation history, extract behavioral patterns, and generate personalized instructions that help the assistant better understand your preferences and working style.\n\n## How it works\n\nvardoger prepares your conversation history in batches. You (the assistant) summarize each batch for behavioral signals, then synthesize all summaries into a personalization. vardoger writes the result.\n\n## Sandbox note (read before running any command)\n\nvardoger reads and writes files **outside** the current workspace:\n\n- Reads conversation history from the platform's session directory (e.g. `~/.codex/sessions/`, `~/.claude/projects/`, `~/.cursor/projects/`, `~/.openclaw/agents/`).\n- Writes a checkpoint state file to `~/.vardoger/state.json` (created on first run).\n- Writes the final personalization to the platform's rules file (e.g. `~/.codex/AGENTS.md`, `~/.claude/rules/vardoger.md`, `.cursor/rules/vardoger.md`, `~/.openclaw/skills/vardoger-personalization/SKILL.md`).\n\nWhen the host asks to approve a `vardoger` command, approve it with write access beyond the workspace. Otherwise the first `vardoger prepare` call will fail with `PermissionError: ... ~/.vardoger/state.tmp` because the sandbox blocks writes outside the current working directory.\n\n## Steps\n\n### 1. Verify vardoger is installed\n\n```bash\nif ! command -v vardoger >/dev/null 2>&1; then\n  cat <<'INSTALL_EOF'\nvardoger CLI is not installed.\n\nThis skill calls the vardoger CLI to read your conversation history and\nwrite a personalization file, so the CLI must be on PATH.\n\nInstall options:\n\n  # Recommended:\n  pipx install vardoger\n\n  # Or run without installing:\n  uvx vardoger --help\n\nIf you do not have pipx, see https://pipx.pypa.io/stable/installation/.\n\nProject page: https://github.com/dstrupl/vardoger\n\nAfter installing, re-run the personalization request.\nINSTALL_EOF\n  exit 1\nfi\n```\n\n### 2. Check if a refresh is needed\n\n```bash\nvardoger status --platform openclaw --json\n```\n\nIf the output shows `\"is_stale\": false`, tell the user their personalization is up to date and ask if they want to re-run anyway. If stale or never generated, continue with the analysis.\n\n### 3. Get batch metadata\n\n```bash\nvardoger prepare --platform openclaw\n```\n\nThis prints JSON like `{\"batches\": 3, \"total_conversations\": 29}`. Note the number of batches. Tell the user: \"Found N conversations in M batches. Analyzing...\"\n\n### 4. Summarize each batch\n\nFor each batch number from 1 to N, run:\n\n```bash\nvardoger prepare --platform openclaw --batch 1\n```\n\nThe output contains a summarization prompt and conversation data. Read the output carefully and produce a concise bullet-point summary of the behavioral signals you observe in that batch. Keep your summary for later.\n\nTell the user which batch you are processing: \"Analyzing batch 1 of N...\"\n\nRepeat for all batches (--batch 2, --batch 3, etc.).\n\n### 5. Get the synthesis prompt\n\n```bash\nvardoger prepare --platform openclaw --synthesize\n```\n\n### 6. Synthesize the personalization\n\nFollowing the synthesis prompt, combine all your batch summaries into a single personalization. The output should be clean markdown with actionable instructions for an AI assistant.\n\n### 7. Write the result\n\nPipe your personalization to vardoger:\n\n```bash\necho \"YOUR_PERSONALIZATION_HERE\" | vardoger write --platform openclaw --scope global\n```\n\nReplace `YOUR_PERSONALIZATION_HERE` with the actual personalization markdown you generated.\n\n### 8. Report to the user\n\nTell the user what was written and where. Mention they can ask you to re-run vardoger any time to update the personalization.\n\n## When to use\n\n- When the user asks to personalize their assistant\n- When the user asks to analyze their conversation history\n- When the user mentions \"vardoger\"\n\nFile v0.3.1:_meta.json\n\n{\n  \"ownerId\": \"kn72ffy5f0ytdypch2d4qxw1cd85b96j\",\n  \"slug\": \"vardoger-analyze\",\n  \"version\": \"0.3.1\",\n  \"publishedAt\": 1777057320613\n}\n\nFile v0.3.1:skill-card.md\n\n## Description: <br>\nRuns the vardoger CLI to analyze OpenClaw conversation history and generate tailored assistant personalization instructions. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[dstrupl](https://clawhub.ai/user/dstrupl) <br>\n\n### License/Terms of Use: <br>\nApache-2.0 <br>\n\n\n## Use Case: <br>\nDevelopers and OpenClaw users use this skill to inspect prior assistant conversations, summarize behavioral preferences, and generate persistent personalization instructions for future assistant sessions. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: The skill reads broad past conversation history. <br>\nMitigation: Install and run it only when the user wants conversation-history analysis, verify the vardoger CLI source and version, and approve only expected vardoger commands. <br>\nRisk: The skill writes persistent global assistant personalization outside the current workspace. <br>\nMitigation: Review the generated markdown before keeping it and remove or edit the personalization file if it captures sensitive or unwanted instructions. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/dstrupl/vardoger-analyze) <br>\n- [vardoger project page](https://github.com/dstrupl/vardoger) <br>\n- [pipx installation documentation](https://pipx.pypa.io/stable/installation/.) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, markdown, shell commands, configuration, guidance] <br>\n**Output Format:** [Markdown personalization guidance with inline shell commands and JSON command output] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Requires the vardoger CLI and may read conversation history and write persistent assistant personalization outside the current workspace.] <br>\n\n## Skill Version(s): <br>\n0.3.1 (source: frontmatter and server release metadata) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v0.3.0: 2 files, 2134 bytes\n\nFiles: SKILL.md (4231b), _meta.json (135b)\n\nFile v0.3.0:SKILL.md\n\n---\nname: analyze\ndescription: \"Use when the user asks to personalize their assistant, to use vardoger, or to analyze their OpenClaw conversation history. Runs the vardoger CLI to read past conversations and generate tailored instructions.\"\nversion: \"0.3.0\"\nhomepage: \"https://github.com/dstrupl/vardoger\"\nmetadata:\n  openclaw:\n    requires:\n      bins:\n        - vardoger\n---\n# Analyze conversation history and generate personalized instructions\n\nUse this skill to read your OpenClaw conversation history, extract behavioral patterns, and generate personalized instructions that help the assistant better understand your preferences and working style.\n\n## How it works\n\nvardoger prepares your conversation history in batches. You (the assistant) summarize each batch for behavioral signals, then synthesize all summaries into a personalization. vardoger writes the result.\n\n## Sandbox note (read before running any command)\n\nvardoger reads and writes files **outside** the current workspace:\n\n- Reads conversation history from the platform's session directory (e.g. `~/.codex/sessions/`, `~/.claude/projects/`, `~/.cursor/projects/`, `~/.openclaw/agents/`).\n- Writes a checkpoint state file to `~/.vardoger/state.json` (created on first run).\n- Writes the final personalization to the platform's rules file (e.g. `~/.codex/AGENTS.md`, `~/.claude/rules/vardoger.md`, `.cursor/rules/vardoger.md`, `~/.openclaw/skills/vardoger-personalization/SKILL.md`).\n\nWhen the host asks to approve a `vardoger` command, approve it with write access beyond the workspace. Otherwise the first `vardoger prepare` call will fail with `PermissionError: ... ~/.vardoger/state.tmp` because the sandbox blocks writes outside the current working directory.\n\n## Steps\n\n### 1. Verify vardoger is installed\n\n```bash\nif ! command -v vardoger >/dev/null 2>&1; then\n  cat <<'INSTALL_EOF'\nvardoger CLI is not installed.\n\nThis skill calls the vardoger CLI to read your conversation history and\nwrite a personalization file, so the CLI must be on PATH.\n\nInstall options:\n\n  # Recommended:\n  pipx install vardoger\n\n  # Or run without installing:\n  uvx vardoger --help\n\nIf you do not have pipx, see https://pipx.pypa.io/stable/installation/.\n\nProject page: https://github.com/dstrupl/vardoger\n\nAfter installing, re-run the personalization request.\nINSTALL_EOF\n  exit 1\nfi\n```\n\n### 2. Check if a refresh is needed\n\n```bash\nvardoger status --platform openclaw --json\n```\n\nIf the output shows `\"is_stale\": false`, tell the user their personalization is up to date and ask if they want to re-run anyway. If stale or never generated, continue with the analysis.\n\n### 3. Get batch metadata\n\n```bash\nvardoger prepare --platform openclaw\n```\n\nThis prints JSON like `{\"batches\": 3, \"total_conversations\": 29}`. Note the number of batches. Tell the user: \"Found N conversations in M batches. Analyzing...\"\n\n### 4. Summarize each batch\n\nFor each batch number from 1 to N, run:\n\n```bash\nvardoger prepare --platform openclaw --batch 1\n```\n\nThe output contains a summarization prompt and conversation data. Read the output carefully and produce a concise bullet-point summary of the behavioral signals you observe in that batch. Keep your summary for later.\n\nTell the user which batch you are processing: \"Analyzing batch 1 of N...\"\n\nRepeat for all batches (--batch 2, --batch 3, etc.).\n\n### 5. Get the synthesis prompt\n\n```bash\nvardoger prepare --platform openclaw --synthesize\n```\n\n### 6. Synthesize the personalization\n\nFollowing the synthesis prompt, combine all your batch summaries into a single personalization. The output should be clean markdown with actionable instructions for an AI assistant.\n\n### 7. Write the result\n\nPipe your personalization to vardoger:\n\n```bash\necho \"YOUR_PERSONALIZATION_HERE\" | vardoger write --platform openclaw --scope global\n```\n\nReplace `YOUR_PERSONALIZATION_HERE` with the actual personalization markdown you generated.\n\n### 8. Report to the user\n\nTell the user what was written and where. Mention they can ask you to re-run vardoger any time to update the personalization.\n\n## When to use\n\n- When the user asks to personalize their assistant\n- When the user asks to analyze their conversation history\n- When the user mentions \"vardoger\"\n\nFile v0.3.0:_meta.json\n\n{\n  \"ownerId\": \"kn72ffy5f0ytdypch2d4qxw1cd85b96j\",\n  \"slug\": \"vardoger-analyze\",\n  \"version\": \"0.3.0\",\n  \"publishedAt\": 1776877744712\n}","readmeExcerpt":"Skill: vardoger — Analyze History Owner: dstrupl Summary: Use when the user asks to personalize their assistant, to use vardoger, or to analyze their OpenClaw conversation history. Runs the vardoger CLI to read past... Tags: latest:0.3.2 Version history: v0.3.2 | 2026-07-09T20:09:41.866Z | user Update the skill for vardoger 0.3.2 and current platform support. v0.3.1 | 2026-04-24T19:02:00.613Z | user Add explicit Apac","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"if ! command -v vardoger >/dev/null 2>&1; then\n  cat <<'INSTALL_EOF'\nvardoger CLI is not installed.\n\nThis skill calls the vardoger CLI to read your conversation history and\nwrite a personalization file, so the CLI must be on PATH.\n\nInstall options:\n\n  # Recommended:\n  pipx install vardoger\n\n  # Or run without installing:\n  uvx vardoger --help\n\nIf you do not have pipx, see https://pipx.pypa.io/stable/installation/.\n\nProject page: https://github.com/dstrupl/vardoger\n\nAfter installing, re-run the personalization request.\nINSTALL_EOF\n  exit 1\nfi"},{"language":"bash","snippet":"vardoger status --platform openclaw --json"},{"language":"bash","snippet":"vardoger prepare --platform openclaw"},{"language":"bash","snippet":"vardoger prepare --platform openclaw --batch 1"},{"language":"bash","snippet":"vardoger prepare --platform openclaw --synthesize"},{"language":"bash","snippet":"echo \"YOUR_PERSONALIZATION_HERE\" | vardoger write --platform openclaw --scope global"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: analyze\ndescription: \"Use when the user asks to personalize their assistant, to use vardoger, or to analyze their OpenClaw conversation history. Runs the vardoger CLI to read past conversations and generate tailored instructions.\"\nversion: \"0.3.2\"\nlicense: Apache-2.0\nhomepage: \"https://github.com/dstrupl/vardoger\"\nmetadata:\n  openclaw:\n    requires:\n      bins:\n        - vardoger\n---\n# Analyze conversation history and generate personalized instructions\n\nUse this skill to read your OpenClaw conversation history, extract behavioral patterns, and generate personalized instructions that help the assistant better understand your preferences and working style.\n\n## How it works\n\nvardoger prepares your conversation history in batches. You (the assistant) summarize each batch for behavioral signals, then synthesize all summaries into a personalization. vardoger writes the result.\n\n## Sandbox note (read before running any command)\n\nvardoger reads and writes files **outside** the current workspace:\n\n- Reads conversation history from the platform's session directory (e.g. `~/.codex/sessions/`, `~/.claude/projects/`, `~/.cursor/projects/`, `~/.openclaw/agents/`).\n- Writes a checkpoint state file to `~/.vardoger/state.json` (created on first run).\n- Writes the final personalization to the platform's rules file (e.g. `~/.codex/AGENTS.md`, `~/.claude/rules/vardoger.md`, `.cursor/rules/vardoger.md`, `~/.openclaw/skills/vardoger-personalization/SKILL.md`).\n\nWhen the host asks to approve a `vardoger` command, approve it with write access beyond the workspace. Otherwise the first `vardoger prepare` call will fail with `PermissionError: ... ~/.vardoger/state.tmp` because the sandbox blocks writes outside the current working directory.\n\n## Steps\n\n### 1. Verify vardoger is installed\n\n```bash\nif ! command -v vardoger >/dev/null 2>&1; then\n  cat <<'INSTALL_EOF'\nvardoger CLI is not installed.\n\nThis skill calls the vardoger CLI to read your conversation history and\nwrite a personalization file, so the CLI must be on PATH.\n\nInstall options:\n\n  # Recommended:\n  pipx install vardoger\n\n  # Or run without installing:\n  uvx vardoger --help\n\nIf you do not have pipx, see https://pipx.pypa.io/stable/installation/.\n\nProject page: https://github.com/dstrupl/vardoger\n\nAfter installing, re-run the personalization request.\nINSTALL_EOF\n  exit 1\nfi\n```\n\n### 2. Check if a refresh is needed\n\n```bash\nvardoger status --platform openclaw --json\n```\n\nIf the output shows `\"is_stale\": false`, tell the user their personalization is up to date and ask if they want to re-run anyway. If stale or never generated, continue with the analysis.\n\n### 3. Get batch metadata\n\n```bash\nvardoger prepare --platform openclaw\n```\n\nThis prints JSON like `{\"batches\": 3, \"total_conversations\": 29}`. Note the number of batches. Tell the user: \"Found N conversations in M batches. Analyzing...\"\n\n### 4. Summarize each batch\n\nFor each batch number from 1 to N, run:\n\n```bash\nvardoger prepare --platform openclaw --"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn72ffy5f0ytdypch2d4qxw1cd85b96j\",\n  \"slug\": \"vardoger-analyze\",\n  \"version\": \"0.3.2\",\n  \"publishedAt\": 1783627781866\n}"},{"path":"skill-card.md","content":"## Description:\n\nUse when the user asks to personalize their assistant, to use vardoger, or to analyze their OpenClaw conversation history.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dstrupl](https://clawhub.ai/user/dstrupl)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and assistant users use this skill to analyze OpenClaw conversation history with the vardoger CLI and generate persistent personalization instructions for assistant behavior.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill reads private conversation history.\n\nMitigation: Run it only after explicit user consent and only in trusted local environments.\n\nRisk: The skill writes persistent assistant rules that can change future assistant behavior.\n\nMitigation: Review the generated markdown before writing it and keep a rollback path for the previous rules file.\n\nRisk: The provided echo-based write example can mishandle generated markdown.\n\nMitigation: Use a safer stdin or file-based mechanism when passing personalization content to vardoger.\n\nRisk: The vardoger commands need filesystem access outside the workspace.\n\nMitigation: Use a pinned, reviewed vardoger version and grant expanded file access only for the specific command being run.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/dstrupl/skills/vardoger-analyze)\n- [dstrupl publisher profile](https://clawhub.ai/user/dstrupl)\n- [Vardoger project page](https://github.com/dstrupl/vardoger)\n- [pipx installation documentation](https://pipx.pypa.io/stable/installation/)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown personalization guidance with shell commands and concise status messages]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Requires the vardoger CLI and explicit user consent before reading conversation history or writing persistent assistant rules.]\n\n## Skill Version(s):\n\n0.3.2 (source: server release metadata and SKILL.md frontmatter)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment."}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Use when the user asks to personalize their assistant, to use vardoger, or to analyze their OpenClaw conversation history. Runs the vardoger CLI to read past... Skill: vardoger — Analyze History Owner: dstrupl Summary: Use when the user asks to personalize their assistant, to use vardoger, or to analyze their OpenClaw conversation history. Runs the vardoger CLI to read past... Tags: latest:0.3.2 Version history: v0.3.2 | 2026-07-09T20:09:41.866Z | user Update the skill for vardoger 0.3.2 and current platform support. v0.3.1 | 2026-04-24T19:02:00.613Z | user Add explicit Apac","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1013,"uniquenessScore":49,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-11T04:26:27.659Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-11T04:26:27.659Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-11T07:40:11.211Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}