# Send Clawboard to your agent Use the source page and any available docs to guide the install because the item currently does not return a direct package file. ## Fast path - Open the source page via Open source listing. - If you can obtain the package, extract it into a folder your agent can access. - Paste one of the prompts below and point your agent at the source page and extracted files. ## Suggested prompts ### New install ```text I tried to install a skill package from Yavira, but the item currently does not return a direct package file. Inspect the source page and any extracted docs, then tell me what you can confirm and any manual steps still required. ``` ### Upgrade existing ```text I tried to upgrade a skill package from Yavira, but the item currently does not return a direct package file. Compare the source page and any extracted docs with my current installation, then summarize what changed and what manual follow-up I still need. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "clawboard", "name": "Clawboard", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/sirouk/clawboard", "canonicalUrl": "https://clawhub.ai/sirouk/clawboard", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/clawboard", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=clawboard", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "SKILL.md", "scripts/setup-openclaw-memory-backup.sh", "scripts/backup_openclaw_curated_memories.sh", "scripts/setup-openclaw-local-memory.sh", "scripts/export_clawboard_backup.py", "agents/openai.yaml" ], "downloadMode": "manual_only", "sourceHealth": { "source": "tencent", "slug": "clawboard", "status": "source_issue", "reason": "not_found", "recommendedAction": "review_source", "checkedAt": "2026-05-01T16:03:58.665Z", "expiresAt": "2026-05-02T16:03:58.665Z", "httpStatus": 404, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=clawboard", "contentType": "text/plain", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=clawboard", "contentDisposition": null, "redirectLocation": null, "bodySnippet": null, "slug": "clawboard" }, "scope": "item", "summary": "Known item issue.", "detail": "This item's current download entry is known to bounce back to a listing or homepage instead of returning a package file.", "primaryActionLabel": "Open source listing", "primaryActionHref": "https://clawhub.ai/sirouk/clawboard" }, "validation": { "installChecklist": [ "Open the source listing and confirm there is a real package or setup artifact available.", "Review SKILL.md before asking your agent to continue.", "Treat this source as manual setup until the upstream download flow is fixed." ], "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/clawboard", "downloadUrl": "https://openagent3.xyz/downloads/clawboard", "agentUrl": "https://openagent3.xyz/skills/clawboard/agent", "manifestUrl": "https://openagent3.xyz/skills/clawboard/agent.json", "briefUrl": "https://openagent3.xyz/skills/clawboard/agent.md" } } ``` ## Documentation ### Status ClawHub: not available yet. Install path today: scripted bootstrap or manual repo install. If OpenClaw is missing and user wants Chutes provider, start with add_chutes.sh after creating a https://chutes.ai account. ### Current Architecture Snapshot web (Next.js): http://localhost:3010 api (FastAPI + SQLite): http://localhost:8010 classifier (async stage-2 worker): topic/task classification loop qdrant (vector index): dense retrieval backend on internal Docker network clawboard-logger plugin: stage-1 firehose logging + response-time context extension Retrieval/search stack: Dense vectors + BM25 + lexical matching Reciprocal rank fusion + reranking Qdrant primary, SQLite embeddings mirror/fallback ### Goal Get a user to a working Clawboard install where: Clawboard web/api/classifier are running. clawboard-logger plugin is installed and enabled. Token flow is configured correctly (required for writes + non-localhost reads). OpenClaw gateway is restarted and logging into Clawboard. ### Hard Rules (Repo vs Installed Skill) Repo copy (version controlled): $CLAWBOARD_DIR/skills/clawboard Installed skill path (what OpenClaw reads): $HOME/.openclaw/skills/clawboard Default install mode is symlink (~/.openclaw/skills/clawboard -> $CLAWBOARD_DIR/skills/clawboard). Detect mode deterministically at runtime: if [ -L "$HOME/.openclaw/skills/clawboard" ]; then echo "symlink" else echo "copy" fi In symlink mode (default), repo edits are immediately visible to OpenClaw. In copy mode, repo edits do not update OpenClaw until you sync/copy again. After skill file changes (SKILL.md, agents/, references/, scripts/), sync into OpenClaw: cd "$CLAWBOARD_DIR" bash scripts/sync_openclaw_skill.sh --to-openclaw --apply --force If you changed files under ~/.openclaw/skills/clawboard while in copy mode, sync them back before committing: cd "$CLAWBOARD_DIR" bash scripts/sync_openclaw_skill.sh --to-repo --apply ### Workspace + Runtime Assumptions (for coding tasks) Typical repo locations for Clawboard code: ~/[agent_name]/clawboard ~/[agent_name]/projects/clawboard For scripted installs, bootstrap auto-detects OpenClaw workspace conventions and usually lands in one of those layouts. When asked to work on Clawboard frontend/backend, prefer the active git repo copy under those locations, not ~/.openclaw/skills/*. After typical bootstrap, assume Docker services are running: CLAWBOARD_WEB_HOT_RELOAD=1: web-dev is used for Next.js hot reload (web is stopped). CLAWBOARD_WEB_HOT_RELOAD=0: production-style web service is used. Fast runtime check commands: docker compose ps echo "$CLAWBOARD_WEB_HOT_RELOAD" (or read from $CLAWBOARD_DIR/.env) curl -s http://localhost:8010/api/health Parity rules while editing: Skill path mode should be checked first (test -L ~/.openclaw/skills/clawboard). If symlink mode: edit repo files directly ($CLAWBOARD_DIR/skills/clawboard/**). If copy mode: sync to OpenClaw after edits (bash scripts/sync_openclaw_skill.sh --to-openclaw --apply --force). Logger plugin edits (extensions/clawboard-logger/**) must be reinstalled/enabled in OpenClaw: openclaw plugins install -l "$CLAWBOARD_DIR/extensions/clawboard-logger" openclaw plugins enable clawboard-logger ~/.openclaw/skills/clawboard-logger is optional and may not exist by default. If your environment has it, keep it synced with its repo copy explicitly. ### 1) Quick Scripted Install (recommended) Use: curl -fsSL https://raw.githubusercontent.com/sirouk/clawboard/main/scripts/bootstrap_openclaw.sh | bash What the script does: Clones/updates repo by auto-detecting your OpenClaw workspace. If it finds a projects/ (or project/) convention, it installs there; otherwise it falls back to ~/clawboard. Override with --dir , CLAWBOARD_DIR=, or CLAWBOARD_PARENT_DIR= (installs to /clawboard). Generates a token if missing and writes .env with CLAWBOARD_TOKEN. Detects browser access URLs (Tailscale if available, else localhost) and writes .env CLAWBOARD_PUBLIC_API_BASE and CLAWBOARD_PUBLIC_WEB_URL. Builds and starts Docker services. Ensures web + api + classifier + qdrant are running. Installs skill at $HOME/.openclaw/skills/clawboard (default: symlink to repo skill; optional copy mode). Installs/enables clawboard-logger plugin. Writes plugin config (baseUrl, token, enabled) via openclaw config set. Ensures OpenClaw OpenResponses endpoint is enabled (POST /v1/responses) for attachments. Restarts OpenClaw gateway. Sets /api/config title + integration level. If openclaw CLI is not installed yet, the script still deploys Clawboard and prints follow-up instructions. It now also offers to run the Chutes fast path automatically when openclaw is missing. Useful flags: --integration-level full|write|manual (default write) --no-backfill (same as manual) --api-url http://localhost:8010 --web-url http://localhost:3010 --web-hot-reload / --no-web-hot-reload --public-api-base https://api.example.com --public-web-url https://clawboard.example.com --token --title "" --skill-symlink (default) --skill-copy (fallback if you do not want symlink mode) --update ### 2) Human Manual Install Prereqs: git, docker (+ compose), openclaw CLI Docker Desktop on macOS Steps: Clone repo: CLAWBOARD_PARENT_DIR="${CLAWBOARD_PARENT_DIR:-}" CLAWBOARD_DIR="${CLAWBOARD_DIR:-${CLAWBOARD_PARENT_DIR:+$CLAWBOARD_PARENT_DIR/clawboard}}" CLAWBOARD_DIR="${CLAWBOARD_DIR:-$HOME/clawboard}" git clone https://github.com/sirouk/clawboard "$CLAWBOARD_DIR" cd "$CLAWBOARD_DIR" Create token and env: cp .env.example .env openssl rand -hex 32 Set CLAWBOARD_TOKEN= in $CLAWBOARD_DIR/.env. Set CLAWBOARD_PUBLIC_API_BASE= in $CLAWBOARD_DIR/.env. Optional: set CLAWBOARD_PUBLIC_WEB_URL= in $CLAWBOARD_DIR/.env. Examples: local: http://localhost:8010 tailscale: http://100.x.y.z:8010 custom domain: https://api.example.com Start Clawboard: docker compose up -d --build Install skill: mkdir -p "$HOME/.openclaw/skills" rm -rf "$HOME/.openclaw/skills/clawboard" ln -s "$CLAWBOARD_DIR/skills/clawboard" "$HOME/.openclaw/skills/clawboard" If you explicitly want copy mode instead of symlink: mkdir -p "$HOME/.openclaw/skills" rm -rf "$HOME/.openclaw/skills/clawboard" cp -R "$CLAWBOARD_DIR/skills/clawboard" "$HOME/.openclaw/skills/clawboard" If user keeps skills elsewhere, use that path instead of $HOME/.openclaw/skills. Install + enable logger plugin: openclaw plugins install -l "$CLAWBOARD_DIR/extensions/clawboard-logger" openclaw plugins enable clawboard-logger Configure plugin (writes into OpenClaw config): # contextMode options: auto | cheap | full | patient openclaw config set plugins.entries.clawboard-logger.config --json '{ "baseUrl":"http://localhost:8010", "token":"YOUR_TOKEN", "enabled":true, "contextMode":"auto", "contextFallbackMode":"cheap", "contextFetchTimeoutMs":1200, "contextTotalBudgetMs":2200, "contextMaxChars":2200 }' openclaw config set plugins.entries.clawboard-logger.enabled --json true Enable OpenResponses (recommended for attachments): openclaw config set gateway.http.endpoints.responses.enabled --json true Restart gateway: openclaw gateway restart Notes: OpenClaw config is stored at $HOME/.openclaw/openclaw.json. Keep plugin token aligned with API server CLAWBOARD_TOKEN. ### 3) Agentic Install (copy/paste into OpenClaw) Use this exact prompt: Install Clawboard for me end-to-end. ClawHub is not available yet, so choose one of these: 1) Scripted install (preferred): - Run: curl -fsSL https://raw.githubusercontent.com/sirouk/clawboard/main/scripts/bootstrap_openclaw.sh | bash 2) Manual install: - Clone repo to \`$CLAWBOARD_DIR\` - Create \`CLAWBOARD_TOKEN\` and write \`$CLAWBOARD_DIR/.env\` - Set \`CLAWBOARD_PUBLIC_API_BASE\` (local/Tailscale/custom domain) in \`$CLAWBOARD_DIR/.env\` - Set \`CLAWBOARD_PUBLIC_WEB_URL\` (local/Tailscale/custom domain) in \`$CLAWBOARD_DIR/.env\` - Start docker compose - Symlink skill to $HOME/.openclaw/skills/clawboard (default; copy only if explicitly requested) - Install/enable clawboard-logger plugin - Set plugin config (baseUrl + token) in OpenClaw config - Restart gateway After install, validate: - http://localhost:8010/api/health - http://localhost:8010/api/config - plugin enabled + gateway restarted - send one test message and confirm it appears in Clawboard logs Ask me before choosing local vs Tailscale API base URL. Security reminder for all methods: CLAWBOARD_TOKEN is required for all writes and all non-localhost reads. Localhost reads can run tokenless (read-only default posture). Keep network boundaries strict (localhost/firewall/Tailscale ACLs; avoid Funnel/public exposure unless explicitly intended). Compose defaults keep vector/db/cache services off host ports; use the API as the supported read/write/delete interface. ### Validation Checklist Run: curl -s http://localhost:8010/api/health curl -s http://localhost:8010/api/config openclaw plugins list | rg clawboard-logger curl -s "http://localhost:8010/api/search?q=continuity" Expect: API health is ok. tokenRequired is true. tokenConfigured is true. Logger plugin is enabled. Search endpoint returns mode/details (and will include qdrant mode when vectors are available). New OpenClaw message appears in Clawboard Logs. ### Optional Helpers Local memory setup script: $CLAWBOARD_DIR/skills/clawboard/scripts/setup-openclaw-local-memory.sh Curated memory cloud backup (GitHub private repo): Setup (interactive): $CLAWBOARD_DIR/skills/clawboard/scripts/setup-openclaw-memory-backup.sh Backup run (safe for automation; commits/pushes only when changed): $CLAWBOARD_DIR/skills/clawboard/scripts/backup_openclaw_curated_memories.sh Includes optional full Clawboard state export (config/topics/tasks/logs + optional attachments). Stores config at: $HOME/.openclaw/credentials/clawboard-memory-backup.json (chmod 600) Chutes provider helper: curl -fsSL https://raw.githubusercontent.com/sirouk/clawboard/main/inference-providers/add_chutes.sh | bash ### References references/clawboard-api.md references/openclaw-hooks.md references/openclaw-memory-local.md ## Trust - Source: tencent - Verification: Indexed source record - Publisher: sirouk - Version: 1.0.1 ## Source health - Status: source_issue - Known item issue. - This item's current download entry is known to bounce back to a listing or homepage instead of returning a package file. - Health scope: item - Reason: not_found - Checked at: 2026-05-01T16:03:58.665Z - Expires at: 2026-05-02T16:03:58.665Z - Recommended action: Open source listing ## Links - [Detail page](https://openagent3.xyz/skills/clawboard) - [Send to Agent page](https://openagent3.xyz/skills/clawboard/agent) - [JSON manifest](https://openagent3.xyz/skills/clawboard/agent.json) - [Markdown brief](https://openagent3.xyz/skills/clawboard/agent.md) - [Download page](https://openagent3.xyz/downloads/clawboard)