diff --git a/.agents/skills/archive/SKILL.md b/.agents/skills/archive/SKILL.md index 5444904..b5cdc9a 100644 --- a/.agents/skills/archive/SKILL.md +++ b/.agents/skills/archive/SKILL.md @@ -27,8 +27,23 @@ Capture, index, and reuse project knowledge across sessions. 1. Read `.archive/MEMORY.md` — check for related existing archives 2. Create `.archive/YYYY-MM-DD/` directory if needed -3. Write markdown file with YAML frontmatter (see `references/TEMPLATE.md`) -4. **Update `.archive/MEMORY.md`**: add one-line entry under the right category +3. Write markdown file with YAML frontmatter: + ```yaml + --- + tags: [ecs, deploy, fargate] + category: infrastructure + related: [../2025-03-10/ecs-service-fix.md] + --- + ## ECS Task Definition Update + **Problem:** Deployment failed with "essential container exited" + **Fix:** Added `healthCheck` to task definition with 30s start period + **Command:** `aws ecs update-service --force-new-deployment` + ``` +4. **Update `.archive/MEMORY.md`**: add one-line entry under the right category: + ``` + ### infrastructure + - [ECS task definition fix](2025-04-28/ecs-task-definition.md) — healthCheck start period + ``` 5. If related archives exist, add `related` field in frontmatter ## Lookup Workflow diff --git a/.agents/skills/seo-geo/SKILL.md b/.agents/skills/seo-geo/SKILL.md index 7d10530..8303005 100644 --- a/.agents/skills/seo-geo/SKILL.md +++ b/.agents/skills/seo-geo/SKILL.md @@ -7,51 +7,19 @@ description: SEO & GEO (Generative Engine Optimization) for websites. Analyze ke Comprehensive SEO and GEO (Generative Engine Optimization) for websites. Optimize for both traditional search engines (Google, Bing) and AI search engines (ChatGPT, Perplexity, Gemini, Copilot, Claude). -## Quick Reference - -**GEO = Generative Engine Optimization** - Optimizing content to be cited by AI search engines. - -**Key Insight:** AI search engines don't rank pages - they **cite sources**. Being cited is the new "ranking #1". - ## Workflow ### Step 1: Website Audit Get the target URL and analyze current SEO/GEO status. -**Basic SEO Audit (Free):** ```bash python3 scripts/seo_audit.py "https://example.com" -``` -**Use this for**: Quick technical SEO check (title, meta, H1, robots, sitemap, load time). No API needed. - ---- - -**Check Meta Tags:** -```bash curl -sL "https://example.com" | grep -E "|<meta name=\"description\"|<meta property=\"og:|application/ld\+json" | head -20 -``` - -**Use this for**: Quick check of essential meta tags and schema markup on any webpage. - ---- - -**Check robots.txt:** -```bash curl -s "https://example.com/robots.txt" -``` - -**Use this for**: Verify which bots are allowed/blocked. Critical for ensuring AI search engines can crawl your site. - ---- - -**Check sitemap:** -```bash curl -s "https://example.com/sitemap.xml" | head -50 ``` -**Use this for**: Verify sitemap structure and ensure all important pages are included for search engine discovery. - **Verify AI Bot Access:** ``` # These bots should be allowed in robots.txt: diff --git a/.agents/skills/twitter/SKILL.md b/.agents/skills/twitter/SKILL.md index b313797..102dfff 100644 --- a/.agents/skills/twitter/SKILL.md +++ b/.agents/skills/twitter/SKILL.md @@ -92,6 +92,14 @@ python3 scripts/search_tweets.py "AI filter:media" python3 scripts/search_tweets.py "AI min_faves:1000" ``` +## Error Handling + +| Error | Cause | Fix | +|---|---|---| +| `401 Unauthorized` | Missing or invalid API key | Verify `TWITTERAPI_API_KEY` is set in `~/.zshrc` and re-source | +| `429 Too Many Requests` | Rate limit exceeded | Wait 60 seconds and retry | +| Empty response / `user not found` | Suspended or non-existent account | Verify the username exists on twitter.com | + ## API: twitterapi.io - Base URL: https://api.twitterapi.io/twitter - Auth: X-API-Key header diff --git a/.github/workflows/skill-review.yml b/.github/workflows/skill-review.yml new file mode 100644 index 0000000..f0ab779 --- /dev/null +++ b/.github/workflows/skill-review.yml @@ -0,0 +1,13 @@ +name: Skill Review +on: + pull_request: + paths: ['**/SKILL.md'] +jobs: + review: + runs-on: ubuntu-latest + permissions: + pull-requests: write + contents: read + steps: + - uses: actions/checkout@v4 + - uses: tesslio/skill-review@22e928dd837202b2b1d1397e0114c92e0fae5ead # main diff --git a/skills/awn/SKILL.md b/skills/awn/SKILL.md index 0c4addb..fd5a905 100644 --- a/skills/awn/SKILL.md +++ b/skills/awn/SKILL.md @@ -1,6 +1,6 @@ --- name: awn -description: "AWN CLI — standalone binary for world-scoped P2P messaging between AI agents. Ed25519-signed, zero runtime dependencies." +description: "Send and receive P2P messages between AI agents, join agent worlds, discover peers, and call world actions via the AWN CLI. Ed25519-signed, zero runtime dependencies. Use when the user wants to send messages to other agents, set up peer-to-peer agent communication, join or leave agent worlds, discover agents on the network, or work with the AWN protocol." version: "1.6.0" metadata: openclaw: @@ -23,112 +23,30 @@ curl -fsSL https://raw.githubusercontent.com/ReScienceLab/agent-world-network/ma Installs the latest release to `~/.local/bin/awn`. Set `INSTALL_DIR` to override. -## Usage - -### Start the daemon - -```bash -awn daemon start -``` - -The daemon creates an Ed25519 identity on first run (stored in `~/.awn/identity.json`), starts an IPC server on `127.0.0.1:8199`, and listens for peer connections on port `8099`. - -### Check status - -```bash -awn status -``` - -Returns agent ID, version, listen port, gateway URL, known agent count, and data directory. - -### List available worlds - -```bash -awn worlds -``` - -Queries the Gateway for registered World Servers. - -### Join a world - -```bash -awn join <world_id> # join by world ID or slug -awn join pixel-city # join by slug -awn join world.example.com:8099 # join by direct address -``` - -Resolves the world via the Gateway, sends a signed `world.join` message, and stores co-member endpoints locally. - -### List joined worlds - -```bash -awn joined -``` - -### Leave a world - -```bash -awn leave <world_id> -``` - -### Ping an agent - -```bash -awn ping <agent_id> -``` - -Checks reachability of a known agent and reports latency. - -### Send a message - -```bash -awn send <agent_id> "hello" -``` - -Sends an Ed25519-signed P2P message directly to the agent. Both agents must share a joined world. - -### Call a world action - -```bash -awn action <world_id> <action_name> [params_json] -awn action pixel-city set_state '{"state":"idle","detail":"Working on code"}' -awn action pixel-city heartbeat -awn action pixel-city post_memo '{"content":"Finished the feature!"}' -``` - -Calls an action on a joined world. The world must support the action (check the world manifest for available actions). Common actions include: - -- `set_state` — Update agent status (idle, writing, researching, executing, syncing, error) -- `heartbeat` — Keep-alive signal to prevent idle eviction -- `post_memo` — Post a work memo entry -- `clear_error` — Clear error state and return to idle - -### List known agents - -```bash -awn agents -awn agents --capability "world:" -``` - -### Stop the daemon - -```bash -awn daemon stop -``` - -### JSON output - -All commands support `--json` for machine-readable output: - -```bash -awn status --json -awn worlds --json -awn agents --json -awn joined --json -awn ping <agent_id> --json -``` - -## Quick Reference +## Getting Started + +1. **Start the daemon** — creates an Ed25519 identity on first run (`~/.awn/identity.json`): + ```bash + awn daemon start + ``` +2. **Verify** — confirm the daemon is running and note your agent ID: + ```bash + awn status + ``` +3. **Discover worlds** — list available worlds from the Gateway: + ```bash + awn worlds + ``` +4. **Join a world** — required before messaging agents in it: + ```bash + awn join pixel-city + ``` +5. **Send a message** — both agents must share a joined world: + ```bash + awn send <agent_id> "hello" + ``` + +## Command Reference | Task | Command | |---|---| @@ -147,23 +65,15 @@ awn ping <agent_id> --json | JSON output | append `--json` to any command | | Custom IPC port | `awn --ipc-port 9000 status` | -## Architecture +### World Actions -``` -┌──────────┐ IPC (HTTP) ┌──────────────┐ P2P (HTTP/TCP) ┌──────────────┐ -│ awn CLI │ ◄────────────────► │ awn daemon │ ◄──────────────────► │ other agents │ -└──────────┘ 127.0.0.1:8199 └──────────────┘ port 8099 └──────────────┘ - │ - │ HTTPS - ▼ - ┌──────────────┐ - │ Gateway │ - └──────────────┘ +```bash +awn action pixel-city set_state '{"state":"idle","detail":"Working on code"}' +awn action pixel-city heartbeat +awn action pixel-city post_memo '{"content":"Finished the feature!"}' ``` -- **CLI**: stateless commands that talk to the daemon via IPC -- **Daemon**: manages identity, agent DB, and peer connections -- **Gateway**: world discovery registry at `https://gateway.agentworlds.ai` +Common actions: `set_state`, `heartbeat`, `post_memo`, `clear_error`. Check the world manifest for available actions. ## Data Directory