[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CZCQZFFK3F54E9NG5RH86H":3,"skill-same:01M6CZCQZFFK3F54E9NG5RH86H":70},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":38,"linkOnly":39,"markdownContent":40,"markdownBody":41,"frontMatter":42,"refName":47,"commitSha":48,"skillDirectory":49,"forksCount":50,"repositoryHtmlUrl":51,"repositoryHomepageUrl":52,"ownerHtmlUrl":53,"ownerBlogUrl":52,"ownerDescription":54,"updatedAt":55,"install":56,"resources":69},"01M6CZCQZFFK3F54E9NG5RH86H","spawn-instance",null,"Clone this Aeon agent into a new GitHub repo - fork, configure skills, validate, and register in the fleet","aeonfun\u002Faeon","aeonfun","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F287715280?v=4","01M6CZ23C6MXGMF4N0V1DZ1247","aeon","01M6CZ23GMZP1BR424J8Y8K3DG",793,"MIT","https:\u002F\u002Fgithub.com\u002Faeonfun\u002Faeon\u002Fblob\u002Fmain\u002Fskills\u002Fspawn-instance\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,12,30,31,32,33,34,35,36,37],"spawn","spawn instance","github","validate","core","dev","configure","repo","register","fleet","clone","fork","github repo","new","2026-11-10 10:12:30",false,"---\nname: spawn-instance\ndescription: Clone this Aeon agent into a new GitHub repo - fork, configure skills, validate, and register in the fleet\nmetadata:\n  title: Spawn Instance\n  category: core\n  var: \"\"\n  tags:\n    - dev\n---\n\u003C!-- autoresearch: variation C — robust: skill-existence validation, exit taxonomy, idempotent recovery, dynamic SETUP.md, pre\u002Fpost-flight verification -->\n\n> **${var}** — Name and purpose of the new instance. Format `name: purpose`, e.g. `crypto-tracker: monitor DeFi protocols and token movements`. If empty, notify the owner and **stop** with exit `SPAWN_INVALID_VAR`.\n\nToday is ${today}. Create a new Aeon instance by forking this repo, configuring it for a specific purpose, validating the configuration, and registering it in the fleet.\n\nRead `memory\u002FMEMORY.md` at the start for context.\n\n## Security Model\n\nThis skill creates the repo and configuration but does **NOT** propagate secrets.\nThe new instance is inert until the owner manually sets secrets (`ANTHROPIC_API_KEY` or `CLAUDE_CODE_OAUTH_TOKEN`, plus notification secrets).\nEach instance has its own API keys for billing isolation and blast-radius containment.\n\n## Exit Taxonomy\n\nEvery run ends with one of these status codes, written to the log and (where relevant) included in the notification:\n\n| Code | Meaning |\n|------|---------|\n| `SPAWN_OK` | Fork created, configured, pushed, Actions enabled, registered. |\n| `SPAWN_FORK_EXISTS_RECOVERED` | Fork already existed but wasn't registered → configured + registered now. |\n| `SPAWN_FORK_EXISTS_REGISTERED` | Fork exists AND is already registered and not archived — refused, no change. |\n| `SPAWN_INVALID_VAR` | var was empty or couldn't be parsed into `name: purpose`. |\n| `SPAWN_NO_SKILLS` | After validation, the skill plan was empty — refused. |\n| `SPAWN_FORK_FAILED` | `gh repo fork` and the fallback `forks` API both failed. |\n| `SPAWN_PUSH_FAILED` | Fork created but push failed — fork left in place, recovery instructions emitted. |\n| `SPAWN_ACTIONS_FAILED` | Configuration pushed but enabling Actions failed — recovery instructions emitted. |\n| `SPAWN_API_ERROR` | Any other GitHub API failure not covered above. |\n\n## Steps\n\n### 1. Parse and validate the var\n\n- If `${var}` is empty, log `SPAWN_INVALID_VAR: empty var` to `memory\u002Flogs\u002F${today}.md`, notify: `spawn-instance: empty var — re-run with \"name: purpose\"`, and **stop**.\n- Split on the first `:` — left is `NAME_RAW`, right is `PURPOSE` (trim whitespace). If either is empty, exit `SPAWN_INVALID_VAR`.\n- Derive `NAME`: lowercase `NAME_RAW`, replace non-alphanumeric runs with `-`, strip leading\u002Ftrailing `-`, truncate to 40 chars. If empty after sanitization, exit `SPAWN_INVALID_VAR`.\n- Set `REPO_NAME=\"aeon-${NAME}\"`.\n\n### 2. Pre-flight checks\n\n**Shell shape.** Each Bash call is one allowed command (pipes are fine). The run refuses a call that sets a variable (`OWNER=$(gh api ...)`, `TMPDIR=$(mktemp -d)`), uses `if` \u002F `for` \u002F `while` or a `[ ... ]` test, joins commands with `;`, `&&` or `||` (including `|| { echo ...; exit 1; }`), or starts with `cd DIR`, and `find`, `rm`, `awk`, `basename`, `mktemp`, `seq` and `sleep` are not allowed commands; each refusal costs a model turn. So run each `gh` \u002F `git` command as its own call, read what it prints and write that value into later commands literally (the `\u003COWNER>`, `\u003CREPO_NAME>` style placeholders in the snippets); turn each `|| exit` into the prose check after the call; run `git` in the clone with `git -C \u003Cdir>`; write files with Write\u002FEdit; and do the memory reset deletes inside one `python3 -c` call.\n\nRun each as its own call:\n```bash\ngh auth status\n```\nIf it fails, log `SPAWN_API_ERROR: gh not authenticated` and stop.\n```bash\ngh api user --jq '.login'\n```\nIt prints OWNER. If it fails, log `SPAWN_API_ERROR: cannot read user` and stop.\n```bash\ngh repo view --json nameWithOwner -q .nameWithOwner\n```\nIt prints PARENT_REPO. If the current repo is itself a fork, use the upstream as the parent; this prints PARENT_UPSTREAM:\n```bash\ngh api repos\u002F\u003CPARENT_REPO> --jq '.parent.full_name \u002F\u002F .full_name'\n```\n\nCheck rate limit:\n```bash\ngh api rate_limit --jq '.resources.core.remaining'\n```\nIt prints REMAINING. If it is below 50 (or empty, which counts as 0), log `SPAWN_API_ERROR: rate limit too low (\u003CREMAINING>)` and stop.\n\n### 3. Check the fleet registry\n\nRead `memory\u002Finstances.json`. If it doesn't exist, create it with `{\"instances\": []}`.\n\n```json\n{\n  \"instances\": [\n    {\n      \"name\": \"crypto-tracker\",\n      \"repo\": \"OWNER\u002Faeon-crypto-tracker\",\n      \"purpose\": \"monitor DeFi protocols and token movements\",\n      \"created\": \"2026-04-20\",\n      \"status\": \"pending_secrets\",\n      \"skills_enabled\": [\"token-movers\", \"defi-overview\", \"heartbeat\"],\n      \"parent\": \"OWNER\u002Faeon\"\n    }\n  ]\n}\n```\n\n- If an entry with `name == NAME` exists and `status != \"archived\"`, exit `SPAWN_FORK_EXISTS_REGISTERED`, notify, and **stop**.\n- If an entry exists and is archived, remove it — the new run replaces it.\n\n### 4. Build the skill plan from the live catalog\n\n**Do not use a hardcoded skill list.** The catalog in earlier revisions contained broken names (`wallet-digest`, `trending-coins`, `tweet-digest`, `hn-digest` — none of which exist in `skills\u002F`). Always enumerate live.\n\nBuild the live catalog of available skills and their tags\u002Fdescription in one call (a shell `for` loop is refused; the loop lives inside `node -e`). It prints each skill's name and the frontmatter between its first two `---` lines, skipping directories with no `SKILL.md`:\n```bash\nnode -e 'const fs=require(\"fs\"); for (const d of fs.readdirSync(\"skills\").sort()) { const f=\"skills\u002F\"+d+\"\u002FSKILL.md\"; if (!fs.existsSync(f)) continue; const m=fs.readFileSync(f,\"utf8\").split(\u002F^---[^\\n]*$\u002Fm)[1] || \"\"; console.log(\"== \"+d+\"\\n\"+m.trim()) }'\n```\n\nFor each skill, parse the frontmatter `description:` and `tags:` lines. Classify the purpose into themes by keyword match (case-insensitive) and pick skills whose description or tags overlap:\n\n| Purpose keywords | Prefer skills matching tags \u002F keywords |\n|---|---|\n| `crypto`, `defi`, `token`, `chain`, `wallet` | tags `[crypto]` or description contains `token`\u002F`defi`\u002F`chain` |\n| `research`, `paper`, `academic`, `science` | tags `[research]` or name contains `paper`\u002F`research`\u002F`deep-research` |\n| `social`, `twitter`, `x `, `tweet`, `farcaster` | tags `[social]` or name contains `tweet`\u002F`twitter`\u002F`farcaster`\u002F`reply` |\n| `news`, `digest`, `feed`, `brief` | name contains `digest`\u002F`brief`\u002F`morning`\u002F`rss`\u002F`hacker-news` |\n| `dev`, `code`, `github`, `repo`, `pr ` | tags `[dev]` or name contains `github`\u002F`code`\u002F`repo`\u002F`pr-`\u002F`changelog` |\n| `security`, `vuln`, `audit` | tags `[security]` or name contains `security`\u002F`vuln`\u002F`audit` |\n| `prediction`, `polymarket`, `kalshi`, `market` | name contains `polymarket`\u002F`kalshi`\u002F`market`\u002F`narrative` |\n\nRules:\n- **Cap at 8** content skills. Rank by keyword density in description against purpose; tie-break by name.\n- **Always include `heartbeat`** if the file `skills\u002Fheartbeat\u002FSKILL.md` exists (health monitoring).\n- If the purpose doesn't match any theme, fall back to `[reflect, heartbeat]` (filtered against existence).\n- **Validate every candidate** — drop any skill where `skills\u002F${skill}\u002FSKILL.md` doesn't exist; log each drop as `SPAWN_DROPPED_SKILL: ${skill}`.\n- If the final list is empty (no content skills survive), exit `SPAWN_NO_SKILLS`, notify, and **stop**.\n\nSave the final list as `SKILLS_ENABLED`.\n\n### 5. Fork the parent repo\n\nFirst check whether the fork already exists:\n```bash\ngh api repos\u002F\u003COWNER>\u002F\u003CREPO_NAME> --jq '.full_name'\n```\nIf it prints the full name, `FORK_STATE` is `exists`; skip to the wait below. If it fails (404), try the modern flag first:\n```bash\ngh repo fork \u003CPARENT_UPSTREAM> --fork-name \u003CREPO_NAME> --clone=false\n```\nIf that fails, fall back to a POST to `\u002Frepos\u002F{owner}\u002F{repo}\u002Fforks` with a custom name:\n```bash\ngh api repos\u002F\u003CPARENT_UPSTREAM>\u002Fforks -X POST -f name=\u003CREPO_NAME> --jq '.full_name'\n```\nIf that fails too, log `SPAWN_FORK_FAILED` and stop. Otherwise `FORK_STATE` is `created`.\n\n**Wait for fork availability** (GitHub forks are async): run this check as a separate call, up to 10 times, until it prints the full name (each model turn between calls is the wait; there is no `sleep`):\n```bash\ngh api repos\u002F\u003COWNER>\u002F\u003CREPO_NAME> --jq '.full_name'\n```\nIf it still fails after 10 tries, log `SPAWN_FORK_FAILED: fork not reachable after wait` and stop.\n\n### 6. Configure the fork\n\nWork in the fixed directory `\u002Ftmp\u002Fspawn-instance-work` (the runner is thrown away after the run, so there is no cleanup step). Each line below is its own call:\n```bash\nmkdir -p \u002Ftmp\u002Fspawn-instance-work\n```\n```bash\ngh repo clone \u003COWNER>\u002F\u003CREPO_NAME> \u002Ftmp\u002Fspawn-instance-work\u002Frepo -- --quiet\n```\nIf the clone fails, log `SPAWN_API_ERROR: clone failed` and stop.\n```bash\ngit -C \u002Ftmp\u002Fspawn-instance-work\u002Frepo config user.name \"aeonframework\"\n```\n```bash\ngit -C \u002Ftmp\u002Fspawn-instance-work\u002Frepo config user.email \"aeonframework@proton.me\"\n```\n\nEvery path in 6a-6e (`aeon.yml`, `SETUP.md`, `CLAUDE.md`, `memory\u002F...`, `skills\u002F...`) is inside the clone, `\u002Ftmp\u002Fspawn-instance-work\u002Frepo`. Read and change those files with Read\u002FEdit\u002FWrite on their absolute paths.\n\n#### 6a. Write a customized `aeon.yml`\n\n- Read the parent `aeon.yml` as a base (preserves comments, ordering, and the full skill list).\n- Set `enabled: true` only on skills in `SKILLS_ENABLED`. All others must have `enabled: false`.\n- Do not drop any skills — keep the full inventory so the child can enable more later.\n- **Validate the result**: every skill name with `enabled: true` must correspond to an existing `skills\u002F${skill}\u002FSKILL.md` in the fork's tree. If any enabled skill is missing, abort before pushing (this is a sanity check — step 4 already validated, but the child's repo tree must match).\n\n#### 6b. Write `SETUP.md` dynamically\n\nParse each enabled skill's `skills\u002F${skill}\u002FSKILL.md` for references to uppercase env var names (pattern: `[A-Z][A-Z0-9_]{2,}_(KEY|TOKEN|URL|ID|SECRET)`). Collect the union across enabled skills, excluding built-ins (`GITHUB_TOKEN`, `GH_TOKEN`).\n\nEmit a SETUP.md with three sections:\n\n```markdown\n# Aeon Instance Setup\n\nThis is a managed Aeon instance spawned from `${PARENT_UPSTREAM}`.\n\n## Purpose\n${PURPOSE}\n\n## Enabled Skills\n${comma-separated list with one-line descriptions from each SKILL.md}\n\n## Activate This Instance\n\nGo to **Settings > Secrets and variables > Actions** and add these secrets:\n\n### Required (pick one for Claude auth)\n| Secret | Description |\n|--------|------------|\n| `ANTHROPIC_API_KEY` | Anthropic API key - console.anthropic.com |\n| `CLAUDE_CODE_OAUTH_TOKEN` | Alternative: Claude Code OAuth token |\n\n### Recommended (notifications)\n| Secret | Description |\n|--------|------------|\n| `TELEGRAM_BOT_TOKEN` | Telegram bot token |\n| `TELEGRAM_CHAT_ID` | Telegram chat ID |\n| `DISCORD_WEBHOOK_URL` | Discord webhook URL |\n| `SLACK_WEBHOOK_URL` | Slack webhook URL |\n\n### Required by your enabled skills\n${one row per detected env var, with the list of skills that reference it}\n\n## Fleet Parent\nManaged by `${PARENT_UPSTREAM}`. The parent can dispatch skills and monitor health via `fleet-control`.\n\n## Security Note\nThis instance has NO access to the parent's secrets. Each instance maintains its own API keys and credentials.\n```\n\nIf no env vars are detected beyond the required\u002Frecommended set, omit the \"Required by your enabled skills\" section header (don't leave an empty table).\n\n#### 6c. Update `CLAUDE.md` idempotently\n\nFind the heading line `## About This Repo` (or the first `## ` section if not present). Under it, insert exactly one line:\n```\n- Managed instance of ${PARENT_UPSTREAM}. Purpose: ${PURPOSE}.\n```\n\nIf a line starting with `- Managed instance of` already exists, replace it rather than appending a duplicate.\n\n#### 6d. Reset child memory\n\nThe child starts with a clean slate:\n\n1. Reset `memory\u002FMEMORY.md` to a minimal template with Write (PARENT_UPSTREAM and PURPOSE written in literally):\n   ```markdown\n   # Long-term Memory\n   *Last consolidated: never*\n\n   ## About This Repo\n   - Aeon instance of \u003CPARENT_UPSTREAM>. Purpose: \u003CPURPOSE>.\n\n   ## Next Priorities\n   - Configure secrets per SETUP.md\n   - Wait for first scheduled skill to run\n   ```\n2. Clear logs, state and topics, safe paths only, never following symlinks, in one call: it deletes every regular file under `memory\u002Flogs`, `memory\u002Ftopics` and `memory\u002Fissues` (except files named `INDEX.md`), and removes `memory\u002Finstances.json` (the child has no fleet of its own). Missing directories are skipped:\n   ```bash\n   python3 -c 'import os; r=\"\u002Ftmp\u002Fspawn-instance-work\u002Frepo\u002Fmemory\"; [os.remove(p) for s in (\"logs\", \"topics\", \"issues\") for dp, _, fs in os.walk(os.path.join(r, s)) for f in fs for p in [os.path.join(dp, f)] if os.path.isfile(p) and not os.path.islink(p) and not (s == \"issues\" and f == \"INDEX.md\")]; j=os.path.join(r, \"instances.json\"); os.path.lexists(j) and os.remove(j)'\n   ```\n3. If `memory\u002Fissues\u002FINDEX.md` exists (check with Glob), overwrite it with Write as the single line `# Issues - none open`.\n4. Write `memory\u002Fcron-state.json` as `{}` with Write.\n\n#### 6e. Commit and push\n\nEach its own call, with PURPOSE, the skills list and PARENT_UPSTREAM written in literally:\n```bash\ngit -C \u002Ftmp\u002Fspawn-instance-work\u002Frepo add -A\n```\n```bash\ngit -C \u002Ftmp\u002Fspawn-instance-work\u002Frepo commit -m \"chore: configure instance - \u003CPURPOSE>\n\nSkills enabled: \u003CSKILLS_ENABLED_CSV>\nParent: \u003CPARENT_UPSTREAM>\nSpawned: ${today}\"\n```\n```bash\ngit -C \u002Ftmp\u002Fspawn-instance-work\u002Frepo push origin main\n```\nIf that push fails, try:\n```bash\ngit -C \u002Ftmp\u002Fspawn-instance-work\u002Frepo push origin HEAD:main\n```\nIf that fails too, log `SPAWN_PUSH_FAILED` and stop.\n\nIf push fails, **do not delete the fork** — leave it for manual inspection and notify with:\n```\nspawn-instance: fork created but push failed for ${OWNER}\u002F${REPO_NAME}.\nRecover with: gh repo clone ${OWNER}\u002F${REPO_NAME} && push manually, then re-register.\n```\n\n### 7. Enable GitHub Actions on the fork\n\nForks have Actions disabled by default. Use **typed** booleans (`-F`, not `-f`, or `enabled=true` is sent as the string \"true\"):\n\n```bash\ngh api repos\u002F\u003COWNER>\u002F\u003CREPO_NAME>\u002Factions\u002Fpermissions -X PUT \\\n  -F enabled=true -f allowed_actions=all\n```\nIf it fails, log `SPAWN_ACTIONS_FAILED` and stop.\n\n### 8. Post-flight verification\n\nThree separate calls. Fork reachable:\n```bash\ngh api repos\u002F\u003COWNER>\u002F\u003CREPO_NAME> --jq '.full_name'\n```\nIf it fails, log `SPAWN_API_ERROR: post-flight fork check failed` and stop. Our commit is HEAD:\n```bash\ngh api repos\u002F\u003COWNER>\u002F\u003CREPO_NAME>\u002Fcommits\u002Fmain --jq '.sha'\n```\nIt prints HEAD_SHA. If it fails or prints nothing, log `SPAWN_API_ERROR: post-flight HEAD check failed` and stop. Actions enabled:\n```bash\ngh api repos\u002F\u003COWNER>\u002F\u003CREPO_NAME>\u002Factions\u002Fpermissions --jq '.enabled'\n```\nIf it does not print `true`, log `SPAWN_ACTIONS_FAILED: post-flight` and stop.\n\n### 9. Register the instance\n\nUpdate `memory\u002Finstances.json` in the **parent** repo. Append:\n```json\n{\n  \"name\": \"${NAME}\",\n  \"repo\": \"${OWNER}\u002F${REPO_NAME}\",\n  \"purpose\": \"${PURPOSE}\",\n  \"created\": \"${today}\",\n  \"status\": \"pending_secrets\",\n  \"skills_enabled\": ${SKILLS_ENABLED_JSON},\n  \"parent\": \"${PARENT_UPSTREAM}\"\n}\n```\n\nIf `FORK_STATE == \"exists\"` at step 5, the final exit status is `SPAWN_FORK_EXISTS_RECOVERED`, otherwise `SPAWN_OK`.\n\n### 10. Log to memory\n\nAppend to `memory\u002Flogs\u002F${today}.md`:\n```\n### spawn-instance\n- Status: ${EXIT_CODE}\n- Instance: ${OWNER}\u002F${REPO_NAME}\n- Purpose: ${PURPOSE}\n- Skills: ${SKILLS_ENABLED_CSV}\n- Dropped skills: ${DROPPED_CSV or \"(none)\"}\n- Actions enabled: yes\n```\n\n### 11. Notify via `.\u002Fnotify`\n\nOn success (`SPAWN_OK` or `SPAWN_FORK_EXISTS_RECOVERED`):\n```\n*New Aeon Instance*\n\nRepo: ${OWNER}\u002F${REPO_NAME}\nPurpose: ${PURPOSE}\nSkills (${N}): ${SKILLS_ENABLED_CSV}\nStatus: ${EXIT_CODE} - PENDING SECRETS\n\nActivate:\n1. https:\u002F\u002Fgithub.com\u002F${OWNER}\u002F${REPO_NAME}\u002Fsettings\u002Fsecrets\u002Factions\n2. Add ANTHROPIC_API_KEY (or CLAUDE_CODE_OAUTH_TOKEN)\n3. Add TELEGRAM_BOT_TOKEN + TELEGRAM_CHAT_ID (or Discord\u002FSlack)\n\nSee SETUP.md in the repo for the full secret list tailored to your enabled skills.\n```\n\nOn refusal (`SPAWN_FORK_EXISTS_REGISTERED`, `SPAWN_INVALID_VAR`, `SPAWN_NO_SKILLS`):\n```\nspawn-instance: ${EXIT_CODE} - ${one-line reason}. No changes made.\n```\n\nOn failure (`SPAWN_FORK_FAILED`, `SPAWN_PUSH_FAILED`, `SPAWN_ACTIONS_FAILED`, `SPAWN_API_ERROR`):\n```\nspawn-instance FAILED: ${EXIT_CODE}\nTarget: ${OWNER}\u002F${REPO_NAME}\nRecovery: ${one-line recovery instruction}\n```\n\n## Network note\n\nThis skill runs entirely through `gh` CLI, which handles auth internally, so no bare `$SECRET` ever lands on the command line for the Bash permission layer to refuse. No WebFetch fallback needed. If `gh` is missing or unauthenticated, the pre-flight step fails with `SPAWN_API_ERROR`.\n\n## Constraints\n\n- **No secret propagation.** Never read or write `ANTHROPIC_API_KEY`, `TELEGRAM_*`, `DISCORD_*`, `SLACK_*`, or any API key into the child repo. The whole security model depends on this.\n- **No hardcoded skill list.** Always enumerate `skills\u002F*\u002FSKILL.md` at runtime to avoid referencing renamed or removed skills.\n- **Idempotent.** Re-running with the same `${var}` must never produce duplicate registry entries, duplicate CLAUDE.md lines, or a second fork.\n- **Never delete a fork.** If anything fails partway through, leave the fork in place and emit recovery guidance — the operator is the only party authorized to delete it.\n- **Never push to the parent without committing `memory\u002Finstances.json` via the normal Aeon workflow.** The parent commit happens through the same path as any other skill output.\n\nWrite complete, working code. No TODOs or placeholders.\n","\u003C!-- autoresearch: variation C — robust: skill-existence validation, exit taxonomy, idempotent recovery, dynamic SETUP.md, pre\u002Fpost-flight verification -->\n\n> **${var}** — Name and purpose of the new instance. Format `name: purpose`, e.g. `crypto-tracker: monitor DeFi protocols and token movements`. If empty, notify the owner and **stop** with exit `SPAWN_INVALID_VAR`.\n\nToday is ${today}. Create a new Aeon instance by forking this repo, configuring it for a specific purpose, validating the configuration, and registering it in the fleet.\n\nRead `memory\u002FMEMORY.md` at the start for context.\n\n## Security Model\n\nThis skill creates the repo and configuration but does **NOT** propagate secrets.\nThe new instance is inert until the owner manually sets secrets (`ANTHROPIC_API_KEY` or `CLAUDE_CODE_OAUTH_TOKEN`, plus notification secrets).\nEach instance has its own API keys for billing isolation and blast-radius containment.\n\n## Exit Taxonomy\n\nEvery run ends with one of these status codes, written to the log and (where relevant) included in the notification:\n\n| Code | Meaning |\n|------|---------|\n| `SPAWN_OK` | Fork created, configured, pushed, Actions enabled, registered. |\n| `SPAWN_FORK_EXISTS_RECOVERED` | Fork already existed but wasn't registered → configured + registered now. |\n| `SPAWN_FORK_EXISTS_REGISTERED` | Fork exists AND is already registered and not archived — refused, no change. |\n| `SPAWN_INVALID_VAR` | var was empty or couldn't be parsed into `name: purpose`. |\n| `SPAWN_NO_SKILLS` | After validation, the skill plan was empty — refused. |\n| `SPAWN_FORK_FAILED` | `gh repo fork` and the fallback `forks` API both failed. |\n| `SPAWN_PUSH_FAILED` | Fork created but push failed — fork left in place, recovery instructions emitted. |\n| `SPAWN_ACTIONS_FAILED` | Configuration pushed but enabling Actions failed — recovery instructions emitted. |\n| `SPAWN_API_ERROR` | Any other GitHub API failure not covered above. |\n\n## Steps\n\n### 1. Parse and validate the var\n\n- If `${var}` is empty, log `SPAWN_INVALID_VAR: empty var` to `memory\u002Flogs\u002F${today}.md`, notify: `spawn-instance: empty var — re-run with \"name: purpose\"`, and **stop**.\n- Split on the first `:` — left is `NAME_RAW`, right is `PURPOSE` (trim whitespace). If either is empty, exit `SPAWN_INVALID_VAR`.\n- Derive `NAME`: lowercase `NAME_RAW`, replace non-alphanumeric runs with `-`, strip leading\u002Ftrailing `-`, truncate to 40 chars. If empty after sanitization, exit `SPAWN_INVALID_VAR`.\n- Set `REPO_NAME=\"aeon-${NAME}\"`.\n\n### 2. Pre-flight checks\n\n**Shell shape.** Each Bash call is one allowed command (pipes are fine). The run refuses a call that sets a variable (`OWNER=$(gh api ...)`, `TMPDIR=$(mktemp -d)`), uses `if` \u002F `for` \u002F `while` or a `[ ... ]` test, joins commands with `;`, `&&` or `||` (including `|| { echo ...; exit 1; }`), or starts with `cd DIR`, and `find`, `rm`, `awk`, `basename`, `mktemp`, `seq` and `sleep` are not allowed commands; each refusal costs a model turn. So run each `gh` \u002F `git` command as its own call, read what it prints and write that value into later commands literally (the `\u003COWNER>`, `\u003CREPO_NAME>` style placeholders in the snippets); turn each `|| exit` into the prose check after the call; run `git` in the clone with `git -C \u003Cdir>`; write files with Write\u002FEdit; and do the memory reset deletes inside one `python3 -c` call.\n\nRun each as its own call:\n```bash\ngh auth status\n```\nIf it fails, log `SPAWN_API_ERROR: gh not authenticated` and stop.\n```bash\ngh api user --jq '.login'\n```\nIt prints OWNER. If it fails, log `SPAWN_API_ERROR: cannot read user` and stop.\n```bash\ngh repo view --json nameWithOwner -q .nameWithOwner\n```\nIt prints PARENT_REPO. If the current repo is itself a fork, use the upstream as the parent; this prints PARENT_UPSTREAM:\n```bash\ngh api repos\u002F\u003CPARENT_REPO> --jq '.parent.full_name \u002F\u002F .full_name'\n```\n\nCheck rate limit:\n```bash\ngh api rate_limit --jq '.resources.core.remaining'\n```\nIt prints REMAINING. If it is below 50 (or empty, which counts as 0), log `SPAWN_API_ERROR: rate limit too low (\u003CREMAINING>)` and stop.\n\n### 3. Check the fleet registry\n\nRead `memory\u002Finstances.json`. If it doesn't exist, create it with `{\"instances\": []}`.\n\n```json\n{\n  \"instances\": [\n    {\n      \"name\": \"crypto-tracker\",\n      \"repo\": \"OWNER\u002Faeon-crypto-tracker\",\n      \"purpose\": \"monitor DeFi protocols and token movements\",\n      \"created\": \"2026-04-20\",\n      \"status\": \"pending_secrets\",\n      \"skills_enabled\": [\"token-movers\", \"defi-overview\", \"heartbeat\"],\n      \"parent\": \"OWNER\u002Faeon\"\n    }\n  ]\n}\n```\n\n- If an entry with `name == NAME` exists and `status != \"archived\"`, exit `SPAWN_FORK_EXISTS_REGISTERED`, notify, and **stop**.\n- If an entry exists and is archived, remove it — the new run replaces it.\n\n### 4. Build the skill plan from the live catalog\n\n**Do not use a hardcoded skill list.** The catalog in earlier revisions contained broken names (`wallet-digest`, `trending-coins`, `tweet-digest`, `hn-digest` — none of which exist in `skills\u002F`). Always enumerate live.\n\nBuild the live catalog of available skills and their tags\u002Fdescription in one call (a shell `for` loop is refused; the loop lives inside `node -e`). It prints each skill's name and the frontmatter between its first two `---` lines, skipping directories with no `SKILL.md`:\n```bash\nnode -e 'const fs=require(\"fs\"); for (const d of fs.readdirSync(\"skills\").sort()) { const f=\"skills\u002F\"+d+\"\u002FSKILL.md\"; if (!fs.existsSync(f)) continue; const m=fs.readFileSync(f,\"utf8\").split(\u002F^---[^\\n]*$\u002Fm)[1] || \"\"; console.log(\"== \"+d+\"\\n\"+m.trim()) }'\n```\n\nFor each skill, parse the frontmatter `description:` and `tags:` lines. Classify the purpose into themes by keyword match (case-insensitive) and pick skills whose description or tags overlap:\n\n| Purpose keywords | Prefer skills matching tags \u002F keywords |\n|---|---|\n| `crypto`, `defi`, `token`, `chain`, `wallet` | tags `[crypto]` or description contains `token`\u002F`defi`\u002F`chain` |\n| `research`, `paper`, `academic`, `science` | tags `[research]` or name contains `paper`\u002F`research`\u002F`deep-research` |\n| `social`, `twitter`, `x `, `tweet`, `farcaster` | tags `[social]` or name contains `tweet`\u002F`twitter`\u002F`farcaster`\u002F`reply` |\n| `news`, `digest`, `feed`, `brief` | name contains `digest`\u002F`brief`\u002F`morning`\u002F`rss`\u002F`hacker-news` |\n| `dev`, `code`, `github`, `repo`, `pr ` | tags `[dev]` or name contains `github`\u002F`code`\u002F`repo`\u002F`pr-`\u002F`changelog` |\n| `security`, `vuln`, `audit` | tags `[security]` or name contains `security`\u002F`vuln`\u002F`audit` |\n| `prediction`, `polymarket`, `kalshi`, `market` | name contains `polymarket`\u002F`kalshi`\u002F`market`\u002F`narrative` |\n\nRules:\n- **Cap at 8** content skills. Rank by keyword density in description against purpose; tie-break by name.\n- **Always include `heartbeat`** if the file `skills\u002Fheartbeat\u002FSKILL.md` exists (health monitoring).\n- If the purpose doesn't match any theme, fall back to `[reflect, heartbeat]` (filtered against existence).\n- **Validate every candidate** — drop any skill where `skills\u002F${skill}\u002FSKILL.md` doesn't exist; log each drop as `SPAWN_DROPPED_SKILL: ${skill}`.\n- If the final list is empty (no content skills survive), exit `SPAWN_NO_SKILLS`, notify, and **stop**.\n\nSave the final list as `SKILLS_ENABLED`.\n\n### 5. Fork the parent repo\n\nFirst check whether the fork already exists:\n```bash\ngh api repos\u002F\u003COWNER>\u002F\u003CREPO_NAME> --jq '.full_name'\n```\nIf it prints the full name, `FORK_STATE` is `exists`; skip to the wait below. If it fails (404), try the modern flag first:\n```bash\ngh repo fork \u003CPARENT_UPSTREAM> --fork-name \u003CREPO_NAME> --clone=false\n```\nIf that fails, fall back to a POST to `\u002Frepos\u002F{owner}\u002F{repo}\u002Fforks` with a custom name:\n```bash\ngh api repos\u002F\u003CPARENT_UPSTREAM>\u002Fforks -X POST -f name=\u003CREPO_NAME> --jq '.full_name'\n```\nIf that fails too, log `SPAWN_FORK_FAILED` and stop. Otherwise `FORK_STATE` is `created`.\n\n**Wait for fork availability** (GitHub forks are async): run this check as a separate call, up to 10 times, until it prints the full name (each model turn between calls is the wait; there is no `sleep`):\n```bash\ngh api repos\u002F\u003COWNER>\u002F\u003CREPO_NAME> --jq '.full_name'\n```\nIf it still fails after 10 tries, log `SPAWN_FORK_FAILED: fork not reachable after wait` and stop.\n\n### 6. Configure the fork\n\nWork in the fixed directory `\u002Ftmp\u002Fspawn-instance-work` (the runner is thrown away after the run, so there is no cleanup step). Each line below is its own call:\n```bash\nmkdir -p \u002Ftmp\u002Fspawn-instance-work\n```\n```bash\ngh repo clone \u003COWNER>\u002F\u003CREPO_NAME> \u002Ftmp\u002Fspawn-instance-work\u002Frepo -- --quiet\n```\nIf the clone fails, log `SPAWN_API_ERROR: clone failed` and stop.\n```bash\ngit -C \u002Ftmp\u002Fspawn-instance-work\u002Frepo config user.name \"aeonframework\"\n```\n```bash\ngit -C \u002Ftmp\u002Fspawn-instance-work\u002Frepo config user.email \"aeonframework@proton.me\"\n```\n\nEvery path in 6a-6e (`aeon.yml`, `SETUP.md`, `CLAUDE.md`, `memory\u002F...`, `skills\u002F...`) is inside the clone, `\u002Ftmp\u002Fspawn-instance-work\u002Frepo`. Read and change those files with Read\u002FEdit\u002FWrite on their absolute paths.\n\n#### 6a. Write a customized `aeon.yml`\n\n- Read the parent `aeon.yml` as a base (preserves comments, ordering, and the full skill list).\n- Set `enabled: true` only on skills in `SKILLS_ENABLED`. All others must have `enabled: false`.\n- Do not drop any skills — keep the full inventory so the child can enable more later.\n- **Validate the result**: every skill name with `enabled: true` must correspond to an existing `skills\u002F${skill}\u002FSKILL.md` in the fork's tree. If any enabled skill is missing, abort before pushing (this is a sanity check — step 4 already validated, but the child's repo tree must match).\n\n#### 6b. Write `SETUP.md` dynamically\n\nParse each enabled skill's `skills\u002F${skill}\u002FSKILL.md` for references to uppercase env var names (pattern: `[A-Z][A-Z0-9_]{2,}_(KEY|TOKEN|URL|ID|SECRET)`). Collect the union across enabled skills, excluding built-ins (`GITHUB_TOKEN`, `GH_TOKEN`).\n\nEmit a SETUP.md with three sections:\n\n```markdown\n# Aeon Instance Setup\n\nThis is a managed Aeon instance spawned from `${PARENT_UPSTREAM}`.\n\n## Purpose\n${PURPOSE}\n\n## Enabled Skills\n${comma-separated list with one-line descriptions from each SKILL.md}\n\n## Activate This Instance\n\nGo to **Settings > Secrets and variables > Actions** and add these secrets:\n\n### Required (pick one for Claude auth)\n| Secret | Description |\n|--------|------------|\n| `ANTHROPIC_API_KEY` | Anthropic API key - console.anthropic.com |\n| `CLAUDE_CODE_OAUTH_TOKEN` | Alternative: Claude Code OAuth token |\n\n### Recommended (notifications)\n| Secret | Description |\n|--------|------------|\n| `TELEGRAM_BOT_TOKEN` | Telegram bot token |\n| `TELEGRAM_CHAT_ID` | Telegram chat ID |\n| `DISCORD_WEBHOOK_URL` | Discord webhook URL |\n| `SLACK_WEBHOOK_URL` | Slack webhook URL |\n\n### Required by your enabled skills\n${one row per detected env var, with the list of skills that reference it}\n\n## Fleet Parent\nManaged by `${PARENT_UPSTREAM}`. The parent can dispatch skills and monitor health via `fleet-control`.\n\n## Security Note\nThis instance has NO access to the parent's secrets. Each instance maintains its own API keys and credentials.\n```\n\nIf no env vars are detected beyond the required\u002Frecommended set, omit the \"Required by your enabled skills\" section header (don't leave an empty table).\n\n#### 6c. Update `CLAUDE.md` idempotently\n\nFind the heading line `## About This Repo` (or the first `## ` section if not present). Under it, insert exactly one line:\n```\n- Managed instance of ${PARENT_UPSTREAM}. Purpose: ${PURPOSE}.\n```\n\nIf a line starting with `- Managed instance of` already exists, replace it rather than appending a duplicate.\n\n#### 6d. Reset child memory\n\nThe child starts with a clean slate:\n\n1. Reset `memory\u002FMEMORY.md` to a minimal template with Write (PARENT_UPSTREAM and PURPOSE written in literally):\n   ```markdown\n   # Long-term Memory\n   *Last consolidated: never*\n\n   ## About This Repo\n   - Aeon instance of \u003CPARENT_UPSTREAM>. Purpose: \u003CPURPOSE>.\n\n   ## Next Priorities\n   - Configure secrets per SETUP.md\n   - Wait for first scheduled skill to run\n   ```\n2. Clear logs, state and topics, safe paths only, never following symlinks, in one call: it deletes every regular file under `memory\u002Flogs`, `memory\u002Ftopics` and `memory\u002Fissues` (except files named `INDEX.md`), and removes `memory\u002Finstances.json` (the child has no fleet of its own). Missing directories are skipped:\n   ```bash\n   python3 -c 'import os; r=\"\u002Ftmp\u002Fspawn-instance-work\u002Frepo\u002Fmemory\"; [os.remove(p) for s in (\"logs\", \"topics\", \"issues\") for dp, _, fs in os.walk(os.path.join(r, s)) for f in fs for p in [os.path.join(dp, f)] if os.path.isfile(p) and not os.path.islink(p) and not (s == \"issues\" and f == \"INDEX.md\")]; j=os.path.join(r, \"instances.json\"); os.path.lexists(j) and os.remove(j)'\n   ```\n3. If `memory\u002Fissues\u002FINDEX.md` exists (check with Glob), overwrite it with Write as the single line `# Issues - none open`.\n4. Write `memory\u002Fcron-state.json` as `{}` with Write.\n\n#### 6e. Commit and push\n\nEach its own call, with PURPOSE, the skills list and PARENT_UPSTREAM written in literally:\n```bash\ngit -C \u002Ftmp\u002Fspawn-instance-work\u002Frepo add -A\n```\n```bash\ngit -C \u002Ftmp\u002Fspawn-instance-work\u002Frepo commit -m \"chore: configure instance - \u003CPURPOSE>\n\nSkills enabled: \u003CSKILLS_ENABLED_CSV>\nParent: \u003CPARENT_UPSTREAM>\nSpawned: ${today}\"\n```\n```bash\ngit -C \u002Ftmp\u002Fspawn-instance-work\u002Frepo push origin main\n```\nIf that push fails, try:\n```bash\ngit -C \u002Ftmp\u002Fspawn-instance-work\u002Frepo push origin HEAD:main\n```\nIf that fails too, log `SPAWN_PUSH_FAILED` and stop.\n\nIf push fails, **do not delete the fork** — leave it for manual inspection and notify with:\n```\nspawn-instance: fork created but push failed for ${OWNER}\u002F${REPO_NAME}.\nRecover with: gh repo clone ${OWNER}\u002F${REPO_NAME} && push manually, then re-register.\n```\n\n### 7. Enable GitHub Actions on the fork\n\nForks have Actions disabled by default. Use **typed** booleans (`-F`, not `-f`, or `enabled=true` is sent as the string \"true\"):\n\n```bash\ngh api repos\u002F\u003COWNER>\u002F\u003CREPO_NAME>\u002Factions\u002Fpermissions -X PUT \\\n  -F enabled=true -f allowed_actions=all\n```\nIf it fails, log `SPAWN_ACTIONS_FAILED` and stop.\n\n### 8. Post-flight verification\n\nThree separate calls. Fork reachable:\n```bash\ngh api repos\u002F\u003COWNER>\u002F\u003CREPO_NAME> --jq '.full_name'\n```\nIf it fails, log `SPAWN_API_ERROR: post-flight fork check failed` and stop. Our commit is HEAD:\n```bash\ngh api repos\u002F\u003COWNER>\u002F\u003CREPO_NAME>\u002Fcommits\u002Fmain --jq '.sha'\n```\nIt prints HEAD_SHA. If it fails or prints nothing, log `SPAWN_API_ERROR: post-flight HEAD check failed` and stop. Actions enabled:\n```bash\ngh api repos\u002F\u003COWNER>\u002F\u003CREPO_NAME>\u002Factions\u002Fpermissions --jq '.enabled'\n```\nIf it does not print `true`, log `SPAWN_ACTIONS_FAILED: post-flight` and stop.\n\n### 9. Register the instance\n\nUpdate `memory\u002Finstances.json` in the **parent** repo. Append:\n```json\n{\n  \"name\": \"${NAME}\",\n  \"repo\": \"${OWNER}\u002F${REPO_NAME}\",\n  \"purpose\": \"${PURPOSE}\",\n  \"created\": \"${today}\",\n  \"status\": \"pending_secrets\",\n  \"skills_enabled\": ${SKILLS_ENABLED_JSON},\n  \"parent\": \"${PARENT_UPSTREAM}\"\n}\n```\n\nIf `FORK_STATE == \"exists\"` at step 5, the final exit status is `SPAWN_FORK_EXISTS_RECOVERED`, otherwise `SPAWN_OK`.\n\n### 10. Log to memory\n\nAppend to `memory\u002Flogs\u002F${today}.md`:\n```\n### spawn-instance\n- Status: ${EXIT_CODE}\n- Instance: ${OWNER}\u002F${REPO_NAME}\n- Purpose: ${PURPOSE}\n- Skills: ${SKILLS_ENABLED_CSV}\n- Dropped skills: ${DROPPED_CSV or \"(none)\"}\n- Actions enabled: yes\n```\n\n### 11. Notify via `.\u002Fnotify`\n\nOn success (`SPAWN_OK` or `SPAWN_FORK_EXISTS_RECOVERED`):\n```\n*New Aeon Instance*\n\nRepo: ${OWNER}\u002F${REPO_NAME}\nPurpose: ${PURPOSE}\nSkills (${N}): ${SKILLS_ENABLED_CSV}\nStatus: ${EXIT_CODE} - PENDING SECRETS\n\nActivate:\n1. https:\u002F\u002Fgithub.com\u002F${OWNER}\u002F${REPO_NAME}\u002Fsettings\u002Fsecrets\u002Factions\n2. Add ANTHROPIC_API_KEY (or CLAUDE_CODE_OAUTH_TOKEN)\n3. Add TELEGRAM_BOT_TOKEN + TELEGRAM_CHAT_ID (or Discord\u002FSlack)\n\nSee SETUP.md in the repo for the full secret list tailored to your enabled skills.\n```\n\nOn refusal (`SPAWN_FORK_EXISTS_REGISTERED`, `SPAWN_INVALID_VAR`, `SPAWN_NO_SKILLS`):\n```\nspawn-instance: ${EXIT_CODE} - ${one-line reason}. No changes made.\n```\n\nOn failure (`SPAWN_FORK_FAILED`, `SPAWN_PUSH_FAILED`, `SPAWN_ACTIONS_FAILED`, `SPAWN_API_ERROR`):\n```\nspawn-instance FAILED: ${EXIT_CODE}\nTarget: ${OWNER}\u002F${REPO_NAME}\nRecovery: ${one-line recovery instruction}\n```\n\n## Network note\n\nThis skill runs entirely through `gh` CLI, which handles auth internally, so no bare `$SECRET` ever lands on the command line for the Bash permission layer to refuse. No WebFetch fallback needed. If `gh` is missing or unauthenticated, the pre-flight step fails with `SPAWN_API_ERROR`.\n\n## Constraints\n\n- **No secret propagation.** Never read or write `ANTHROPIC_API_KEY`, `TELEGRAM_*`, `DISCORD_*`, `SLACK_*`, or any API key into the child repo. The whole security model depends on this.\n- **No hardcoded skill list.** Always enumerate `skills\u002F*\u002FSKILL.md` at runtime to avoid referencing renamed or removed skills.\n- **Idempotent.** Re-running with the same `${var}` must never produce duplicate registry entries, duplicate CLAUDE.md lines, or a second fork.\n- **Never delete a fork.** If anything fails partway through, leave the fork in place and emit recovery guidance — the operator is the only party authorized to delete it.\n- **Never push to the parent without committing `memory\u002Finstances.json` via the normal Aeon workflow.** The parent commit happens through the same path as any other skill output.\n\nWrite complete, working code. No TODOs or placeholders.\n",{"name":5,"metadata":43,"description":7},{"var":44,"tags":45,"title":46,"category":28},"",[29],"Spawn Instance","main","504a21d53c0c9b485f6e90c43db83000825e1d3c","skills\u002Fspawn-instance",308,"https:\u002F\u002Fgithub.com\u002Faeonfun\u002Faeon","https:\u002F\u002Fwww.aeon.fun\u002F","https:\u002F\u002Fgithub.com\u002Faeonfun","The most autonomous agent framework.","2026-11-15 03:40:18",{"source":8,"skillName":5,"commands":57,"prompt":67,"zipAvailable":68},[58,61,64],{"tool":59,"command":60},"npx","npx skills add aeonfun\u002Faeon --skill spawn-instance",{"tool":62,"command":63},"bunx","bunx skills add aeonfun\u002Faeon --skill spawn-instance",{"tool":65,"command":66},"pnpm","pnpm dlx skills add aeonfun\u002Faeon --skill spawn-instance","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Faeonfun\u002Faeon\u002Fblob\u002Fmain\u002Fskills\u002Fspawn-instance\u002FSKILL.md",true,[],[71,78,84,90,96,102],{"skillNo":72,"name":73,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":77},"01M7DSM3QWBJ44FKRMDDRAGNET","Warn Mixed Script","https:\u002F\u002Fgithub.com\u002Faeonfun\u002Faeon\u002Fblob\u002Fmain\u002Fscripts\u002Ftests\u002Fskill-scan-fixtures\u002Fwarn-mixed-script\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":79,"name":80,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":77},"01M7DSM0496DRYYW5A4NAAHZDX","Warn Hidden CSS","https:\u002F\u002Fgithub.com\u002Faeonfun\u002Faeon\u002Fblob\u002Fmain\u002Fscripts\u002Ftests\u002Fskill-scan-fixtures\u002Fwarn-hidden-css\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":77},"01M7DSKWCGDVYZSDJM31YHS2JB","Malicious Injection Uppercase","https:\u002F\u002Fgithub.com\u002Faeonfun\u002Faeon\u002Fblob\u002Fmain\u002Fscripts\u002Ftests\u002Fskill-scan-fixtures\u002Fmalicious-injection-uppercase\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":77},"01M7DSKRV2RRA1V0HK13KYWJXD","Malicious Injection Homoglyph","https:\u002F\u002Fgithub.com\u002Faeonfun\u002Faeon\u002Fblob\u002Fmain\u002Fscripts\u002Ftests\u002Fskill-scan-fixtures\u002Fmalicious-injection-homoglyph\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":77},"01M7DSKMXJKY0167YHVCKF7B49","Malicious Injection Disregard Prior","https:\u002F\u002Fgithub.com\u002Faeonfun\u002Faeon\u002Fblob\u002Fmain\u002Fscripts\u002Ftests\u002Fskill-scan-fixtures\u002Fmalicious-injection-disregard-prior\u002FSKILL.md",[],[],{"skillNo":103,"name":104,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":77},"01M7DSKGFQ5V2VNSA4K97CVFMB","Benign Greek Math","https:\u002F\u002Fgithub.com\u002Faeonfun\u002Faeon\u002Fblob\u002Fmain\u002Fscripts\u002Ftests\u002Fskill-scan-fixtures\u002Fbenign-greek-math\u002FSKILL.md",[],[]]