[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AGD6NJGDS33Y2EWAVWS4SN":3,"skill-same:01M7AGD6NJGDS33Y2EWAVWS4SN":48},{"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":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M7AGD6NJGDS33Y2EWAVWS4SN","secretzero-agent",null,"Use for agentic and operational SecretZero workflows including unified\n`agent sync`, CLI\u002FAPI\u002FMCP parity, secure human-in-the-loop vectors, and\nautomation-safe run loops.","zloeber\u002FSecretZero","zloeber","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F4702624?v=4","01M7AGCEQ32CCAQKAJJ3NS7BE3","Zachary Loeber","01M7AGCEQV5M7FRW8FYTJQAM64",8,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fzloeber\u002FSecretZero\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fsecretzero-agent\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: secretzero-agent\ndescription: |\n  Use for agentic and operational SecretZero workflows including unified\n  `agent sync`, CLI\u002FAPI\u002FMCP parity, secure human-in-the-loop vectors, and\n  automation-safe run loops.\n---\n\n# SecretZero Agent Skill\n\nUse this skill when running SecretZero in agentic workflows (manual-assisted, web-assisted, or fully automated), or when guiding users through runtime usage scenarios.\n\n## Install \u002F Verify\n\nPreferred install:\n\n```bash\nuv tool install -U \"secretzero[all]\"\n```\n\nLean or provider-specific installs:\n\n```bash\nuv tool install -U secretzero\nuv tool install -U \"secretzero[aws]\"\nuv tool install -U \"secretzero[azure]\"\n```\n\nAlternative:\n\n```bash\npip install -U \"secretzero[all]\"\n```\n\nVerify CLI:\n\n```bash\nsecretzero --help\nsecretzero agent sync --help\n```\n\n### MCP host (optional)\n\nWhen the agent host exposes SecretZero MCP tools (`secretzero-mcp`):\n\n```bash\nuv tool install -U \"secretzero[mcp]\"\nsecretzero mcp config generate --workspace \u002Fpath\u002Fto\u002Frepo --format cursor\n```\n\nSee `docs\u002Fmcp-setup.md`. The MCP server sets **`SZ_AGENT_MODE=true`** by default (same spill contract as `skills\u002Fsecretzero-handle\u002FSKILL.md`). Prefer `secretzero mcp serve`; `secretzero-mcp` remains a deprecated wrapper.\n\n## Core Agent Contract\n\n**Absolute rule:** `skills\u002Fsecretzero\u002FSKILL.md` — never consume secrets in context; use SecretZero for all handling (`agent sync`, `--web`, validate, status). Never request, receive, or print plaintext secret values.\n- Prefer JSON output for machine handling.\n- When running in automation or spill-sensitive hosts, set **`SZ_AGENT_MODE=true`** so the CLI blocks or redacts commands that would dump secret-bearing config (see `skills\u002Fsecretzero-handle\u002FSKILL.md`).\n- Use the unified entrypoint:\n\n```bash\nsecretzero agent sync --json [--web] [--dry-run] [--verbose]\n```\n\n## Three Usage Vectors\n\n1. **Human-instructed (Vector 1)**\n   - Run `secretzero agent sync --json`.\n   - Relay `pending_secrets[].summary` and ordered `steps` exactly.\n   - Re-run until clean.\n\n2. **Secure local web capture (Vector 2)**\n   - Run `secretzero agent sync --web` (add `--json` only when you also need structured stdout after the run finishes).\n   - **Do not block the whole agent session on the foreground TTY if your environment allows it:** start the command in a **background terminal** (or equivalent job control) on the operator’s machine so the process can stay alive until the form is submitted, and **capture stdout** if you need to quote the URL line back reliably.\n   - When the CLI prints the localhost URL, **relay the complete URL verbatim** to the user (scheme, host, port, and path — no truncation). Vector 2 binds to `127.0.0.1`; the printed URL is the handoff surface (this is **not** the same as `secretzero web`, which uses a separate **bootstrap token** for the network dashboard — if you use that command, pass through its **full login URL including the token** per that command’s output).\n   - Remind the operator **not to paste secret values into chat**; only the URL and UI instructions belong in the agent thread.\n   - Remind the operator to **submit the form once** and close the browser tab when done: the CLI helper **stops the temporary localhost server** after a successful submit; if they walk away, **Ctrl+C** (or waiting for timeout) ends the wait.\n   - **API Vector 2:** `POST \u002Fagent\u002Fsync` with `web: true` returns `web_url` and `web_session_id` — give the operator the **exact `web_url`**, poll `GET \u002Fagent\u002Fsync\u002Fweb\u002F{web_session_id}` until `done`, and treat the session id as sensitive correlation data. The API process may keep that localhost port open until restart; do not forward `web_url` beyond the trusted operator.\n   - Poll\u002Fre-run `agent sync --json` until `pending_secrets` clears.\n\n3. **Fully automated (Vector 3)**\n   - Ensure provider auth is available (and optionally `SZ_AGENT=true`).\n   - Run `secretzero agent sync --json`.\n   - Handle `failed_secrets` with manifest fixes and retry.\n\n## Agent runtime integration\n\nWhen bootstrapping or restoring Hermes\u002FOpenClaw installs:\n\n```bash\nsecretzero agent list --format json\nsecretzero agent adopt --dry-run --format json\nsecretzero agent adopt --preseed-lockfile --format json\n```\n\nLoad `skills\u002Fsecretzero-agent-adopt\u002FSKILL.md` for the full adopt\u002Frestore playbook. `agent backup` is an alias of `agent adopt` (not `secretzero backup create`).\n\n## Standard Agent Loop\n\n1. Run `secretzero agent sync --json` first; escalate to `--web` when you need the localhost form (see Vector 2 handoff above).\n2. Parse status and `pending_secrets`\u002F`failed_secrets`.\n3. Execute the appropriate vector behavior.\n4. Re-run command until both arrays are empty.\n5. Continue downstream only after clean completion.\n\n## API Parity\n\nUse API when running remote orchestration:\n\n- `POST \u002Fagent\u002Fsync` with `{ dry_run, web, lockfile?, sz_agent? }`\n- For Vector 2 polling: `GET \u002Fagent\u002Fsync\u002Fweb\u002F{session_id}`\n\nTreat API payload semantics the same as CLI semantics.\n\n## MCP operational tools\n\nWhen MCP tools are available, prefer them for **metadata-only** maintenance (hashes, counts, drift — never values):\n\n| MCP tool | CLI parity | Use for |\n|----------|------------|---------|\n| `sz_status` | `secretzero status --format json` | Preflight, lockfile hashes, per-target sync state |\n| `sz_sync` | `secretzero sync --format json` | Reconcile targets (non-interactive; prompts disabled) |\n| `sz_rotate` | `secretzero rotate --format json` | Rotation policy execution |\n| `sz_drift_check` | `secretzero drift --format json` | External target drift |\n| `sz_discover` | `secretzero discover --format json` | Credential inventory during authoring (see `secretzero-author`) |\n\nPass `environment` and `var_files` on MCP tools for multi-environment lanes (same semantics as CLI `--environment` \u002F `--var-file`). Set `SZ_WORKSPACE` (or tool `workspace`) to the repo root.\n\n**MCP gap — bootstrap \u002F human seeding:** MCP does **not** expose `agent sync` (Vectors 1–3) or `--web`. For pending manual secrets, first-time bootstrap, or Vector 2 localhost forms, use:\n\n```bash\nsecretzero agent sync --json [--web]\n```\n\nor API `POST \u002Fagent\u002Fsync` with `{ \"web\": true }` when remote.\n\n**Agent loop with MCP:** run **`agent sync --json`** until `pending_secrets` \u002F `failed_secrets` are empty; then use `sz_status` \u002F `sz_sync` \u002F `sz_drift_check` for ongoing operations.\n\n## Operational Playbooks\n\n- **Agent adopt (Hermes\u002FOpenClaw):** see `skills\u002Fsecretzero-agent-adopt\u002FSKILL.md` — `agent list` → `agent adopt` → `agent sync`\n- **Bootstrap:** `validate` -> `init --install` -> `test` -> `agent sync --json`\n- **Preflight:** `sz_status` or `secretzero status --format json`; dry-run via `sz_sync` (`dry_run: true`) or `secretzero sync --dry-run`\n- **Maintenance:** `sz_rotate` \u002F `sz_drift_check` or CLI `secretzero rotate`, `secretzero drift`\n\n## Common Failure Handling\n\n- Missing extras\u002Fprovider dependencies -> run install\u002F`secretzero init --install`\n- Auth missing\u002Fexpired -> fix provider auth, re-run `secretzero test`\n- Manual-seeded secret lacks instructions -> add `agent_instructions`, retry\n- Variable interpolation issues -> check vars and `--var-file` usage\n\n## Definition of Done\n\n- Secret bootstrap\u002Fsync flow reaches no pending or failed secrets.\n- Workflow used secure vector handling with no secret leakage.\n- CLI\u002FAPI\u002FMCP behavior stays consistent for the selected scenario.\n","# SecretZero Agent Skill\n\nUse this skill when running SecretZero in agentic workflows (manual-assisted, web-assisted, or fully automated), or when guiding users through runtime usage scenarios.\n\n## Install \u002F Verify\n\nPreferred install:\n\n```bash\nuv tool install -U \"secretzero[all]\"\n```\n\nLean or provider-specific installs:\n\n```bash\nuv tool install -U secretzero\nuv tool install -U \"secretzero[aws]\"\nuv tool install -U \"secretzero[azure]\"\n```\n\nAlternative:\n\n```bash\npip install -U \"secretzero[all]\"\n```\n\nVerify CLI:\n\n```bash\nsecretzero --help\nsecretzero agent sync --help\n```\n\n### MCP host (optional)\n\nWhen the agent host exposes SecretZero MCP tools (`secretzero-mcp`):\n\n```bash\nuv tool install -U \"secretzero[mcp]\"\nsecretzero mcp config generate --workspace \u002Fpath\u002Fto\u002Frepo --format cursor\n```\n\nSee `docs\u002Fmcp-setup.md`. The MCP server sets **`SZ_AGENT_MODE=true`** by default (same spill contract as `skills\u002Fsecretzero-handle\u002FSKILL.md`). Prefer `secretzero mcp serve`; `secretzero-mcp` remains a deprecated wrapper.\n\n## Core Agent Contract\n\n**Absolute rule:** `skills\u002Fsecretzero\u002FSKILL.md` — never consume secrets in context; use SecretZero for all handling (`agent sync`, `--web`, validate, status). Never request, receive, or print plaintext secret values.\n- Prefer JSON output for machine handling.\n- When running in automation or spill-sensitive hosts, set **`SZ_AGENT_MODE=true`** so the CLI blocks or redacts commands that would dump secret-bearing config (see `skills\u002Fsecretzero-handle\u002FSKILL.md`).\n- Use the unified entrypoint:\n\n```bash\nsecretzero agent sync --json [--web] [--dry-run] [--verbose]\n```\n\n## Three Usage Vectors\n\n1. **Human-instructed (Vector 1)**\n   - Run `secretzero agent sync --json`.\n   - Relay `pending_secrets[].summary` and ordered `steps` exactly.\n   - Re-run until clean.\n\n2. **Secure local web capture (Vector 2)**\n   - Run `secretzero agent sync --web` (add `--json` only when you also need structured stdout after the run finishes).\n   - **Do not block the whole agent session on the foreground TTY if your environment allows it:** start the command in a **background terminal** (or equivalent job control) on the operator’s machine so the process can stay alive until the form is submitted, and **capture stdout** if you need to quote the URL line back reliably.\n   - When the CLI prints the localhost URL, **relay the complete URL verbatim** to the user (scheme, host, port, and path — no truncation). Vector 2 binds to `127.0.0.1`; the printed URL is the handoff surface (this is **not** the same as `secretzero web`, which uses a separate **bootstrap token** for the network dashboard — if you use that command, pass through its **full login URL including the token** per that command’s output).\n   - Remind the operator **not to paste secret values into chat**; only the URL and UI instructions belong in the agent thread.\n   - Remind the operator to **submit the form once** and close the browser tab when done: the CLI helper **stops the temporary localhost server** after a successful submit; if they walk away, **Ctrl+C** (or waiting for timeout) ends the wait.\n   - **API Vector 2:** `POST \u002Fagent\u002Fsync` with `web: true` returns `web_url` and `web_session_id` — give the operator the **exact `web_url`**, poll `GET \u002Fagent\u002Fsync\u002Fweb\u002F{web_session_id}` until `done`, and treat the session id as sensitive correlation data. The API process may keep that localhost port open until restart; do not forward `web_url` beyond the trusted operator.\n   - Poll\u002Fre-run `agent sync --json` until `pending_secrets` clears.\n\n3. **Fully automated (Vector 3)**\n   - Ensure provider auth is available (and optionally `SZ_AGENT=true`).\n   - Run `secretzero agent sync --json`.\n   - Handle `failed_secrets` with manifest fixes and retry.\n\n## Agent runtime integration\n\nWhen bootstrapping or restoring Hermes\u002FOpenClaw installs:\n\n```bash\nsecretzero agent list --format json\nsecretzero agent adopt --dry-run --format json\nsecretzero agent adopt --preseed-lockfile --format json\n```\n\nLoad `skills\u002Fsecretzero-agent-adopt\u002FSKILL.md` for the full adopt\u002Frestore playbook. `agent backup` is an alias of `agent adopt` (not `secretzero backup create`).\n\n## Standard Agent Loop\n\n1. Run `secretzero agent sync --json` first; escalate to `--web` when you need the localhost form (see Vector 2 handoff above).\n2. Parse status and `pending_secrets`\u002F`failed_secrets`.\n3. Execute the appropriate vector behavior.\n4. Re-run command until both arrays are empty.\n5. Continue downstream only after clean completion.\n\n## API Parity\n\nUse API when running remote orchestration:\n\n- `POST \u002Fagent\u002Fsync` with `{ dry_run, web, lockfile?, sz_agent? }`\n- For Vector 2 polling: `GET \u002Fagent\u002Fsync\u002Fweb\u002F{session_id}`\n\nTreat API payload semantics the same as CLI semantics.\n\n## MCP operational tools\n\nWhen MCP tools are available, prefer them for **metadata-only** maintenance (hashes, counts, drift — never values):\n\n| MCP tool | CLI parity | Use for |\n|----------|------------|---------|\n| `sz_status` | `secretzero status --format json` | Preflight, lockfile hashes, per-target sync state |\n| `sz_sync` | `secretzero sync --format json` | Reconcile targets (non-interactive; prompts disabled) |\n| `sz_rotate` | `secretzero rotate --format json` | Rotation policy execution |\n| `sz_drift_check` | `secretzero drift --format json` | External target drift |\n| `sz_discover` | `secretzero discover --format json` | Credential inventory during authoring (see `secretzero-author`) |\n\nPass `environment` and `var_files` on MCP tools for multi-environment lanes (same semantics as CLI `--environment` \u002F `--var-file`). Set `SZ_WORKSPACE` (or tool `workspace`) to the repo root.\n\n**MCP gap — bootstrap \u002F human seeding:** MCP does **not** expose `agent sync` (Vectors 1–3) or `--web`. For pending manual secrets, first-time bootstrap, or Vector 2 localhost forms, use:\n\n```bash\nsecretzero agent sync --json [--web]\n```\n\nor API `POST \u002Fagent\u002Fsync` with `{ \"web\": true }` when remote.\n\n**Agent loop with MCP:** run **`agent sync --json`** until `pending_secrets` \u002F `failed_secrets` are empty; then use `sz_status` \u002F `sz_sync` \u002F `sz_drift_check` for ongoing operations.\n\n## Operational Playbooks\n\n- **Agent adopt (Hermes\u002FOpenClaw):** see `skills\u002Fsecretzero-agent-adopt\u002FSKILL.md` — `agent list` → `agent adopt` → `agent sync`\n- **Bootstrap:** `validate` -> `init --install` -> `test` -> `agent sync --json`\n- **Preflight:** `sz_status` or `secretzero status --format json`; dry-run via `sz_sync` (`dry_run: true`) or `secretzero sync --dry-run`\n- **Maintenance:** `sz_rotate` \u002F `sz_drift_check` or CLI `secretzero rotate`, `secretzero drift`\n\n## Common Failure Handling\n\n- Missing extras\u002Fprovider dependencies -> run install\u002F`secretzero init --install`\n- Auth missing\u002Fexpired -> fix provider auth, re-run `secretzero test`\n- Manual-seeded secret lacks instructions -> add `agent_instructions`, retry\n- Variable interpolation issues -> check vars and `--var-file` usage\n\n## Definition of Done\n\n- Secret bootstrap\u002Fsync flow reaches no pending or failed secrets.\n- Workflow used secure vector handling with no secret leakage.\n- CLI\u002FAPI\u002FMCP behavior stays consistent for the selected scenario.\n",{"name":5,"description":7},"main","a682dba45de8f378811b7c88ac060527ce90a912",".agents\u002Fskills\u002Fsecretzero-agent",0,"https:\u002F\u002Fgithub.com\u002Fzloeber\u002FSecretZero","https:\u002F\u002Fsecret0.com\u002F","https:\u002F\u002Fgithub.com\u002Fzloeber","https:\u002F\u002Fblog.zacharyloeber.com","Infrastructure and cloud solutions architect. Automation engineer. Professional complexity eater.","2026-10-31 22:04:55",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add zloeber\u002FSecretZero --skill secretzero-agent",{"tool":40,"command":41},"bunx","bunx skills add zloeber\u002FSecretZero --skill secretzero-agent",{"tool":43,"command":44},"pnpm","pnpm dlx skills add zloeber\u002FSecretZero --skill secretzero-agent","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzloeber\u002FSecretZero\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fsecretzero-agent\u002FSKILL.md",true,[],[49,56,63,70,75,82],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":19},"01M7AGFT72DBDAFDCCS2SCY12Q","secretzero","Compatibility entrypoint for SecretZero skills. Enforces the absolute rule:\nnever consume secrets in agent context — use SecretZero for all secret\nhandling. Routes to secretzero-author, secretzero-agent, secretzero-handle,\nand secretzero-agent-adopt.","https:\u002F\u002Fgithub.com\u002Fzloeber\u002FSecretZero\u002Fblob\u002Fmain\u002Fsrc\u002Fsecretzero\u002Fdata\u002Fskills\u002Fsecretzero\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M7AGFNGG84QMWQ97NP7SAQZE","secretzero-handle","Use when the task touches `.env`, dotenv\u002Fjson\u002Fyaml secret files, local `file` targets,\nor any workflow where secret material could enter agent context. Enforces\n`SZ_AGENT_MODE=true` spill-safe CLI usage, ingest preseed, strict manifest validation,\nand safe discovery patterns alongside `secretzero-agent` \u002F `secretzero-author`.","https:\u002F\u002Fgithub.com\u002Fzloeber\u002FSecretZero\u002Fblob\u002Fmain\u002Fsrc\u002Fsecretzero\u002Fdata\u002Fskills\u002Fsecretzero-handle\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M7AGFDSKKWBQY3F3KE1DTVCE","secretzero-author","Use when authoring, reviewing, or walking a user through a new or existing\n`Secretfile.yml`. Guided session: manifest root, inventory table, optional\nlocal discovery, add\u002Fedit loop with secret-type and target menus, validate,\noptional `secretzero web`. Hermes + MCP notes included. Safe contextless\ndiscovery, `.szvar` lanes, policy-bound targets. Inherits absolute rule from\n`skills\u002Fsecretzero\u002FSKILL.md`. Co-load `skills\u002Fsecretzero-handle\u002FSKILL.md`\nfor `.env` \u002F spill-safe CLI.","https:\u002F\u002Fgithub.com\u002Fzloeber\u002FSecretZero\u002Fblob\u002Fmain\u002Fsrc\u002Fsecretzero\u002Fdata\u002Fskills\u002Fsecretzero-author\u002FSKILL.md",[],[],{"skillNo":71,"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":72,"categories":73,"keywords":74,"publishedAt":19},"01M7AGFAAKHFGJWNPE0R6Q6PT9","https:\u002F\u002Fgithub.com\u002Fzloeber\u002FSecretZero\u002Fblob\u002Fmain\u002Fsrc\u002Fsecretzero\u002Fdata\u002Fskills\u002Fsecretzero-agent\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M7AGF6EQTHKAE55FJA8M23PM","secretzero-agent-adopt","Use for agent runtime integration: discover Hermes\u002FOpenClaw installs,\nbootstrap SecretZero environments with `secretzero agent list` \u002F `agent adopt`,\nlockfile preseed, and restore loops. Inherits absolute rule from\n`skills\u002Fsecretzero\u002FSKILL.md` (SecretZero only; never secrets in context).","https:\u002F\u002Fgithub.com\u002Fzloeber\u002FSecretZero\u002Fblob\u002Fmain\u002Fsrc\u002Fsecretzero\u002Fdata\u002Fskills\u002Fsecretzero-agent-adopt\u002FSKILL.md",[],[],{"skillNo":83,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M7AGF26S7HJT7571JWGV2E53","https:\u002F\u002Fgithub.com\u002Fzloeber\u002FSecretZero\u002Fblob\u002Fmain\u002Fskills\u002Fsecretzero\u002FSKILL.md",[],[]]