[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M73DFSDC3N09ZEW5ATCD81H9":3,"skill-same:01M73DFSDC3N09ZEW5ATCD81H9":49},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":30,"ownerHtmlUrl":31,"ownerBlogUrl":32,"ownerDescription":33,"updatedAt":34,"install":35,"resources":48},"01M73DFSDC3N09ZEW5ATCD81H9","langchain-ai--openwiki",null,"Use when the user wants to generate or keep repository documentation up to date via OpenWiki (langchain-ai\u002Fopenwiki) — an LLM-driven CLI that writes a wiki for a codebase (or a personal knowledge base from Notion\u002FGmail\u002FSlack\u002FX\u002Fweb search) and keeps it fresh via a scheduled CI pull request. Examples: \"set up OpenWiki for this repo\", \"keep the docs updated automatically\", \"generate an agent wiki\".","Horonomos-laps\u002FYana-AI","Horonomos-laps","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F355299122?v=4","01M76B3QPXE88ET2SQPDPVATZT"," Horonomos-laps","01M72ZQRJPCYPSSWT4D00VJR2A",13,"MIT","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Flangchain-ai--openwiki\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: langchain-ai--openwiki\ndescription: \"Use when the user wants to generate or keep repository documentation up to date via OpenWiki (langchain-ai\u002Fopenwiki) — an LLM-driven CLI that writes a wiki for a codebase (or a personal knowledge base from Notion\u002FGmail\u002FSlack\u002FX\u002Fweb search) and keeps it fresh via a scheduled CI pull request. Examples: \\\"set up OpenWiki for this repo\\\", \\\"keep the docs updated automatically\\\", \\\"generate an agent wiki\\\".\"\norigin: https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Fopenwiki\nlicense: MIT\n---\n\n# OpenWiki (langchain-ai\u002Fopenwiki)\n\nCLI that writes and maintains an **agent wiki** for a codebase, or a personal\nknowledge wiki from configured connectors (Notion, Gmail, Slack, X, web\nsearch, Hacker News). Unlike a purely graph\u002Findex-based tool, OpenWiki uses an\nLLM to *synthesize* documentation from ingested sources, and ships a CI\nworkflow to keep that documentation current automatically.\n\nNot a duplicate of `gitnexus-cli` in this repo: GitNexus builds a knowledge\ngraph + embeddings for structural code queries; OpenWiki synthesizes prose\ndocumentation via an LLM and can pull from non-code sources too. Use GitNexus\nfor \"trace calls to X\" style structural queries, OpenWiki for \"keep readable\ndocs current.\"\n\n## Install\n\n```bash\nnpm install -g openwiki\n# or: pnpm add -g openwiki\n```\n\nBun install can fall back to compiling a native `better-sqlite3` dependency —\nprefer npm\u002Fpnpm unless Visual Studio Build Tools (Windows) or build essentials\nare already set up.\n\n## Two modes — pick one explicitly\n\n```bash\nopenwiki code --init        # repository documentation, written to openwiki\u002F\nopenwiki personal --init    # personal knowledge wiki, written to ~\u002F.openwiki\u002Fwiki\u002F\n```\n\nBare `openwiki --init` is not supported — mode is required on init.\n\n## Commands\n\n| Command | Effect |\n|---|---|\n| `openwiki` | Interactive CLI, stays open for follow-up messages |\n| `openwiki \"\u003Crequest>\"` | Interactive, with an initial request |\n| `openwiki -p \"\u003Crequest>\"` | One-shot, non-interactive, prints final output and exits |\n| `openwiki code --update` | Refresh repo docs (creates them first if missing) |\n| `openwiki --update` | Refresh personal wiki (defaults to personal mode) |\n| `openwiki auth \u003Cslack\\|gmail\\|x\\|notion>` | Authenticate a connector |\n| `openwiki ngrok start` | Tunnel for Slack OAuth callback during first-time auth |\n| `openwiki --help` | Full command reference |\n\nIn an interactive session: `\u002Fapi-key` updates the provider key, `\u002Flangsmith-key`\nsets\u002Fclears optional LangSmith tracing credentials. Both use masked prompts —\n**never paste a real key into a non-interactive transcript this skill's own\nguidance produces**; direct the user to run these interactively themselves.\n\n## CI auto-update (the main reason to reach for this over a one-off doc gen)\n\nCopy the example workflow into the target repo so docs stay current without\nmanual reruns:\n\n- GitHub Actions: `examples\u002Fopenwiki-update.yml` → `.github\u002Fworkflows\u002Fopenwiki-update.yml`\n- GitLab CI: `examples\u002Fopenwiki-update.gitlab-ci.yml` → include from `.gitlab-ci.yml`\n\nIn CI, use `openwiki code --update --print` — `--update` creates the initial\n`openwiki\u002F` docs if none exist yet, so `--init` isn't needed in that path, as\nlong as the workflow provides the provider\u002Fmodel env vars. The scheduled run\nopens a PR\u002FMR with the documentation delta, not a direct push to the default\nbranch.\n\n## AGENTS.md \u002F CLAUDE.md integration\n\nEach `code` run maintains both files at the repo root inside a managed\n`\u003C!-- OPENWIKI:START -->…\u003C!-- OPENWIKI:END -->` block — created if absent,\notherwise only that block is rewritten and the rest of the file is left\nalone. Safe to run in a repo that already has a hand-written `CLAUDE.md`.\n\n## Rules\n\n- Mode (`code` vs `personal`) must be explicit on `--init` — don't guess which one the user wants; ask if it's ambiguous from context.\n- Config and secrets land in `~\u002F.openwiki\u002F.env` on the user's own machine — never read, log, or echo this file's contents on the user's behalf.\n- Connector auth (`openwiki auth ...`) opens an interactive OAuth flow — run it and let the user complete auth themselves, don't attempt to script credentials into it.\n- Recommend the CI workflow (auto-PR) over manual reruns when the user's actual goal is \"keep docs from going stale,\" not \"generate docs once.\"\n\n## Anti-patterns\n\n```\n❌ Running `openwiki auth \u003Cprovider>` and trying to supply credentials non-interactively\n❌ Reading\u002Fprinting ~\u002F.openwiki\u002F.env \"to check the config\"\n❌ Suggesting a direct push to main from the CI workflow instead of the tool's own PR\u002FMR flow\n❌ Treating this as a replacement for gitnexus-cli's structural graph queries — different job\n```\n\n## Verification\n\nAfter `openwiki code --init` or `--update`, confirm the `openwiki\u002F` directory\n(or `~\u002F.openwiki\u002Fwiki\u002F` for personal mode) was actually written and `AGENTS.md`\u002F\n`CLAUDE.md` contain the managed block, rather than assuming success from the\nCLI's exit code alone.\n","# OpenWiki (langchain-ai\u002Fopenwiki)\n\nCLI that writes and maintains an **agent wiki** for a codebase, or a personal\nknowledge wiki from configured connectors (Notion, Gmail, Slack, X, web\nsearch, Hacker News). Unlike a purely graph\u002Findex-based tool, OpenWiki uses an\nLLM to *synthesize* documentation from ingested sources, and ships a CI\nworkflow to keep that documentation current automatically.\n\nNot a duplicate of `gitnexus-cli` in this repo: GitNexus builds a knowledge\ngraph + embeddings for structural code queries; OpenWiki synthesizes prose\ndocumentation via an LLM and can pull from non-code sources too. Use GitNexus\nfor \"trace calls to X\" style structural queries, OpenWiki for \"keep readable\ndocs current.\"\n\n## Install\n\n```bash\nnpm install -g openwiki\n# or: pnpm add -g openwiki\n```\n\nBun install can fall back to compiling a native `better-sqlite3` dependency —\nprefer npm\u002Fpnpm unless Visual Studio Build Tools (Windows) or build essentials\nare already set up.\n\n## Two modes — pick one explicitly\n\n```bash\nopenwiki code --init        # repository documentation, written to openwiki\u002F\nopenwiki personal --init    # personal knowledge wiki, written to ~\u002F.openwiki\u002Fwiki\u002F\n```\n\nBare `openwiki --init` is not supported — mode is required on init.\n\n## Commands\n\n| Command | Effect |\n|---|---|\n| `openwiki` | Interactive CLI, stays open for follow-up messages |\n| `openwiki \"\u003Crequest>\"` | Interactive, with an initial request |\n| `openwiki -p \"\u003Crequest>\"` | One-shot, non-interactive, prints final output and exits |\n| `openwiki code --update` | Refresh repo docs (creates them first if missing) |\n| `openwiki --update` | Refresh personal wiki (defaults to personal mode) |\n| `openwiki auth \u003Cslack\\|gmail\\|x\\|notion>` | Authenticate a connector |\n| `openwiki ngrok start` | Tunnel for Slack OAuth callback during first-time auth |\n| `openwiki --help` | Full command reference |\n\nIn an interactive session: `\u002Fapi-key` updates the provider key, `\u002Flangsmith-key`\nsets\u002Fclears optional LangSmith tracing credentials. Both use masked prompts —\n**never paste a real key into a non-interactive transcript this skill's own\nguidance produces**; direct the user to run these interactively themselves.\n\n## CI auto-update (the main reason to reach for this over a one-off doc gen)\n\nCopy the example workflow into the target repo so docs stay current without\nmanual reruns:\n\n- GitHub Actions: `examples\u002Fopenwiki-update.yml` → `.github\u002Fworkflows\u002Fopenwiki-update.yml`\n- GitLab CI: `examples\u002Fopenwiki-update.gitlab-ci.yml` → include from `.gitlab-ci.yml`\n\nIn CI, use `openwiki code --update --print` — `--update` creates the initial\n`openwiki\u002F` docs if none exist yet, so `--init` isn't needed in that path, as\nlong as the workflow provides the provider\u002Fmodel env vars. The scheduled run\nopens a PR\u002FMR with the documentation delta, not a direct push to the default\nbranch.\n\n## AGENTS.md \u002F CLAUDE.md integration\n\nEach `code` run maintains both files at the repo root inside a managed\n`\u003C!-- OPENWIKI:START -->…\u003C!-- OPENWIKI:END -->` block — created if absent,\notherwise only that block is rewritten and the rest of the file is left\nalone. Safe to run in a repo that already has a hand-written `CLAUDE.md`.\n\n## Rules\n\n- Mode (`code` vs `personal`) must be explicit on `--init` — don't guess which one the user wants; ask if it's ambiguous from context.\n- Config and secrets land in `~\u002F.openwiki\u002F.env` on the user's own machine — never read, log, or echo this file's contents on the user's behalf.\n- Connector auth (`openwiki auth ...`) opens an interactive OAuth flow — run it and let the user complete auth themselves, don't attempt to script credentials into it.\n- Recommend the CI workflow (auto-PR) over manual reruns when the user's actual goal is \"keep docs from going stale,\" not \"generate docs once.\"\n\n## Anti-patterns\n\n```\n❌ Running `openwiki auth \u003Cprovider>` and trying to supply credentials non-interactively\n❌ Reading\u002Fprinting ~\u002F.openwiki\u002F.env \"to check the config\"\n❌ Suggesting a direct push to main from the CI workflow instead of the tool's own PR\u002FMR flow\n❌ Treating this as a replacement for gitnexus-cli's structural graph queries — different job\n```\n\n## Verification\n\nAfter `openwiki code --init` or `--update`, confirm the `openwiki\u002F` directory\n(or `~\u002F.openwiki\u002Fwiki\u002F` for personal mode) was actually written and `AGENTS.md`\u002F\n`CLAUDE.md` contain the managed block, rather than assuming success from the\nCLI's exit code alone.\n",{"name":5,"origin":24,"license":15,"description":7},"https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Fopenwiki","main","481dcd7dd2e288b9d627a2bd017db70e64e6c6fa","core\u002Fskills\u002Flangchain-ai--openwiki",2,"https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI","https:\u002F\u002Fyana.vutam.link\u002F","https:\u002F\u002Fgithub.com\u002FHoronomos-laps","https:\u002F\u002Fyana.vutam.link","An open-source governed runtime & execution environment for multi-agent AI systems.","2026-11-14 13:24:09",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add Horonomos-laps\u002FYana-AI --skill langchain-ai--openwiki",{"tool":41,"command":42},"bunx","bunx skills add Horonomos-laps\u002FYana-AI --skill langchain-ai--openwiki",{"tool":44,"command":45},"pnpm","pnpm dlx skills add Horonomos-laps\u002FYana-AI --skill langchain-ai--openwiki","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Flangchain-ai--openwiki\u002FSKILL.md",true,[],[50,57,65,73,81,89],{"skillNo":51,"name":52,"nameZh":6,"description":53,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":54,"categories":55,"keywords":56,"publishedAt":19},"01M735GKET5YVYKAY62W2P5YXB","openai--sentry--sentry","Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry API; perform read-only queries with the bundled script and require `SENTRY_AUTH_TOKEN`.","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fopenai--sentry--sentry\u002FSKILL.md",[],[],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":61,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"01M73DCAP83T17HY7SMGK7MGFE","ito-basket-compare","Compare Itô prediction-market baskets against a user's knowledge base, portfolio notes, financial context, watchlist, or research thesis. Use for read-only basket comparison and gap analysis without investment advice or live trading.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fito-basket-compare\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":61,"licenseFileUrl":69,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M734CYEMZFDR3KH6SW0JP8TD","implementing-network-traffic-baselining","Build network traffic baselines from NetFlow\u002FIPFIX data using Python pandas for statistical analysis, z-score anomaly detection, and hourly\u002Fdaily traffic pattern profiling","https:\u002F\u002Fgithub.com\u002Fyanacuti1121\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-network-traffic-baselining\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-network-traffic-baselining\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":61,"licenseFileUrl":77,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M73ASZ6NJRJM44Z2P84NGQ3Q","detecting-evasion-techniques-in-endpoint-logs","Detects defense evasion techniques used by adversaries in endpoint logs including log tampering, timestomping, process injection, and security tool disabling. Use when investigating suspicious endpoint behavior, building detection rules for evasion tactics, or conducting threat hunting for stealthy adversary activity. Activates for requests involving evasion detection, defense evasion analysis, log tampering detection, or MITRE ATT&CK TA0005.","https:\u002F\u002Fgithub.com\u002Fyanacuti1121\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fdetecting-evasion-techniques-in-endpoint-logs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fdetecting-evasion-techniques-in-endpoint-logs\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":61,"licenseFileUrl":85,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M734AFNXD06Z78QRK0VKGT7Q","implementing-microsegmentation-with-guardicore","Implementing microsegmentation using Akamai Guardicore Segmentation to map application dependencies, create granular network policies, visualize east-west traffic flows, and enforce least-privilege communication between workloads across data centers and cloud.","https:\u002F\u002Fgithub.com\u002Fyanacuti1121\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-microsegmentation-with-guardicore\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-microsegmentation-with-guardicore\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":61,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M736TK27QMCXK0DVCH25SJN5","ramdisk-tmpfs-patterns","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Framdisk-tmpfs-patterns\u002FSKILL.md",[],[]]