[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M698S1YG9BWQ7C3A4DYPNA0R":3,"skill-same:01M698S1YG9BWQ7C3A4DYPNA0R":56},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":27,"linkOnly":28,"markdownContent":29,"markdownBody":30,"frontMatter":31,"refName":32,"commitSha":33,"skillDirectory":34,"forksCount":35,"repositoryHtmlUrl":36,"repositoryHomepageUrl":37,"ownerHtmlUrl":38,"ownerBlogUrl":39,"ownerDescription":40,"updatedAt":41,"install":42,"resources":55},"01M698S1YG9BWQ7C3A4DYPNA0R","discrawl",null,"Discord archive: search, sync freshness, DMs, summaries, TUI, repo\u002Frelease work.","openclaw\u002Fdiscrawl","openclaw","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F252820863?v=4","01M698P3FSAZ6B4R928ZF19KPT","01M698RXXYPRCREYMM95SD88XT",862,"MIT","https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fdiscrawl\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdiscrawl\u002FSKILL.md",[],[5,18,19,20,21,22,23,24,25,26],"discord","sync","release","search","archive","work","repo","tui","summaries","2026-11-10 10:12:30",false,"---\nname: discrawl\ndescription: \"Discord archive: search, sync freshness, DMs, summaries, TUI, repo\u002Frelease work.\"\n---\n\n# Discrawl\n\nUse local Discord archive data first for Discord questions. Hit Discord APIs\nonly when the archive is stale, missing the requested scope, or the user asks\nfor current external context.\n\n## Sources\n\n- DB: platform-native XDG data dir, usually\n  `${XDG_DATA_HOME:-~\u002F.local\u002Fshare}\u002Fdiscrawl\u002Fdiscrawl.db` on Linux or\n  `~\u002FLibrary\u002FApplication Support\u002Fdiscrawl\u002Fdiscrawl.db` on macOS\n- Config: platform-native XDG config dir, with legacy fallback to\n  `~\u002F.discrawl\u002Fconfig.toml`\n- Cache: platform-native XDG cache dir\n- Logs: platform-native XDG state dir\n- Git share repo: platform-native XDG data dir\n- Repo: `openclaw\u002Fdiscrawl`; use `~\u002FGIT\u002F_Perso\u002Fdiscrawl` only after verifying\n  its remote targets `openclaw\u002Fdiscrawl`, otherwise use a fresh checkout\n- Preferred CLI: `discrawl`; fallback to `go run .\u002Fcmd\u002Fdiscrawl` from the repo\n  if the installed binary is stale\n\n## Freshness\n\nFor recent\u002Fcurrent questions, check freshness before analysis:\n\n```bash\ndiscrawl status --json\n```\n\nFor precise freshness from the default database:\n\n```bash\n# Discrawl uses macOS ~\u002FLibrary defaults unless XDG_DATA_HOME is explicitly set.\ncase \"$(uname -s)\" in\n  Darwin)\n    db=\"$HOME\u002FLibrary\u002FApplication Support\u002Fdiscrawl\u002Fdiscrawl.db\"\n    ;;\n  *)\n    db=\"${XDG_DATA_HOME:-$HOME\u002F.local\u002Fshare}\u002Fdiscrawl\u002Fdiscrawl.db\"\n    ;;\nesac\nsqlite3 \"$db\" \\\n  \"select coalesce(max(updated_at),'') from sync_state where scope like 'channel:%';\"\n```\n\nRoutine diagnostics:\n\n```bash\ndiscrawl doctor\n```\n\nDesktop-local refresh:\n\n```bash\ndiscrawl sync --source wiretap\n```\n\nBot API latest refresh, when credentials are available:\n\n```bash\ndiscrawl sync\n```\n\nUse `--full` only for deliberate historical backfills:\n\n```bash\ndiscrawl sync --full\n```\n\nIf SQLite reports busy\u002Flocked, check for stray `discrawl` processes before retrying.\n\n## Query Workflow\n\n1. Resolve scope: guild, channel, DM, author, keyword, date range.\n2. Check freshness for recent\u002Fcurrent requests.\n3. Prefer CLI search\u002Fmessages for slices; use read-only SQL for exact counts.\n4. Report absolute date spans, counts, channel\u002FDM names, and known gaps.\n\nUse root or subcommand help for syntax: `discrawl --help`,\n`discrawl help search`, `discrawl search --help`. Use\n`DISCRAWL_NO_AUTO_UPDATE=1` for read smokes when you do not want git-share\nupdates.\n\nCommon commands:\n\n```bash\nDISCRAWL_NO_AUTO_UPDATE=1 discrawl search --limit 20 \"query\"\ndiscrawl messages --channel '#maintainers' --days 7 --all\ndiscrawl dms --last 20\ndiscrawl tui --dm\nDISCRAWL_NO_AUTO_UPDATE=1 discrawl --json sql \"select count(*) from messages;\"\n```\n\n## SQL\n\nUse `discrawl sql` for exact counts, joins, and ranking queries when normal\nCLI reads are too coarse. The command is read-only by default, accepts SQL as\nargs or stdin, and supports `--json` for agent parsing.\n\nUseful examples:\n\n```bash\nDISCRAWL_NO_AUTO_UPDATE=1 discrawl --json sql \"select count(*) as messages from messages;\"\nDISCRAWL_NO_AUTO_UPDATE=1 discrawl --json sql \"select coalesce(nullif(c.name, ''), m.channel_id) as channel, count(*) as messages from messages m left join channels c on c.id = m.channel_id group by m.channel_id order by messages desc limit 20;\"\nDISCRAWL_NO_AUTO_UPDATE=1 discrawl --json sql \"select coalesce(nullif(mm.display_name, ''), nullif(mm.global_name, ''), nullif(mm.username, ''), m.author_id) as author, count(*) as messages from messages m left join members mm on mm.guild_id = m.guild_id and mm.user_id = m.author_id group by m.guild_id, m.author_id order by messages desc limit 20;\"\n```\n\nNever use `--unsafe --confirm` unless the user explicitly asks for a database\nmutation and the write has been reviewed.\n\nWhen the installed CLI lacks a new feature, build or run from a verified\n`openclaw\u002Fdiscrawl` checkout before concluding the feature is missing.\n\n## Discord Boundaries\n\nBot API sync requires configured Discord bot credentials; do not invent token\navailability. Desktop wiretap mode reads local Discord Desktop artifacts and\nmust not extract credentials, use user tokens, call Discord as the user, or\nwrite to Discord application storage. Wiretap\u002FDesktop cache DMs are local-only\nand must not be described as part of the published Git snapshot. Git-share\nsnapshots must not include secrets or `@me` DM rows.\n\n## Verification\n\nFor repo edits, prefer existing Go gates:\n\n```bash\nGOWORK=off go test .\u002F...\n```\n\nThen run targeted CLI smoke for the touched surface, for example:\n\n```bash\ndiscrawl doctor\ndiscrawl status --json\nDISCRAWL_NO_AUTO_UPDATE=1 discrawl search --limit 5 \"test\"\n```\n","# Discrawl\n\nUse local Discord archive data first for Discord questions. Hit Discord APIs\nonly when the archive is stale, missing the requested scope, or the user asks\nfor current external context.\n\n## Sources\n\n- DB: platform-native XDG data dir, usually\n  `${XDG_DATA_HOME:-~\u002F.local\u002Fshare}\u002Fdiscrawl\u002Fdiscrawl.db` on Linux or\n  `~\u002FLibrary\u002FApplication Support\u002Fdiscrawl\u002Fdiscrawl.db` on macOS\n- Config: platform-native XDG config dir, with legacy fallback to\n  `~\u002F.discrawl\u002Fconfig.toml`\n- Cache: platform-native XDG cache dir\n- Logs: platform-native XDG state dir\n- Git share repo: platform-native XDG data dir\n- Repo: `openclaw\u002Fdiscrawl`; use `~\u002FGIT\u002F_Perso\u002Fdiscrawl` only after verifying\n  its remote targets `openclaw\u002Fdiscrawl`, otherwise use a fresh checkout\n- Preferred CLI: `discrawl`; fallback to `go run .\u002Fcmd\u002Fdiscrawl` from the repo\n  if the installed binary is stale\n\n## Freshness\n\nFor recent\u002Fcurrent questions, check freshness before analysis:\n\n```bash\ndiscrawl status --json\n```\n\nFor precise freshness from the default database:\n\n```bash\n# Discrawl uses macOS ~\u002FLibrary defaults unless XDG_DATA_HOME is explicitly set.\ncase \"$(uname -s)\" in\n  Darwin)\n    db=\"$HOME\u002FLibrary\u002FApplication Support\u002Fdiscrawl\u002Fdiscrawl.db\"\n    ;;\n  *)\n    db=\"${XDG_DATA_HOME:-$HOME\u002F.local\u002Fshare}\u002Fdiscrawl\u002Fdiscrawl.db\"\n    ;;\nesac\nsqlite3 \"$db\" \\\n  \"select coalesce(max(updated_at),'') from sync_state where scope like 'channel:%';\"\n```\n\nRoutine diagnostics:\n\n```bash\ndiscrawl doctor\n```\n\nDesktop-local refresh:\n\n```bash\ndiscrawl sync --source wiretap\n```\n\nBot API latest refresh, when credentials are available:\n\n```bash\ndiscrawl sync\n```\n\nUse `--full` only for deliberate historical backfills:\n\n```bash\ndiscrawl sync --full\n```\n\nIf SQLite reports busy\u002Flocked, check for stray `discrawl` processes before retrying.\n\n## Query Workflow\n\n1. Resolve scope: guild, channel, DM, author, keyword, date range.\n2. Check freshness for recent\u002Fcurrent requests.\n3. Prefer CLI search\u002Fmessages for slices; use read-only SQL for exact counts.\n4. Report absolute date spans, counts, channel\u002FDM names, and known gaps.\n\nUse root or subcommand help for syntax: `discrawl --help`,\n`discrawl help search`, `discrawl search --help`. Use\n`DISCRAWL_NO_AUTO_UPDATE=1` for read smokes when you do not want git-share\nupdates.\n\nCommon commands:\n\n```bash\nDISCRAWL_NO_AUTO_UPDATE=1 discrawl search --limit 20 \"query\"\ndiscrawl messages --channel '#maintainers' --days 7 --all\ndiscrawl dms --last 20\ndiscrawl tui --dm\nDISCRAWL_NO_AUTO_UPDATE=1 discrawl --json sql \"select count(*) from messages;\"\n```\n\n## SQL\n\nUse `discrawl sql` for exact counts, joins, and ranking queries when normal\nCLI reads are too coarse. The command is read-only by default, accepts SQL as\nargs or stdin, and supports `--json` for agent parsing.\n\nUseful examples:\n\n```bash\nDISCRAWL_NO_AUTO_UPDATE=1 discrawl --json sql \"select count(*) as messages from messages;\"\nDISCRAWL_NO_AUTO_UPDATE=1 discrawl --json sql \"select coalesce(nullif(c.name, ''), m.channel_id) as channel, count(*) as messages from messages m left join channels c on c.id = m.channel_id group by m.channel_id order by messages desc limit 20;\"\nDISCRAWL_NO_AUTO_UPDATE=1 discrawl --json sql \"select coalesce(nullif(mm.display_name, ''), nullif(mm.global_name, ''), nullif(mm.username, ''), m.author_id) as author, count(*) as messages from messages m left join members mm on mm.guild_id = m.guild_id and mm.user_id = m.author_id group by m.guild_id, m.author_id order by messages desc limit 20;\"\n```\n\nNever use `--unsafe --confirm` unless the user explicitly asks for a database\nmutation and the write has been reviewed.\n\nWhen the installed CLI lacks a new feature, build or run from a verified\n`openclaw\u002Fdiscrawl` checkout before concluding the feature is missing.\n\n## Discord Boundaries\n\nBot API sync requires configured Discord bot credentials; do not invent token\navailability. Desktop wiretap mode reads local Discord Desktop artifacts and\nmust not extract credentials, use user tokens, call Discord as the user, or\nwrite to Discord application storage. Wiretap\u002FDesktop cache DMs are local-only\nand must not be described as part of the published Git snapshot. Git-share\nsnapshots must not include secrets or `@me` DM rows.\n\n## Verification\n\nFor repo edits, prefer existing Go gates:\n\n```bash\nGOWORK=off go test .\u002F...\n```\n\nThen run targeted CLI smoke for the touched surface, for example:\n\n```bash\ndiscrawl doctor\ndiscrawl status --json\nDISCRAWL_NO_AUTO_UPDATE=1 discrawl search --limit 5 \"test\"\n```\n",{"name":5,"description":7},"main","b095420d39186068c0eddfb8bb597b42a60d7f2e",".agents\u002Fskills\u002Fdiscrawl",101,"https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fdiscrawl","https:\u002F\u002Fdiscrawl.sh","https:\u002F\u002Fgithub.com\u002Fopenclaw","https:\u002F\u002Fopenclaw.ai","Your personal, open source AI assistant.","2026-11-14 21:59:55",{"source":8,"skillName":5,"commands":43,"prompt":53,"zipAvailable":54},[44,47,50],{"tool":45,"command":46},"npx","npx skills add openclaw\u002Fdiscrawl --skill discrawl",{"tool":48,"command":49},"bunx","bunx skills add openclaw\u002Fdiscrawl --skill discrawl",{"tool":51,"command":52},"pnpm","pnpm dlx skills add openclaw\u002Fdiscrawl --skill discrawl","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fdiscrawl\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdiscrawl\u002FSKILL.md",true,[],[57,79],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":27},"01M698S0TVC5HKZWHDCTCRBQ1R","crabbox","Use the Crabbox wrapper for OpenClaw remote validation across Linux, macOS, Windows, and WSL2, including delegated Blacksmith Testbox proof. Report the actual provider and id.","https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fdiscrawl\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcrabbox\u002FSKILL.md",[],[59,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,9],"for","openclaw remote","remote","blacksmith testbox","proof","id","across","provider","Wrapper","use","validation","report","windows","linux","macos",{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":90,"publishedAt":27},"01M698RZJ6JT4SWBFJQ8BHBQC7","autoreview","Structured code review through the shared OpenClaw agent-skills installation.","https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fdiscrawl\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fautoreview\u002FSKILL.md",[85],{"categoryNo":86,"categoryName":87,"taxonomyType":88,"taxonomyTypeDesc":89},"01JBSEEDCAT000000000000007","代码审查","SCENARIO","使用场景",[81,91,92,93,94,95,96,97,98,9],"code review","shared","structured","installation","agent-skills","openclaw agent","code","review"]