[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MENPGZNN7YA79YJ6G80WVM":3,"skill-same:01M6MENPGZNN7YA79YJ6G80WVM":95},{"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":40,"linkOnly":41,"markdownContent":42,"markdownBody":43,"frontMatter":44,"refName":72,"commitSha":73,"skillDirectory":74,"forksCount":75,"repositoryHtmlUrl":76,"repositoryHomepageUrl":77,"ownerHtmlUrl":78,"ownerBlogUrl":79,"ownerDescription":80,"updatedAt":81,"install":82,"resources":94},"01M6MENPGZNN7YA79YJ6G80WVM","claude-exec",null,"Run one prompt through headless Claude with scoped permissions and a time bound. Use when: scripting or automating a `claude -p` call, even a simple one.","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fclaude-exec\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39],"exec","claude exec","when","contract","exit","call","true","scoped","canonical","permission","status","run","pragmatic","command","artifact","permissions","orchestration","effects","design","time","headless","2026-11-10 10:12:30",false,"---\nname: claude-exec\ndescription: 'Run one prompt through headless Claude with scoped permissions and a time bound. Use when: scripting or automating a `claude -p` call, even a simple one.'\nskill_api_version: 1\nuser-invocable: true\nhexagonal_role: driving-adapter\npractices: [pragmatic-programmer, design-by-contract]\nconsumes: [claude-command-packet]\nproduces: [claude-run-output]\ncontext_rel:\n- kind: supplier-to\n  with: validate\n- kind: separate-ways\n  with: codex-exec\nmetadata:\n  tier: orchestration\n  dependencies: []\n  capabilities: [claude_exec]\n  effects: [run_claude_process, permission_tiered_workspace_effects]\n  canonical_status: canonical\n  disposition: keep_optional_adapter\n  stability: stable\noutput_contract: process exit status and captured Claude output artifact\n---\n# Claude Exec — one-shot runtime adapter\n\nRun one caller-supplied prompt through Claude Code print mode and capture the\nresult, only when the caller selects Claude: the native agent stays the\ndefault and batches belong to `orchestrate`. Flags match `claude --help` for\nClaude Code 2.1.309, re-checked on 2026-10-25; recheck it on other versions.\nIt worked when the run drops inherited settings, names its tools and permission\nmode, stays inside one deadline, and the result is judged by exit status and\n`is_error` with `permission_denials` reported.\n\n## Failure modes of a quick `claude -p`\n\n1. **Inherited posture.** A plain run loads the user's settings, hooks,\n   plugins, MCP servers and CLAUDE.md; a settings `bypassPermissions` default\n   held even under `--safe-mode`. Use the clean flags below and set `--tools`\n   and `--permission-mode` to the task's effects. They drop settings files,\n   MCP servers, skills and commands and keep file tools in the working\n   directory; `--bare` also skips CLAUDE.md, auto-memory and plugin hooks.\n2. **Renewed time.** One deadline, fixed once by the caller: `$SECS` is the\n   time left before it, so a retry spends it instead of renewing it. Make one\n   attempt; any other is the caller's decision.\n3. **Exit 0 as proof.** A denied call still exits 0 with `is_error: false`\n   and \"done\" (not re-run since 2.1.282). Name targets by path, check\n   effects there, and leave acceptance to a fresh validator.\n4. **Silent fallback.** With no `claude`, login or model, report and stop\n   instead of switching runtimes or passing `--fallback-model`.\n5. **Self-review.** Review in a new session, never by `--resume` or\n   `--continue` of the author's.\n\n## Run\n\nRedirect the prompt from a file, or pass it as the argument with `\u003C\u002Fdev\u002Fnull`,\nbecause print mode reads stdin to EOF: a pipe left open hangs until the bound\nkills it (not re-run since 2.1.282). Stock macOS lacks `timeout`: use GNU\n`timeout` or Homebrew's `gtimeout`, and launch nothing without one. This\nscript body makes one launch; the caller supplies `$POSTURE`, `$MODEL`,\n`$BUDGET_USD`, `$DEADLINE_EPOCH`, `$ALLOWED` for `test`, an absolute\n`$WORKDIR`, and absolute `$PROMPT_FILE`, `$OUT` and `$ERR` paths outside it.\n\n```bash\nTO=$(command -v timeout || command -v gtimeout) || { echo \"no timeout: not launching\" >&2; exit 2; }\ncase \"$DEADLINE_EPOCH\" in ''|*[!0-9]*) echo \"no deadline: not launching\" >&2; exit 2;; esac\nfor p in \"$WORKDIR\" \"$PROMPT_FILE\" \"$OUT\" \"$ERR\"; do case \"$p\" in \u002F*) ;; *) echo \"not absolute: '$p'\" >&2; exit 2;; esac; done\n[ -n \"$MODEL\" ] && [ -n \"$BUDGET_USD\" ] || { echo \"no model or budget: not launching\" >&2; exit 2; }\nEXTRA=()\ncase \"$POSTURE\" in\n  read) TOOLS=\"Read,Grep,Glob\" MODE=dontAsk ;;   # review, research, questions\n  edit) TOOLS=\"Read,Grep,Glob,Edit,Write\" MODE=acceptEdits ;;   # authorized changes under $WORKDIR\n  test) [ -n \"$ALLOWED\" ] || { echo \"test needs \\$ALLOWED: not launching\" >&2; exit 2; }   # edit plus named commands\n    TOOLS=\"Read,Grep,Glob,Edit,Write,Bash\" MODE=acceptEdits; EXTRA=(--allowedTools \"$ALLOWED\") ;;\n  *) echo \"POSTURE must be read, edit or test: not launching\" >&2; exit 2 ;; esac\ncd \"$WORKDIR\" || exit 2\nSECS=$(( DEADLINE_EPOCH - $(date +%s) ))   # DEADLINE_EPOCH: Unix time fixed once by the caller\n[ \"$SECS\" -gt 0 ] || { echo \"deadline passed: not launching\" >&2; exit 124; }\n\"$TO\" -k 10 \"$SECS\" claude -p --model \"$MODEL\" --output-format json \\\n  --setting-sources \"\" --strict-mcp-config --disable-slash-commands --restricted \\\n  --tools \"$TOOLS\" --permission-mode \"$MODE\" --permission-prompts none ${EXTRA[@]+\"${EXTRA[@]}\"} \\\n  --max-budget-usd \"$BUDGET_USD\" \u003C\"$PROMPT_FILE\" >\"$OUT\" 2>\"$ERR\"; rc=$?; echo \"exit=$rc\"\n```\n\nUnapproved calls are denied and listed in `permission_denials`. `test` adds\n`Bash` only for the authorized commands `$ALLOWED` names, e.g.\n`ALLOWED=\"Bash(go test *)\"`; with settings hooks dropped, that list is the guard.\n`--max-budget-usd` stops after the call that crosses it. `--max-turns \u003Cn>`\ncaps agentic turns in print mode and exits with an error when it is reached:\n2.1.309 accepts it although `--help` omits it, and the CLI reference documents\nit. Time, budget and an optional turn cap are the bounds.\n`--no-session-persistence` keeps no transcript. `--bare` signs in only with\n`ANTHROPIC_API_KEY` or an `apiKeyHelper` passed with `--settings`, never an\nOAuth login.\n\nA host shell tool may kill a call before `$SECS`, leaving `$OUT` empty since\nJSON is written only at exit. When its cap is under `$SECS` plus the 10 s\ngrace, start the command as a host background job and wait on its completion\nnotice; a run the host killed was the one attempt. A quiet run is working.\n\n## Result\n\nJSON carries `result`, `is_error`, `terminal_reason`, `api_error_status`,\n`session_id`, `permission_denials`, and `modelUsage` keyed by the models\nbilled; identity evidence needs `stream-json --verbose` per the\n[model-dispatch recipe](..\u002Fvalidate\u002Freferences\u002Fmodel-dispatch.md). Judge\nby exit status and `is_error`: an unknown model exited 1 with\n`subtype: \"success\"`, `terminal_reason: \"api_error\"` and `api_error_status:\n404`. Exit 1 also covers a spent budget or missing input (not re-run since\n2.1.282); `timeout` gives 124, or 137 when KILL follows 10 seconds later.\nRead the fields before the byte cap, since a cut JSON file no longer parses:\n\n```bash\njq -c '{is_error, terminal_reason, api_error_status, session_id,\n  models: (.modelUsage \u002F\u002F {} | keys), permission_denials}' \"$OUT\" >\"$OUT.meta\"\nok=no; [ \"$rc\" -eq 0 ] && jq -e '.is_error == false' \"$OUT.meta\" >\u002Fdev\u002Fnull && ok=yes\nCAP=${CAP:-10485760} truncated=no   # the caller's byte cap, 10 MiB default\n[ \"$(wc -c \u003C\"$OUT\")\" -le \"$CAP\" ] || { head -c \"$CAP\" \"$OUT\" >\"$OUT.cut\" && mv \"$OUT.cut\" \"$OUT\"; truncated=yes; }\n```\n\nReturn this, and stop:\n\n```text\ncommand: \u003Cexact argv>    posture: \u003Ctools; permission mode; clean flags>\nmodel: \u003Crequested> -> \u003CmodelUsage keys>    exit: \u003Cstatus | timeout at N s>\nok: \u003Cyes|no; a clean run, not acceptance>    is_error: \u003Ctrue|false | none>\nreason: \u003Cterminal_reason; api_error_status | none>    session_id: \u003Cid | none>\noutput: \u003Cpath, bytes, truncated: yes|no>    permission_denials: \u003Ccount and tools>\n```\n","# Claude Exec — one-shot runtime adapter\n\nRun one caller-supplied prompt through Claude Code print mode and capture the\nresult, only when the caller selects Claude: the native agent stays the\ndefault and batches belong to `orchestrate`. Flags match `claude --help` for\nClaude Code 2.1.309, re-checked on 2026-10-25; recheck it on other versions.\nIt worked when the run drops inherited settings, names its tools and permission\nmode, stays inside one deadline, and the result is judged by exit status and\n`is_error` with `permission_denials` reported.\n\n## Failure modes of a quick `claude -p`\n\n1. **Inherited posture.** A plain run loads the user's settings, hooks,\n   plugins, MCP servers and CLAUDE.md; a settings `bypassPermissions` default\n   held even under `--safe-mode`. Use the clean flags below and set `--tools`\n   and `--permission-mode` to the task's effects. They drop settings files,\n   MCP servers, skills and commands and keep file tools in the working\n   directory; `--bare` also skips CLAUDE.md, auto-memory and plugin hooks.\n2. **Renewed time.** One deadline, fixed once by the caller: `$SECS` is the\n   time left before it, so a retry spends it instead of renewing it. Make one\n   attempt; any other is the caller's decision.\n3. **Exit 0 as proof.** A denied call still exits 0 with `is_error: false`\n   and \"done\" (not re-run since 2.1.282). Name targets by path, check\n   effects there, and leave acceptance to a fresh validator.\n4. **Silent fallback.** With no `claude`, login or model, report and stop\n   instead of switching runtimes or passing `--fallback-model`.\n5. **Self-review.** Review in a new session, never by `--resume` or\n   `--continue` of the author's.\n\n## Run\n\nRedirect the prompt from a file, or pass it as the argument with `\u003C\u002Fdev\u002Fnull`,\nbecause print mode reads stdin to EOF: a pipe left open hangs until the bound\nkills it (not re-run since 2.1.282). Stock macOS lacks `timeout`: use GNU\n`timeout` or Homebrew's `gtimeout`, and launch nothing without one. This\nscript body makes one launch; the caller supplies `$POSTURE`, `$MODEL`,\n`$BUDGET_USD`, `$DEADLINE_EPOCH`, `$ALLOWED` for `test`, an absolute\n`$WORKDIR`, and absolute `$PROMPT_FILE`, `$OUT` and `$ERR` paths outside it.\n\n```bash\nTO=$(command -v timeout || command -v gtimeout) || { echo \"no timeout: not launching\" >&2; exit 2; }\ncase \"$DEADLINE_EPOCH\" in ''|*[!0-9]*) echo \"no deadline: not launching\" >&2; exit 2;; esac\nfor p in \"$WORKDIR\" \"$PROMPT_FILE\" \"$OUT\" \"$ERR\"; do case \"$p\" in \u002F*) ;; *) echo \"not absolute: '$p'\" >&2; exit 2;; esac; done\n[ -n \"$MODEL\" ] && [ -n \"$BUDGET_USD\" ] || { echo \"no model or budget: not launching\" >&2; exit 2; }\nEXTRA=()\ncase \"$POSTURE\" in\n  read) TOOLS=\"Read,Grep,Glob\" MODE=dontAsk ;;   # review, research, questions\n  edit) TOOLS=\"Read,Grep,Glob,Edit,Write\" MODE=acceptEdits ;;   # authorized changes under $WORKDIR\n  test) [ -n \"$ALLOWED\" ] || { echo \"test needs \\$ALLOWED: not launching\" >&2; exit 2; }   # edit plus named commands\n    TOOLS=\"Read,Grep,Glob,Edit,Write,Bash\" MODE=acceptEdits; EXTRA=(--allowedTools \"$ALLOWED\") ;;\n  *) echo \"POSTURE must be read, edit or test: not launching\" >&2; exit 2 ;; esac\ncd \"$WORKDIR\" || exit 2\nSECS=$(( DEADLINE_EPOCH - $(date +%s) ))   # DEADLINE_EPOCH: Unix time fixed once by the caller\n[ \"$SECS\" -gt 0 ] || { echo \"deadline passed: not launching\" >&2; exit 124; }\n\"$TO\" -k 10 \"$SECS\" claude -p --model \"$MODEL\" --output-format json \\\n  --setting-sources \"\" --strict-mcp-config --disable-slash-commands --restricted \\\n  --tools \"$TOOLS\" --permission-mode \"$MODE\" --permission-prompts none ${EXTRA[@]+\"${EXTRA[@]}\"} \\\n  --max-budget-usd \"$BUDGET_USD\" \u003C\"$PROMPT_FILE\" >\"$OUT\" 2>\"$ERR\"; rc=$?; echo \"exit=$rc\"\n```\n\nUnapproved calls are denied and listed in `permission_denials`. `test` adds\n`Bash` only for the authorized commands `$ALLOWED` names, e.g.\n`ALLOWED=\"Bash(go test *)\"`; with settings hooks dropped, that list is the guard.\n`--max-budget-usd` stops after the call that crosses it. `--max-turns \u003Cn>`\ncaps agentic turns in print mode and exits with an error when it is reached:\n2.1.309 accepts it although `--help` omits it, and the CLI reference documents\nit. Time, budget and an optional turn cap are the bounds.\n`--no-session-persistence` keeps no transcript. `--bare` signs in only with\n`ANTHROPIC_API_KEY` or an `apiKeyHelper` passed with `--settings`, never an\nOAuth login.\n\nA host shell tool may kill a call before `$SECS`, leaving `$OUT` empty since\nJSON is written only at exit. When its cap is under `$SECS` plus the 10 s\ngrace, start the command as a host background job and wait on its completion\nnotice; a run the host killed was the one attempt. A quiet run is working.\n\n## Result\n\nJSON carries `result`, `is_error`, `terminal_reason`, `api_error_status`,\n`session_id`, `permission_denials`, and `modelUsage` keyed by the models\nbilled; identity evidence needs `stream-json --verbose` per the\n[model-dispatch recipe](..\u002Fvalidate\u002Freferences\u002Fmodel-dispatch.md). Judge\nby exit status and `is_error`: an unknown model exited 1 with\n`subtype: \"success\"`, `terminal_reason: \"api_error\"` and `api_error_status:\n404`. Exit 1 also covers a spent budget or missing input (not re-run since\n2.1.282); `timeout` gives 124, or 137 when KILL follows 10 seconds later.\nRead the fields before the byte cap, since a cut JSON file no longer parses:\n\n```bash\njq -c '{is_error, terminal_reason, api_error_status, session_id,\n  models: (.modelUsage \u002F\u002F {} | keys), permission_denials}' \"$OUT\" >\"$OUT.meta\"\nok=no; [ \"$rc\" -eq 0 ] && jq -e '.is_error == false' \"$OUT.meta\" >\u002Fdev\u002Fnull && ok=yes\nCAP=${CAP:-10485760} truncated=no   # the caller's byte cap, 10 MiB default\n[ \"$(wc -c \u003C\"$OUT\")\" -le \"$CAP\" ] || { head -c \"$CAP\" \"$OUT\" >\"$OUT.cut\" && mv \"$OUT.cut\" \"$OUT\"; truncated=yes; }\n```\n\nReturn this, and stop:\n\n```text\ncommand: \u003Cexact argv>    posture: \u003Ctools; permission mode; clean flags>\nmodel: \u003Crequested> -> \u003CmodelUsage keys>    exit: \u003Cstatus | timeout at N s>\nok: \u003Cyes|no; a clean run, not acceptance>    is_error: \u003Ctrue|false | none>\nreason: \u003Cterminal_reason; api_error_status | none>    session_id: \u003Cid | none>\noutput: \u003Cpath, bytes, truncated: yes|no>    permission_denials: \u003Ccount and tools>\n```\n",{"name":5,"consumes":45,"metadata":47,"produces":56,"practices":58,"context_rel":61,"description":7,"hexagonal_role":68,"user-invocable":69,"output_contract":70,"skill_api_version":71},[46],"claude-command-packet",{"tier":35,"effects":48,"stability":51,"disposition":52,"capabilities":53,"dependencies":55,"canonical_status":27},[49,50],"run_claude_process","permission_tiered_workspace_effects","stable","keep_optional_adapter",[54],"claude_exec",[],[57],"claude-run-output",[59,60],"pragmatic-programmer","design-by-contract",[62,65],{"kind":63,"with":64},"supplier-to","validate",{"kind":66,"with":67},"separate-ways","codex-exec","driving-adapter",true,"process exit status and captured Claude output artifact",1,"main","347aedf8480cd92b21f761e97b7343a45898f5fa","plugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fclaude-exec",491,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-14 14:06:13",{"source":8,"skillName":5,"commands":83,"prompt":93,"zipAvailable":69},[84,87,90],{"tool":85,"command":86},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill claude-exec",{"tool":88,"command":89},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill claude-exec",{"tool":91,"command":92},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill claude-exec","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fclaude-exec\u002FSKILL.md",[],[96,106,114,122,130,138],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":100,"licenseFileUrl":101,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":105},"01M7DV332YQMGD8WTRJ9DZQXTB","worktable-review-with-annotations","Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.","MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":100,"licenseFileUrl":110,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":105},"01M7DV2YGHCZVBEB1AHYB6CGHE","worktable-find-and-synthesize-context","Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FSKILL.md",[],[],{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":100,"licenseFileUrl":118,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":105},"01M7DV2TQN1H11ME2SAF9MXN7V","worktable-create-or-update-docs","Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FSKILL.md",[],[],{"skillNo":123,"name":124,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":100,"licenseFileUrl":126,"sourceHtmlUrl":127,"categories":128,"keywords":129,"publishedAt":105},"01M7DV2NE452NEA8TXATKSNAJH","worktable-create-or-manage-records","Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FSKILL.md",[],[],{"skillNo":131,"name":132,"nameZh":6,"description":133,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":100,"licenseFileUrl":134,"sourceHtmlUrl":135,"categories":136,"keywords":137,"publishedAt":105},"01M7DV2HENRBR2KSCVM064WH0Y","worktable-create-or-manage-interactive-html","Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FSKILL.md",[],[],{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":100,"licenseFileUrl":142,"sourceHtmlUrl":143,"categories":144,"keywords":145,"publishedAt":105},"01M7DV2CADR5R7RQFFYPNAGR9Y","worktable-collaborate-threads","Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FSKILL.md",[],[]]