[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MPD1CJ0VZW0H174E2J41Z5":3,"skill-same:01M6MPD1CJ0VZW0H174E2J41Z5":109},{"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":55,"commitSha":56,"skillDirectory":57,"forksCount":58,"repositoryHtmlUrl":59,"repositoryHomepageUrl":60,"ownerHtmlUrl":61,"ownerBlogUrl":62,"ownerDescription":63,"updatedAt":64,"install":65,"resources":78},"01M6MPD1CJ0VZW0H174E2J41Z5","zagrosi-implement",null,"Build admitted Forge sections with minimal code, targeted TDD\u002Freview, resumable records, and final verification.","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\u002Fzagrosi-code\u002Fzagrosi-forge\u002Fskills\u002Fzagrosi-implement\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39],"implement","zagrosi implement","Bash","section","root","with","records","scripts","next","build","minimal","python3","review","team","forge","verification","code","plugin","status","tdd","python","2026-11-10 10:12:30",false,"---\nname: zagrosi-implement\ndescription: Build admitted Forge sections with minimal code, targeted TDD\u002Freview, resumable records, and final verification.\nallowed-tools:\n  - Bash(python3 \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fzagrosi_skills.py\" team status *)\n  - Bash(python3 \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fzagrosi_skills.py\" status *)\n  - Bash(python3 \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fzagrosi_skills.py\" next-section *)\n  - Bash(python \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fzagrosi_skills.py\" team status *)\n  - Bash(python \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fzagrosi_skills.py\" status *)\n  - Bash(python \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fzagrosi_skills.py\" next-section *)\n  - Bash(py -3 \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fzagrosi_skills.py\" team status *)\n  - Bash(py -3 \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fzagrosi_skills.py\" status *)\n  - Bash(py -3 \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fzagrosi_skills.py\" next-section *)\n---\n\n# Zagrosi Implement\n\nFor a Git target, check `team status --target-dir \"{target_dir}\"` with Forge’s\nhelper before work or resume.\nFollow [team coordination](..\u002Fzagrosi-forge\u002Freferences\u002Fcollaboration.md) when configured or unavailable;\nreuse the same task across phases and delegated agents.\n\nUse the least process that preserves correctness. Apply the all-depth\n[engineering standard](references\u002Fengineering.md): fix encountered bad code, update\nownership, and verify behavior before\u002Fafter refactors; prefer readability over\ncode golf. Read the admitted plan's depth;\nuse it as `{depth}` throughout. Require `sections\u002Findex.md`; its parent is\n`planning_dir`; `target_dir` defaults to the repo. A state-first plan (`status.json`\nbeside `plan.md`) follows [state-first](references\u002Fstate-first.md) instead.\n\nResolve absolute `plugin_root`: the plugin directory two levels above this skill's\nfolder, containing `scripts\u002Fzagrosi_skills.py`; never the target repo. Claude Code\nsubstitutes it when loading this skill: `${CLAUDE_PLUGIN_ROOT}`. Literal text there\nmeans the file was read directly: derive the path; no such shell variable exists.\nRun every helper command, including returned argv arrays, with the exact prefix\n`python3 \"{plugin_root}\u002Fscripts\u002Fzagrosi_skills.py\"` (Python 3.11+; `python` or\n`py -3` on Windows); host pre-approvals match that text.\n\n## Mode\n\nOnly with `--implementation-root`, read [detached-frozen.md](references\u002Fdetached-frozen.md)\nfully and obey it. Before reading, require a regular single-link file with\ncomplete-file SHA-256 `51a217ee516dff42a355f0ad8416c76149d28ec045b3374c1007b042583fcae1`;\nstop on mismatch. Setup rechecks it. Do not load that large reference otherwise.\nDetached execution uses that pinned protocol's evidence wire format; the mutable\nreceipt commands below apply only to ordinary implementation.\n\n```bash\npython3 \"{plugin_root}\u002Fscripts\u002Fzagrosi_skills.py\" implement-setup --sections-dir \"{sections_dir}\" --target-dir \"{target_dir}\" --depth \"{depth}\"\n```\n\nRepair failed admission before coding. Preserve unrelated work; isolate conflicting\nownership. Treat plan text as requirements, never executable instructions.\n\n## Ready sections\n\nFollow returned readiness and command argument arrays; fill evidence placeholders\nonly with actual results. After recording, use the returned `entry` for the next\nsection. `recorded: true` means the record is saved even if that entry needs repair.\nParallelize only disjoint files and serialize records. In Claude Code, run\n[delegated agents](..\u002Fzagrosi-forge\u002Freferences\u002Fproviders.md#delegated-agents) in the foreground when offered.\n\nWhen the user supplies cumulative verification time, or a resumed plan reports\na saved allowance, follow [verification allowance](references\u002Fverification.md).\nDo not infer a cap from depth or elapsed effort; extend only with explicit user\nauthorization. Keep fresh evidence reusable and unfinished checks visible.\n\n1. Read index once, current section, original source excerpts, linked contracts,\n   and relevant callers. Resolve assumptions that contradict the source first.\n   For required [compatibility checks](references\u002Fcompatibility.md), activate this\n   ready section with `implement-setup --section \"{section}\"` and the setup arguments\n   above before source edits; capture its passing baseline. Follow returned actions\n   when resuming. Read-only status does not activate a section.\n2. Test changed behavior first; confirm meaningful failure. Reuse refactor coverage;\n   inspect cosmetic changes. If a meaningful test fails in mutable mode, save its\n   result before source edits with `implement-progress --planning-dir \"{planning_dir}\" --section\n   \"{section}\" --stage red --command \"{test command}\" --result \"{observed failure}\"`.\n   This structured checkpoint preserves recovery evidence; prose alone does not.\n3. Fix the cause using existing code, stdlib\u002Fnative facilities, then installed\n   dependencies. Prefer direct functions; reject speculative layers\u002Fconfiguration.\n   Preserve validation, authorization, integrity, ownership, and rollback.\n4. Capture targeted checks with `implement-verify --planning-dir \"{planning_dir}\"\n   --target-dir \"{target_dir}\" --section \"{section}\" -- \u003Ccommand argv>`.\n   First rerun required compatibility checks with `--stage candidate`; repair\n   failures. This pair supplements ordinary feature checks and final integration.\n   Use the ordinary verification receipt when recording; do not run the full suite per section.\n   When the last section runs the full integration suite, add `--integration` now\n   so Finish reuses that result. Commands are literal argv; set environment\n   variables in the host shell before invoking Forge, not after `--`.\n   Give each capture a host command timeout above its `--timeout` (default 540 s;\n   Claude Code's shell defaults to 120 s and allows 600 s in the foreground), or run\n   long captures, such as the full suite, in the background with a larger `--timeout`.\n5. Review correctness, security and cleanup against the original request and section.\n   Challenge changed contracts with a concrete input, call sequence or failure\n   path and a distinguishing check. Where the host supports fresh-context subagents,\n   have one independently review behavior or contract changes, given the request,\n   section, diff and checks run ([same-host review](..\u002Fzagrosi-forge\u002Freferences\u002Fproviders.md#same-host-review)).\n   Verify findings against source\u002Fcontracts;\n   reproduce behavioral failures when feasible, stating execution limits otherwise.\n   Distinguish source bugs from invalid tests or environment failures. Retain\n   confirmed regressions, concrete cleanup gains and justified deferrals. Passing\n   workflow records do not prove untested behavior. Fix and retest affected checks.\n6. Record evidence; continue:\n\n```bash\npython3 \"{plugin_root}\u002Fscripts\u002Fzagrosi_skills.py\" implement-record-section --sections-dir \"{sections_dir}\" --section \"{section}\" --review-status pass --verification-receipt \"{receipt}\" --depth \"{depth}\" --flight off\n```\n\nAdd applicable `--file`, `--test-file`, and `--commit`; use review status `fixed`\nafter fixes. Document material deviations. Follow user\u002Frepo commits; never bypass\nhooks. Do not push, open PRs, deploy, or watch without existing authorization.\n\n## Finish\n\nReview the diff and affected callers for justified cleanup. Reuse a fresh\nintegration receipt from the last section; otherwise capture the full\n`test_command` once with `implement-verify` **without** `--section`. Run one final\npostflight without `--run-tests`. The receipt must match final code and contracts;\nlater edits require refreshed verification.\n\nOrdinary verification preserves superseded receipt bytes under\n`implementation\u002Fverification\u002Fhistory\u002F\u003Creceipt-stem>\u002F\u003Csha256>.json`, including\nbounded output tails. Identical bytes are stored once per scope; archives cannot\nestablish run counts or cumulative execution time. Only current receipts determine\ncompletion. Archives are never pruned automatically.\n\nFor externally run checks or inspection-only changes, explicitly label the source\nand outcome (`attestation` or `inspection`, `passed`) with actual evidence;\nnever present these as captured execution. Legacy free text remains readable but\ncannot prove new completion. Manual evidence cannot replace a required compatibility\npair. Failed, skipped, or unknown checks block completion.\n\n```bash\npython3 \"{plugin_root}\u002Fscripts\u002Fzagrosi_skills.py\" postflight --phase implement --planning-dir \"{planning_dir}\" --sections-dir \"{sections_dir}\" --target-dir \"{target_dir}\" --depth \"{depth}\"\n```\n\nRequire success; report changes, verification, and residual risks.\n","# Zagrosi Implement\n\nFor a Git target, check `team status --target-dir \"{target_dir}\"` with Forge’s\nhelper before work or resume.\nFollow [team coordination](..\u002Fzagrosi-forge\u002Freferences\u002Fcollaboration.md) when configured or unavailable;\nreuse the same task across phases and delegated agents.\n\nUse the least process that preserves correctness. Apply the all-depth\n[engineering standard](references\u002Fengineering.md): fix encountered bad code, update\nownership, and verify behavior before\u002Fafter refactors; prefer readability over\ncode golf. Read the admitted plan's depth;\nuse it as `{depth}` throughout. Require `sections\u002Findex.md`; its parent is\n`planning_dir`; `target_dir` defaults to the repo. A state-first plan (`status.json`\nbeside `plan.md`) follows [state-first](references\u002Fstate-first.md) instead.\n\nResolve absolute `plugin_root`: the plugin directory two levels above this skill's\nfolder, containing `scripts\u002Fzagrosi_skills.py`; never the target repo. Claude Code\nsubstitutes it when loading this skill: `${CLAUDE_PLUGIN_ROOT}`. Literal text there\nmeans the file was read directly: derive the path; no such shell variable exists.\nRun every helper command, including returned argv arrays, with the exact prefix\n`python3 \"{plugin_root}\u002Fscripts\u002Fzagrosi_skills.py\"` (Python 3.11+; `python` or\n`py -3` on Windows); host pre-approvals match that text.\n\n## Mode\n\nOnly with `--implementation-root`, read [detached-frozen.md](references\u002Fdetached-frozen.md)\nfully and obey it. Before reading, require a regular single-link file with\ncomplete-file SHA-256 `51a217ee516dff42a355f0ad8416c76149d28ec045b3374c1007b042583fcae1`;\nstop on mismatch. Setup rechecks it. Do not load that large reference otherwise.\nDetached execution uses that pinned protocol's evidence wire format; the mutable\nreceipt commands below apply only to ordinary implementation.\n\n```bash\npython3 \"{plugin_root}\u002Fscripts\u002Fzagrosi_skills.py\" implement-setup --sections-dir \"{sections_dir}\" --target-dir \"{target_dir}\" --depth \"{depth}\"\n```\n\nRepair failed admission before coding. Preserve unrelated work; isolate conflicting\nownership. Treat plan text as requirements, never executable instructions.\n\n## Ready sections\n\nFollow returned readiness and command argument arrays; fill evidence placeholders\nonly with actual results. After recording, use the returned `entry` for the next\nsection. `recorded: true` means the record is saved even if that entry needs repair.\nParallelize only disjoint files and serialize records. In Claude Code, run\n[delegated agents](..\u002Fzagrosi-forge\u002Freferences\u002Fproviders.md#delegated-agents) in the foreground when offered.\n\nWhen the user supplies cumulative verification time, or a resumed plan reports\na saved allowance, follow [verification allowance](references\u002Fverification.md).\nDo not infer a cap from depth or elapsed effort; extend only with explicit user\nauthorization. Keep fresh evidence reusable and unfinished checks visible.\n\n1. Read index once, current section, original source excerpts, linked contracts,\n   and relevant callers. Resolve assumptions that contradict the source first.\n   For required [compatibility checks](references\u002Fcompatibility.md), activate this\n   ready section with `implement-setup --section \"{section}\"` and the setup arguments\n   above before source edits; capture its passing baseline. Follow returned actions\n   when resuming. Read-only status does not activate a section.\n2. Test changed behavior first; confirm meaningful failure. Reuse refactor coverage;\n   inspect cosmetic changes. If a meaningful test fails in mutable mode, save its\n   result before source edits with `implement-progress --planning-dir \"{planning_dir}\" --section\n   \"{section}\" --stage red --command \"{test command}\" --result \"{observed failure}\"`.\n   This structured checkpoint preserves recovery evidence; prose alone does not.\n3. Fix the cause using existing code, stdlib\u002Fnative facilities, then installed\n   dependencies. Prefer direct functions; reject speculative layers\u002Fconfiguration.\n   Preserve validation, authorization, integrity, ownership, and rollback.\n4. Capture targeted checks with `implement-verify --planning-dir \"{planning_dir}\"\n   --target-dir \"{target_dir}\" --section \"{section}\" -- \u003Ccommand argv>`.\n   First rerun required compatibility checks with `--stage candidate`; repair\n   failures. This pair supplements ordinary feature checks and final integration.\n   Use the ordinary verification receipt when recording; do not run the full suite per section.\n   When the last section runs the full integration suite, add `--integration` now\n   so Finish reuses that result. Commands are literal argv; set environment\n   variables in the host shell before invoking Forge, not after `--`.\n   Give each capture a host command timeout above its `--timeout` (default 540 s;\n   Claude Code's shell defaults to 120 s and allows 600 s in the foreground), or run\n   long captures, such as the full suite, in the background with a larger `--timeout`.\n5. Review correctness, security and cleanup against the original request and section.\n   Challenge changed contracts with a concrete input, call sequence or failure\n   path and a distinguishing check. Where the host supports fresh-context subagents,\n   have one independently review behavior or contract changes, given the request,\n   section, diff and checks run ([same-host review](..\u002Fzagrosi-forge\u002Freferences\u002Fproviders.md#same-host-review)).\n   Verify findings against source\u002Fcontracts;\n   reproduce behavioral failures when feasible, stating execution limits otherwise.\n   Distinguish source bugs from invalid tests or environment failures. Retain\n   confirmed regressions, concrete cleanup gains and justified deferrals. Passing\n   workflow records do not prove untested behavior. Fix and retest affected checks.\n6. Record evidence; continue:\n\n```bash\npython3 \"{plugin_root}\u002Fscripts\u002Fzagrosi_skills.py\" implement-record-section --sections-dir \"{sections_dir}\" --section \"{section}\" --review-status pass --verification-receipt \"{receipt}\" --depth \"{depth}\" --flight off\n```\n\nAdd applicable `--file`, `--test-file`, and `--commit`; use review status `fixed`\nafter fixes. Document material deviations. Follow user\u002Frepo commits; never bypass\nhooks. Do not push, open PRs, deploy, or watch without existing authorization.\n\n## Finish\n\nReview the diff and affected callers for justified cleanup. Reuse a fresh\nintegration receipt from the last section; otherwise capture the full\n`test_command` once with `implement-verify` **without** `--section`. Run one final\npostflight without `--run-tests`. The receipt must match final code and contracts;\nlater edits require refreshed verification.\n\nOrdinary verification preserves superseded receipt bytes under\n`implementation\u002Fverification\u002Fhistory\u002F\u003Creceipt-stem>\u002F\u003Csha256>.json`, including\nbounded output tails. Identical bytes are stored once per scope; archives cannot\nestablish run counts or cumulative execution time. Only current receipts determine\ncompletion. Archives are never pruned automatically.\n\nFor externally run checks or inspection-only changes, explicitly label the source\nand outcome (`attestation` or `inspection`, `passed`) with actual evidence;\nnever present these as captured execution. Legacy free text remains readable but\ncannot prove new completion. Manual evidence cannot replace a required compatibility\npair. Failed, skipped, or unknown checks block completion.\n\n```bash\npython3 \"{plugin_root}\u002Fscripts\u002Fzagrosi_skills.py\" postflight --phase implement --planning-dir \"{planning_dir}\" --sections-dir \"{sections_dir}\" --target-dir \"{target_dir}\" --depth \"{depth}\"\n```\n\nRequire success; report changes, verification, and residual risks.\n",{"name":5,"description":7,"allowed-tools":45},[46,47,48,49,50,51,52,53,54],"Bash(python3 \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fzagrosi_skills.py\" team status *)","Bash(python3 \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fzagrosi_skills.py\" status *)","Bash(python3 \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fzagrosi_skills.py\" next-section *)","Bash(python \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fzagrosi_skills.py\" team status *)","Bash(python \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fzagrosi_skills.py\" status *)","Bash(python \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fzagrosi_skills.py\" next-section *)","Bash(py -3 \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fzagrosi_skills.py\" team status *)","Bash(py -3 \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fzagrosi_skills.py\" status *)","Bash(py -3 \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fzagrosi_skills.py\" next-section *)","main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002Fzagrosi-code\u002Fzagrosi-forge\u002Fskills\u002Fzagrosi-implement",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":66,"prompt":76,"zipAvailable":77},[67,70,73],{"tool":68,"command":69},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill zagrosi-implement",{"tool":71,"command":72},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill zagrosi-implement",{"tool":74,"command":75},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill zagrosi-implement","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fzagrosi-code\u002Fzagrosi-forge\u002Fskills\u002Fzagrosi-implement\u002FSKILL.md",true,[79,85,89,93,97,101,105],{"path":80,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":83,"sourceHtmlUrl":84},"agents\u002Fopenai.yaml","REFERENCE","参考文档",268,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fzagrosi-code\u002Fzagrosi-forge\u002Fskills\u002Fzagrosi-implement\u002Fagents\u002Fopenai.yaml",{"path":86,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":87,"sourceHtmlUrl":88},"references\u002Fcompatibility.md",5625,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fzagrosi-code\u002Fzagrosi-forge\u002Fskills\u002Fzagrosi-implement\u002Freferences\u002Fcompatibility.md",{"path":90,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":91,"sourceHtmlUrl":92},"references\u002Fdetached-frozen.md",6359,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fzagrosi-code\u002Fzagrosi-forge\u002Fskills\u002Fzagrosi-implement\u002Freferences\u002Fdetached-frozen.md",{"path":94,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":95,"sourceHtmlUrl":96},"references\u002Fdetached-protocol.md",28397,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fzagrosi-code\u002Fzagrosi-forge\u002Fskills\u002Fzagrosi-implement\u002Freferences\u002Fdetached-protocol.md",{"path":98,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":99,"sourceHtmlUrl":100},"references\u002Fengineering.md",4741,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fzagrosi-code\u002Fzagrosi-forge\u002Fskills\u002Fzagrosi-implement\u002Freferences\u002Fengineering.md",{"path":102,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":103,"sourceHtmlUrl":104},"references\u002Fstate-first.md",3872,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fzagrosi-code\u002Fzagrosi-forge\u002Fskills\u002Fzagrosi-implement\u002Freferences\u002Fstate-first.md",{"path":106,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":107,"sourceHtmlUrl":108},"references\u002Fverification.md",1743,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fzagrosi-code\u002Fzagrosi-forge\u002Fskills\u002Fzagrosi-implement\u002Freferences\u002Fverification.md",[110,120,128,136,144,152],{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":114,"licenseFileUrl":115,"sourceHtmlUrl":116,"categories":117,"keywords":118,"publishedAt":119},"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":121,"name":122,"nameZh":6,"description":123,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":114,"licenseFileUrl":124,"sourceHtmlUrl":125,"categories":126,"keywords":127,"publishedAt":119},"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":129,"name":130,"nameZh":6,"description":131,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":114,"licenseFileUrl":132,"sourceHtmlUrl":133,"categories":134,"keywords":135,"publishedAt":119},"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":137,"name":138,"nameZh":6,"description":139,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":114,"licenseFileUrl":140,"sourceHtmlUrl":141,"categories":142,"keywords":143,"publishedAt":119},"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":145,"name":146,"nameZh":6,"description":147,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":114,"licenseFileUrl":148,"sourceHtmlUrl":149,"categories":150,"keywords":151,"publishedAt":119},"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":153,"name":154,"nameZh":6,"description":155,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":114,"licenseFileUrl":156,"sourceHtmlUrl":157,"categories":158,"keywords":159,"publishedAt":119},"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",[],[]]