[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MJGQGM2PB1JZCZ2VMN4DP5":3,"skill-same:01M6MJGQGM2PB1JZCZ2VMN4DP5":97},{"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":23,"publishedAt":46,"linkOnly":47,"markdownContent":48,"markdownBody":49,"frontMatter":50,"refName":51,"commitSha":52,"skillDirectory":53,"forksCount":54,"repositoryHtmlUrl":55,"repositoryHomepageUrl":56,"ownerHtmlUrl":57,"ownerBlogUrl":58,"ownerDescription":59,"updatedAt":60,"install":61,"resources":74},"01M6MJGQGM2PB1JZCZ2VMN4DP5","review-pr",null,"Review a GitHub pull request with the RAG + code-graph pipeline (reviewer MCP server). Use when the user asks to review a PR (\"review PR 123\", \"заревьюй PR\", a PR URL). Requires ParadeDB\u002FNeo4j running and a built base index.","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\u002Fmimfort\u002Frag_for_git\u002Fplugin\u002Fskills\u002Freview-pr\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45],"review","review pr","pr","running","MCP","when","request","paradedb","URL","with","base","use","reviewer","neo4j","pipeline","server","pull","code","pull request","rag","mcp server","github","2026-11-10 10:12:30",false,"---\nname: review-pr\ndescription: Review a GitHub pull request with the RAG + code-graph pipeline (reviewer MCP server). Use when the user asks to review a PR (\"review PR 123\", \"заревьюй PR\", a PR URL). Requires ParadeDB\u002FNeo4j running and a built base index.\n---\n\n# PR Review Pipeline\n\nOrchestrate a full PR review using the `reviewer` MCP server tools. The deterministic\ntail (policy gate, line grounding, dedup, idempotency, comment cap, publishing) is\nhandled by `publish_review` — your job is analysis quality, not formatting rules.\n\n## Inputs\n\nParse from $ARGUMENTS: target PR as `owner\u002Frepo#N`, `owner\u002Frepo N`, or a GitHub PR URL.\n`--dry-run` flag → pass `dry_run=true` to publish_review and show the report instead\nof posting.\n\n**Include resolution (applies to all steps below).** When you read any\n`references\u002F*-prompt.md` file to dispatch a subagent (steps 3, 4, and 5 —\nanalyze, requirements, risk changes, blast-radius, verify), it may contain\n`\u003C!-- include: _common\u002F\u003Cfile>.md -->` markers. Before putting the prompt into\nthe subagent, replace each marker with the verbatim contents of that file\n(path is relative to `plugin\u002Fskills\u002F`). These `_common\u002F*.md` files are the\nsingle source of the shared findings-schema \u002F anti-hallucination \u002F tool-usage\nblocks.\n\n## Pipeline\n\n1. **Prepare.** Call `prepare_review(repo, pr)`. The payload contains:\n   - `pr`: `{number, title, body, base_sha, head_sha, base_ref, draft}`\n   - `policy`: `{severity_threshold, min_confidence, max_comments, categories, ignore, output_language}`\n   - `units`: list of `{path, patch, commentable_right, commentable_left}`\n   - `task_board`: `{type, project, key_pattern, create_target, done_target, options}` or null —\n     non-secret generic board metadata from `.review.yml`\n   - `task_keys`: `{primary, others}` or null — task keys extracted from the PR by the server\n   - `risk_paths`: bounded non-Python items with\n     `{path, status, reasons, patch, commentable_right, commentable_left}`\n   - `risk_skipped_paths`: classified paths omitted by the deterministic cap\n   - `skipped_paths`, `skip_drafts`, `suggestions_mode`\n\n   If the payload has `status: \"skipped\"`, this is NOT an error but an expected skip\n   (the PR's target branch is not in `REVIEW_BRANCHES`). Tell the user the `reason`\n   value and stop: do not run analyze\u002Fpublish, and do not treat it as a failure.\n\n   If `pr.draft` is true and `skip_drafts` is true, stop and tell the user.\n   Note `policy.output_language` — ALL finding messages, suggestions and the summary\n   MUST be written in that language.\n\n2. **Task context (optional).** Only if `task_board` is non-null. Resolve the task key: an\n   explicit key in `$ARGUMENTS` wins; otherwise use `task_keys.primary`. If no key is available,\n   skip this step and note in the summary that no task key was found.\n\n   Task reads are scoped to this repo's project: pass `project=\u003Ctask_board.project>` (from the target\n   branch `.review.yml`, see step with `task_board`) to `get_task`\u002F`get_task_context`\u002F`search_tasks`\n   (PRI-170; empty `project` = unscoped).\n\n   Read the task **store-first** (unifies with solve-task):\n   - Call reviewer `get_task(key, project=\u003Ctask_board.project>)` first. **Hit** (object with a `key`) → use it as the `TaskBrief`\n     directly; it is already indexed by the server-side sync, so do NOT call `index_task`.\n   - **Miss** (`null`) → call generic incremental\n     `sync_board(board=\u003Ctask_board.project or null>, board_type=\u003Ctask_board.type>,\n     provider_options=\u003Ctask_board.options or {}>, limit=null, purge_orphaned=false)`, then call\n     `get_task(key, project=\u003Ctask_board.project>)` once more. A sync error or second miss is\n     fail-open: skip the requirements dimension and note the reason in the summary — NEVER abort\n     the review.\n\n   The `TaskBrief` schema is `{key, aliases[], title, description, criteria[], status, url, links[]}`\n   (phase 3 adds `aliases[]` and uses `links[]`). On either store **hit** the brief is already\n   indexed — do NOT re-index. Then gather task context to sharpen the requirements check:\n   - `get_task_context(TaskBrief.key, project=\u003Ctask_board.project>)` → linked tasks, their PRs, and the code those PRs touched;\n   - `search_tasks(\"\u003CTaskBrief.title>. \u003Cfirst lines of description>\", project=\u003Ctask_board.project>)` → semantically similar tasks.\n   Keep ONLY the related\u002Fsimilar items that look relevant; you will pass them to the requirements\n   dimension in step 4. All of this is best-effort: if `index_task`\u002F`get_task_context`\u002F`search_tasks`\n   return a \"(… unavailable)\" note or error, continue — never abort the review.\n\n3. **Analyze (fan-out).** The Python per-unit fan-out remains based only on `units`.\n   For each unit in `units`, dispatch a subagent (Task tool,\n   run independent subagents in parallel; batch units if there are more than ~10) with:\n   - the contents of `references\u002Fanalyze-prompt.md` (read it once, resolve includes, include verbatim);\n   - the unit's `path`, `patch`, `commentable_right` (sorted list of new-file line numbers\n     available for inline), `commentable_left` (sorted list of old-file line numbers available\n     for inline), and the PR `title`\u002F`body`;\n   - the repo\u002Fpr identifiers so the subagent can call the reviewer MCP tools\n     (`search_code`, `get_related_symbols`, `read_file`, `get_definition`,\n     `find_callers`, `get_changed_file_diff`);\n   - the target output language.\n   Each subagent submits findings via `submit_findings(repo, pr, findings=[...])` (schema-enforced; the server assigns ids).\n\n4. **Dimensions (parallel with step 3).** Dispatch whole-diff subagents:\n   - performance: follow the methodology of `..\u002Fperformance-review\u002FSKILL.md`\n     (Goal, Method, Severity sections);\n   - maintainability: follow `..\u002Fmaintainability-review\u002FSKILL.md`;\n   - requirements (ONLY if a `TaskBrief` was built in step 2): dispatch one subagent with\n     `references\u002Frequirements-prompt.md`, the diffs of all units (path + patch), the `TaskBrief`,\n     plus the related\u002Fsimilar task context gathered in step 2 (linked tasks, their PRs, touched code,\n     similar tasks) as an optional \"Related context\" block, the repo\u002Fpr identifiers (so it can call\n     the reviewer MCP tools), and the target output language. It submits findings via\n     `submit_findings` with category `requirements`.\n   - risk changes (ONLY if `risk_paths` is non-empty): dispatch one subagent with\n     `references\u002Frisk-changes-prompt.md`, every risk item, the PR title\u002Fbody, repo\u002Fpr\n     identifiers, and output language. It submits only grounded `correctness`\u002F`security`\n     findings via `submit_findings`.\n   - blast-radius: dispatch one subagent with `references\u002Fblast-radius-prompt.md`, the diffs of\n     all units (path + patch), each unit's `commentable_right`\u002F`commentable_left` (the line numbers\n     where inline comments are allowed), the PR `title`\u002F`body`, the repo\u002Fpr identifiers, and the\n     target output language. It runs two checks — changed signatures breaking callers (via\n     `get_impact`) and interface expansion (a changed `Protocol`\u002FABC whose implementations must all\n     be updated, via `get_related_symbols`\u002F`search_code`) — and submits findings via\n     `submit_findings` with category `correctness`.\n   Give the performance\u002Fmaintainability subagents: the diffs of all units (path + patch), the\n   repo\u002Fpr identifiers so they can call the reviewer MCP tools, and the target output language.\n   They must submit findings via `submit_findings` (category `performance` \u002F `maintainability`).\n\n5. **Verify.** Dispatch one subagent with `references\u002Fverify-prompt.md` and the\n   repo\u002Fpr identifiers. It reads candidates via `get_candidate_findings(repo, pr)`\n   and submits verdicts via `submit_verdicts(repo, pr, verdicts=[{id, is_real}])`.\n   A finding with `is_real=false` is dropped at publish; a finding with no verdict\n   is kept (recall-safe — no orchestrator action needed if verify fails).\n\n6. **Publish.** Compose a short review summary (2-5 sentences, in\n   `policy.output_language`): what the PR does, overall assessment, key risks.\n   If a task was read, state whether the PR meets the task's requirements; if the task context was\n   requested but unavailable (no key, sync error, task not found), say so briefly.\n   Mention files that were not analyzed: failed subagents and `skipped_paths`\n   from the prepare payload. Name a failed risk subagent in the summary, and report every\n   `risk_skipped_paths` entry as not inspected. Call `publish_review(repo, pr, summary, dry_run, task_key)`\n   where `task_key` is the canonical `TaskBrief.key` if a task was read (else omit \u002F null). Review\n   cost is captured automatically by the plugin's `PreToolUse` hook (`plugin\u002Fhooks\u002Freview_cost.py`)\n   into a sidecar file that `publish_review` reads server-side — no action needed here. If the CLI\n   separately provides model\u002Fusage\u002Fcost metadata, pass it via the optional keyword arguments\n   `model`, `usage`, and `total_cost` to `publish_review` anyway: explicit arguments take priority\n   over the sidecar on a per-field basis, so pass whatever the CLI can give you. When published,\n   this links the PR to the task in the graph for future reviews. Report to the user:\n   posted\u002Fdry-run, inline count, and the report counters\n   (dropped_by_gate\u002Fdeduped\u002Finvalid\u002Falready_posted\u002Fmoved_to_summary\u002Fcapped\u002Fverify_rejected), run_id.\n\n## Failure handling\n\n- A failed analyze subagent must not abort the run: continue with the other units\n  and mention the skipped file in the summary.\n- A failed risk changes subagent is fail-open: continue with the review and name it in\n  the summary.\n- A `prepare_review` payload with `status: \"skipped\"` is not a failure: report its\n  `reason` (target branch not tracked in `REVIEW_BRANCHES`) and stop without analyze\u002Fpublish.\n- If `prepare_review` fails, surface its error text to the user as-is (it contains\n  the remediation hint, e.g. \"docker compose up -d\").\n- Never post comments yourself via gh\u002Fgit — only through `publish_review`.\n\n## Reporting a reviewer defect\n\n\u003C!-- include: _common\u002Fbug-reporting.md -->\n","# PR Review Pipeline\n\nOrchestrate a full PR review using the `reviewer` MCP server tools. The deterministic\ntail (policy gate, line grounding, dedup, idempotency, comment cap, publishing) is\nhandled by `publish_review` — your job is analysis quality, not formatting rules.\n\n## Inputs\n\nParse from $ARGUMENTS: target PR as `owner\u002Frepo#N`, `owner\u002Frepo N`, or a GitHub PR URL.\n`--dry-run` flag → pass `dry_run=true` to publish_review and show the report instead\nof posting.\n\n**Include resolution (applies to all steps below).** When you read any\n`references\u002F*-prompt.md` file to dispatch a subagent (steps 3, 4, and 5 —\nanalyze, requirements, risk changes, blast-radius, verify), it may contain\n`\u003C!-- include: _common\u002F\u003Cfile>.md -->` markers. Before putting the prompt into\nthe subagent, replace each marker with the verbatim contents of that file\n(path is relative to `plugin\u002Fskills\u002F`). These `_common\u002F*.md` files are the\nsingle source of the shared findings-schema \u002F anti-hallucination \u002F tool-usage\nblocks.\n\n## Pipeline\n\n1. **Prepare.** Call `prepare_review(repo, pr)`. The payload contains:\n   - `pr`: `{number, title, body, base_sha, head_sha, base_ref, draft}`\n   - `policy`: `{severity_threshold, min_confidence, max_comments, categories, ignore, output_language}`\n   - `units`: list of `{path, patch, commentable_right, commentable_left}`\n   - `task_board`: `{type, project, key_pattern, create_target, done_target, options}` or null —\n     non-secret generic board metadata from `.review.yml`\n   - `task_keys`: `{primary, others}` or null — task keys extracted from the PR by the server\n   - `risk_paths`: bounded non-Python items with\n     `{path, status, reasons, patch, commentable_right, commentable_left}`\n   - `risk_skipped_paths`: classified paths omitted by the deterministic cap\n   - `skipped_paths`, `skip_drafts`, `suggestions_mode`\n\n   If the payload has `status: \"skipped\"`, this is NOT an error but an expected skip\n   (the PR's target branch is not in `REVIEW_BRANCHES`). Tell the user the `reason`\n   value and stop: do not run analyze\u002Fpublish, and do not treat it as a failure.\n\n   If `pr.draft` is true and `skip_drafts` is true, stop and tell the user.\n   Note `policy.output_language` — ALL finding messages, suggestions and the summary\n   MUST be written in that language.\n\n2. **Task context (optional).** Only if `task_board` is non-null. Resolve the task key: an\n   explicit key in `$ARGUMENTS` wins; otherwise use `task_keys.primary`. If no key is available,\n   skip this step and note in the summary that no task key was found.\n\n   Task reads are scoped to this repo's project: pass `project=\u003Ctask_board.project>` (from the target\n   branch `.review.yml`, see step with `task_board`) to `get_task`\u002F`get_task_context`\u002F`search_tasks`\n   (PRI-170; empty `project` = unscoped).\n\n   Read the task **store-first** (unifies with solve-task):\n   - Call reviewer `get_task(key, project=\u003Ctask_board.project>)` first. **Hit** (object with a `key`) → use it as the `TaskBrief`\n     directly; it is already indexed by the server-side sync, so do NOT call `index_task`.\n   - **Miss** (`null`) → call generic incremental\n     `sync_board(board=\u003Ctask_board.project or null>, board_type=\u003Ctask_board.type>,\n     provider_options=\u003Ctask_board.options or {}>, limit=null, purge_orphaned=false)`, then call\n     `get_task(key, project=\u003Ctask_board.project>)` once more. A sync error or second miss is\n     fail-open: skip the requirements dimension and note the reason in the summary — NEVER abort\n     the review.\n\n   The `TaskBrief` schema is `{key, aliases[], title, description, criteria[], status, url, links[]}`\n   (phase 3 adds `aliases[]` and uses `links[]`). On either store **hit** the brief is already\n   indexed — do NOT re-index. Then gather task context to sharpen the requirements check:\n   - `get_task_context(TaskBrief.key, project=\u003Ctask_board.project>)` → linked tasks, their PRs, and the code those PRs touched;\n   - `search_tasks(\"\u003CTaskBrief.title>. \u003Cfirst lines of description>\", project=\u003Ctask_board.project>)` → semantically similar tasks.\n   Keep ONLY the related\u002Fsimilar items that look relevant; you will pass them to the requirements\n   dimension in step 4. All of this is best-effort: if `index_task`\u002F`get_task_context`\u002F`search_tasks`\n   return a \"(… unavailable)\" note or error, continue — never abort the review.\n\n3. **Analyze (fan-out).** The Python per-unit fan-out remains based only on `units`.\n   For each unit in `units`, dispatch a subagent (Task tool,\n   run independent subagents in parallel; batch units if there are more than ~10) with:\n   - the contents of `references\u002Fanalyze-prompt.md` (read it once, resolve includes, include verbatim);\n   - the unit's `path`, `patch`, `commentable_right` (sorted list of new-file line numbers\n     available for inline), `commentable_left` (sorted list of old-file line numbers available\n     for inline), and the PR `title`\u002F`body`;\n   - the repo\u002Fpr identifiers so the subagent can call the reviewer MCP tools\n     (`search_code`, `get_related_symbols`, `read_file`, `get_definition`,\n     `find_callers`, `get_changed_file_diff`);\n   - the target output language.\n   Each subagent submits findings via `submit_findings(repo, pr, findings=[...])` (schema-enforced; the server assigns ids).\n\n4. **Dimensions (parallel with step 3).** Dispatch whole-diff subagents:\n   - performance: follow the methodology of `..\u002Fperformance-review\u002FSKILL.md`\n     (Goal, Method, Severity sections);\n   - maintainability: follow `..\u002Fmaintainability-review\u002FSKILL.md`;\n   - requirements (ONLY if a `TaskBrief` was built in step 2): dispatch one subagent with\n     `references\u002Frequirements-prompt.md`, the diffs of all units (path + patch), the `TaskBrief`,\n     plus the related\u002Fsimilar task context gathered in step 2 (linked tasks, their PRs, touched code,\n     similar tasks) as an optional \"Related context\" block, the repo\u002Fpr identifiers (so it can call\n     the reviewer MCP tools), and the target output language. It submits findings via\n     `submit_findings` with category `requirements`.\n   - risk changes (ONLY if `risk_paths` is non-empty): dispatch one subagent with\n     `references\u002Frisk-changes-prompt.md`, every risk item, the PR title\u002Fbody, repo\u002Fpr\n     identifiers, and output language. It submits only grounded `correctness`\u002F`security`\n     findings via `submit_findings`.\n   - blast-radius: dispatch one subagent with `references\u002Fblast-radius-prompt.md`, the diffs of\n     all units (path + patch), each unit's `commentable_right`\u002F`commentable_left` (the line numbers\n     where inline comments are allowed), the PR `title`\u002F`body`, the repo\u002Fpr identifiers, and the\n     target output language. It runs two checks — changed signatures breaking callers (via\n     `get_impact`) and interface expansion (a changed `Protocol`\u002FABC whose implementations must all\n     be updated, via `get_related_symbols`\u002F`search_code`) — and submits findings via\n     `submit_findings` with category `correctness`.\n   Give the performance\u002Fmaintainability subagents: the diffs of all units (path + patch), the\n   repo\u002Fpr identifiers so they can call the reviewer MCP tools, and the target output language.\n   They must submit findings via `submit_findings` (category `performance` \u002F `maintainability`).\n\n5. **Verify.** Dispatch one subagent with `references\u002Fverify-prompt.md` and the\n   repo\u002Fpr identifiers. It reads candidates via `get_candidate_findings(repo, pr)`\n   and submits verdicts via `submit_verdicts(repo, pr, verdicts=[{id, is_real}])`.\n   A finding with `is_real=false` is dropped at publish; a finding with no verdict\n   is kept (recall-safe — no orchestrator action needed if verify fails).\n\n6. **Publish.** Compose a short review summary (2-5 sentences, in\n   `policy.output_language`): what the PR does, overall assessment, key risks.\n   If a task was read, state whether the PR meets the task's requirements; if the task context was\n   requested but unavailable (no key, sync error, task not found), say so briefly.\n   Mention files that were not analyzed: failed subagents and `skipped_paths`\n   from the prepare payload. Name a failed risk subagent in the summary, and report every\n   `risk_skipped_paths` entry as not inspected. Call `publish_review(repo, pr, summary, dry_run, task_key)`\n   where `task_key` is the canonical `TaskBrief.key` if a task was read (else omit \u002F null). Review\n   cost is captured automatically by the plugin's `PreToolUse` hook (`plugin\u002Fhooks\u002Freview_cost.py`)\n   into a sidecar file that `publish_review` reads server-side — no action needed here. If the CLI\n   separately provides model\u002Fusage\u002Fcost metadata, pass it via the optional keyword arguments\n   `model`, `usage`, and `total_cost` to `publish_review` anyway: explicit arguments take priority\n   over the sidecar on a per-field basis, so pass whatever the CLI can give you. When published,\n   this links the PR to the task in the graph for future reviews. Report to the user:\n   posted\u002Fdry-run, inline count, and the report counters\n   (dropped_by_gate\u002Fdeduped\u002Finvalid\u002Falready_posted\u002Fmoved_to_summary\u002Fcapped\u002Fverify_rejected), run_id.\n\n## Failure handling\n\n- A failed analyze subagent must not abort the run: continue with the other units\n  and mention the skipped file in the summary.\n- A failed risk changes subagent is fail-open: continue with the review and name it in\n  the summary.\n- A `prepare_review` payload with `status: \"skipped\"` is not a failure: report its\n  `reason` (target branch not tracked in `REVIEW_BRANCHES`) and stop without analyze\u002Fpublish.\n- If `prepare_review` fails, surface its error text to the user as-is (it contains\n  the remediation hint, e.g. \"docker compose up -d\").\n- Never post comments yourself via gh\u002Fgit — only through `publish_review`.\n\n## Reporting a reviewer defect\n\n\u003C!-- include: _common\u002Fbug-reporting.md -->\n",{"name":5,"description":7},"main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002Fmimfort\u002Frag_for_git\u002Fplugin\u002Fskills\u002Freview-pr",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":62,"prompt":72,"zipAvailable":73},[63,66,69],{"tool":64,"command":65},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill review-pr",{"tool":67,"command":68},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill review-pr",{"tool":70,"command":71},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill review-pr","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fmimfort\u002Frag_for_git\u002Fplugin\u002Fskills\u002Freview-pr\u002FSKILL.md",true,[75,81,85,89,93],{"path":76,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":79,"sourceHtmlUrl":80},"references\u002Fanalyze-prompt.md","REFERENCE","参考文档",2901,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fmimfort\u002Frag_for_git\u002Fplugin\u002Fskills\u002Freview-pr\u002Freferences\u002Fanalyze-prompt.md",{"path":82,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":83,"sourceHtmlUrl":84},"references\u002Fblast-radius-prompt.md",6404,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fmimfort\u002Frag_for_git\u002Fplugin\u002Fskills\u002Freview-pr\u002Freferences\u002Fblast-radius-prompt.md",{"path":86,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":87,"sourceHtmlUrl":88},"references\u002Frequirements-prompt.md",2798,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fmimfort\u002Frag_for_git\u002Fplugin\u002Fskills\u002Freview-pr\u002Freferences\u002Frequirements-prompt.md",{"path":90,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":91,"sourceHtmlUrl":92},"references\u002Frisk-changes-prompt.md",1863,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fmimfort\u002Frag_for_git\u002Fplugin\u002Fskills\u002Freview-pr\u002Freferences\u002Frisk-changes-prompt.md",{"path":94,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":95,"sourceHtmlUrl":96},"references\u002Fverify-prompt.md",2562,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fmimfort\u002Frag_for_git\u002Fplugin\u002Fskills\u002Freview-pr\u002Freferences\u002Fverify-prompt.md",[98,108,116,124,132,140],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":102,"licenseFileUrl":103,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":107},"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":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":102,"licenseFileUrl":112,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":107},"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":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":102,"licenseFileUrl":120,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":107},"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":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":102,"licenseFileUrl":128,"sourceHtmlUrl":129,"categories":130,"keywords":131,"publishedAt":107},"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":133,"name":134,"nameZh":6,"description":135,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":102,"licenseFileUrl":136,"sourceHtmlUrl":137,"categories":138,"keywords":139,"publishedAt":107},"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":141,"name":142,"nameZh":6,"description":143,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":102,"licenseFileUrl":144,"sourceHtmlUrl":145,"categories":146,"keywords":147,"publishedAt":107},"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",[],[]]