[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6FJBHZ24DP4S7S55TAM6AM4":3,"skill-same:01M6FJBHZ24DP4S7S55TAM6AM4":81},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":25,"publishedAt":54,"linkOnly":55,"markdownContent":56,"markdownBody":57,"frontMatter":58,"refName":60,"commitSha":61,"skillDirectory":62,"forksCount":63,"repositoryHtmlUrl":64,"repositoryHomepageUrl":6,"ownerHtmlUrl":65,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":66,"install":67,"resources":80},"01M6FJBHZ24DP4S7S55TAM6AM4","ln-404-test-executor",null,"Executes test tasks (label 'tests') through Todo to To Review with risk-based limits. Use for test task execution. Not for implementation tasks.","boisenoise\u002Fskills-collections","boisenoise","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F193180?v=4","01M6CDBDQK6BDN55ZMA6B6PKBM","01M6CDBDVSJ3JPTBYN26FZ7TZK",12,"MIT","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Flevn-ln-404-test-executor\u002FSKILL.md",[17,22],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53],"test","ln","ln 404 test executor","executor","task","limits","for","path","inspect","with","line","tests","hex","outline","todo","MCP","use","edit","write","read","Bash","verify","risk-based","risk","execution","file","tasks","review","2026-11-10 10:12:30",false,"---\nname: ln-404-test-executor\ndescription: \"Executes test tasks (label 'tests') through Todo to To Review with risk-based limits. Use for test task execution. Not for implementation tasks.\"\nallowed-tools: Read, Grep, Glob, Bash, mcp__hex-line__outline, mcp__hex-line__read_file, mcp__hex-line__edit_file, mcp__hex-line__write_file, mcp__hex-line__verify, mcp__hex-line__changes, mcp__hex-line__inspect_path\nlicense: MIT\n---\n\n> **Paths:** File paths (`shared\u002F`, `references\u002F`, `..\u002Fln-*`) are relative to skills repo root. If not found at CWD, locate this SKILL.md directory and go up one level for repo root. If `shared\u002F` is missing, fetch files via WebFetch from `https:\u002F\u002Fraw.githubusercontent.com\u002Flevnikolaevich\u002Fclaude-code-skills\u002Fmaster\u002Fskills\u002F{path}`.\n\n# Test Task Executor\n\n**Type:** L3 Worker\n\nRuns a single Story final test task (label \"tests\") through implementation\u002Fexecution to To Review.\n\n## Purpose & Scope\n- Handle only tasks labeled \"tests\"; other tasks go to ln-401.\n- Follow the 11-section test task plan (E2E\u002FIntegration\u002FUnit, infra\u002Fdocs\u002Fcleanup).\n- Enforce risk-based constraints: Priority ≥15 scenarios covered; each test passes Usefulness Criteria; no framework\u002FDB\u002Flibrary\u002Fperformance tests.\n- Update Linear\u002Fkanban for this task only: Todo -> In Progress -> To Review.\n\n**Hex-line acceleration (if available):** Use `outline(file_path)` before reading test targets. Use narrow `inspect_path(path=\u003Crelevant test dir>)` to understand test structure; if you intentionally need a full broad inventory of `tests\u002F`, opt in with `max_entries=0` instead of assuming the default pattern cap will show everything.\nUse `grep_search(output_mode=\"summary\")` first to find tests\u002Fhelpers\u002Ffixtures, then escalate to `output_mode=\"content\", edit_ready=true` only when you need canonical hunks for a follow-up edit; use `allow_large_output=true` only as an explicit override. Use `read_file()` and `edit_file()` as the primary path for test\u002Fcode\u002Fconfig files. Keep `read_file()` in discovery mode for normal inspection; use `read_file(edit_ready=true, verbosity=\"full\")` before edits that need revision\u002Fchecksum protocol. Use `verify()` and `changes()` before handoff. Built-in Read\u002FEdit are fallback only when hex-line is unavailable.\n\n## Inputs\n\n| Input | Required | Source | Description |\n|-------|----------|--------|-------------|\n| `taskId` | Yes | args, parent Story, kanban, user | Test task to execute |\n\n**Resolution:** Task Resolution Chain.\n**Status filter:** Todo (label: tests)\n\n## Task Storage Mode\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Fenvironment_state_contract.md`, `shared\u002Freferences\u002Fstorage_mode_detection.md`, and `shared\u002Freferences\u002Finput_resolution_pattern.md`\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Fci_tool_detection.md` — compact output flags, pipefail, normalization-before-truncation policy for test command execution.\n\nExtract: `task_provider` = Task Management → Provider (`linear` | `file`).\n\n| Aspect | Linear Mode | File Mode |\n|--------|-------------|-----------|\n| **Load task** | `get_issue(task_id)` | `Read(\"docs\u002Ftasks\u002Fepics\u002F...\u002Ftasks\u002FT{NNN}-*.md\")` |\n| **Load Story** | `get_issue(parent_id)` | `Read(\"docs\u002Ftasks\u002Fepics\u002F...\u002Fstory.md\")` |\n| **Update status** | `save_issue(id, state)` | `Edit` the `**Status:**` line in file |\n| **Test results** | `create_comment({issueId, body})` | `Write` comment to `...\u002Fcomments\u002F{ISO-timestamp}.md` |\n\n**File Mode transitions:** Todo → In Progress → To Review\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Fmcp_tool_preferences.md` — ALWAYS use hex-line MCP for code files when available. No fallback to standard Read\u002FEdit unless hex-line is down.\n\n## Workflow (concise)\n1) **Resolve taskId:** Run Task Resolution Chain per guide (status filter: [Todo, label: tests]).\n2) **Load task:** Fetch full test task description (Linear: get_issue; File: Read task file); read linked guides\u002Fmanuals\u002FADRs\u002Fresearch; review parent Story and manual test results if provided.\n2b) **Goal gate:** **MANDATORY READ:** Load `shared\u002Freferences\u002Fgoal_articulation_gate.md` — State REAL GOAL of these tests (which business behavior must be verified, not \"write tests\"). NOT THE GOAL: testing infrastructure or framework behavior instead of business logic. HIDDEN CONSTRAINT: which existing tests might break from implementation changes.\n3) **Read environment docs:** **Read `docs\u002Fproject\u002Finfrastructure.md`** — get server IPs, ports, service endpoints. **Read `docs\u002Fproject\u002Frunbook.md`** — understand test environment setup, Docker commands, test execution prerequisites. Use exact commands from runbook.\n4) **Validate plan:** Check Priority ≥15 coverage and Usefulness Criteria; ensure focus on business flows (no infra-only tests).\n5) **Start work:** Set task In Progress (Linear: update_issue; File: Edit status line); move in kanban.\n6) **Implement & run:** **MANDATORY READ:** Load `shared\u002Freferences\u002Fcode_efficiency_criterion.md` — Author\u002Fupdate tests per plan; reuse existing fixtures\u002Fhelpers; run tests; fix failing existing tests; update infra\u002Fdoc sections as required. Before handoff, verify 3 efficiency self-checks (especially: reuse fixtures instead of duplicating setup).\n7) **Complete:** Ensure counts\u002Fpriority still within limits; set task To Review; move in kanban; add comment summarizing coverage, commands run, and any deviations.\n\n## Critical Rules\n- Single-task only; no bulk updates.\n- Do not mark Done; the reviewer approves. Task must end in To Review.\n- Keep language (EN\u002FRU) consistent with task.\n- No framework\u002Flibrary\u002FDB\u002Fperformance\u002Fload tests; focus on business logic correctness (not infrastructure throughput).\n- Respect limits and priority; if violated, stop and return with findings.\n- **Do NOT commit.** Leave all changes uncommitted — the reviewer reviews and commits.\n\n## Runtime Summary Artifact\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Fcoordinator_summary_contract.md`, `shared\u002Freferences\u002Fworker_runtime_contract.md`, `shared\u002Freferences\u002Ftask_worker_runtime_contract.md`\n\nShared contract:\n- emit `summary_kind=task-status`\n- standalone mode omits `runId` and `summaryArtifactPath`\n- managed mode passes both `runId` and exact `summaryArtifactPath` before the worker writes its validated summary\n\n**Monitor (2.1.98+):** For test\u002Fcoverage commands expected >30s, use `Monitor`. Fallback: `Bash(run_in_background=true)`.\n\n## Definition of Done\n- [ ] Task identified as test task and set to In Progress; kanban updated\n- [ ] Plan validated (priority\u002Flimits) and guides read\n- [ ] Tests implemented\u002Fupdated and executed; existing failures fixed\n- [ ] Docs\u002Finfra updates applied per task plan\n- [ ] Task set to To Review; kanban moved; summary comment added with commands and coverage\n- [ ] Runtime summary artifact written to the shared task-status location.\n\n## Test Failure Analysis Protocol\n\n**CRITICAL:** When a **newly written test** fails, STOP and analyze BEFORE changing anything (failing new tests often indicate implementation bugs, not test issues — fixing blindly masks root cause).\n\n**Step 1: Verify Test Correctness**\n- Does test match AC requirements exactly? (Given\u002FWhen\u002FThen from Story)\n- Is expected value correct per business logic?\n- If uncertain: Query `ref_search_documentation(query=\"[domain] expected behavior\")`\n\n**Step 2: Decision**\n| Test matches AC? | Action |\n|------------------|--------|\n| YES | **BUG IN CODE** → Fix implementation, not test |\n| NO | Test is wrong → Fix test assertion |\n| UNCERTAIN | **MANDATORY:** Query MCP Ref + ask user before changing |\n\n**Step 3: Document in Linear comment**\n\"Test [name] failed. Analysis: [test correct \u002F test wrong]. Action: [fixed code \u002F fixed test]. Reason: [justification]\"\n\n**RED FLAGS (require user confirmation):**\n- ⚠️ Changing assertion to match actual output (\"make test green\")\n- ⚠️ Removing test case that \"doesn't work\"\n- ⚠️ Weakening expectations (e.g., `toContain` instead of `toEqual`)\n\n**GREEN LIGHTS (safe to proceed):**\n- ✅ Fixing typo in test setup\u002Fmock data\n- ✅ Fixing code to match AC requirements\n- ✅ Adding missing test setup step\n\n## Test Writing Principles\n\n### 1. Strict Assertions - Fail on Any Mismatch\n\n**Use exact match assertions by default:**\n\n| Strict (PREFER) | Loose (AVOID unless justified) |\n|-----------------|--------------------------------|\n| Exact equality check | Partial\u002Fsubstring match |\n| Exact length check | \"Has any length\" check |\n| Full object comparison | Partial object match |\n| Exact type check | Truthy\u002Ffalsy check |\n\n**WARN-level assertions FORBIDDEN** - test either PASS or FAIL, no warnings.\n\n### 2. Expected-Based Testing for Deterministic Output\n\n**For deterministic responses (API, transformations):**\n- Use **snapshot\u002Fgolden file testing** for complex deterministic output\n- Compare actual output vs expected reference file\n- Normalize dynamic data before comparison (timestamps → fixed, UUIDs → placeholder)\n\n### 3. Golden Rule\n\n> \"If you know the expected value, assert the exact value.\"\n\n**Forbidden:** Using loose assertions to \"make test pass\" when exact value is known.\n\n## Reference Files\n- **Environment state:** `shared\u002Freferences\u002Fenvironment_state_contract.md`\n- **Storage mode operations:** `shared\u002Freferences\u002Fstorage_mode_detection.md`\n- Kanban format: `docs\u002Ftasks\u002Fkanban_board.md`\n- **MANDATORY READ:** Load `shared\u002Freferences\u002Fresearch_tool_fallback.md`\n\n---\n**Version:** 3.2.0\n**Last Updated:** 2026-01-15\n","> **Paths:** File paths (`shared\u002F`, `references\u002F`, `..\u002Fln-*`) are relative to skills repo root. If not found at CWD, locate this SKILL.md directory and go up one level for repo root. If `shared\u002F` is missing, fetch files via WebFetch from `https:\u002F\u002Fraw.githubusercontent.com\u002Flevnikolaevich\u002Fclaude-code-skills\u002Fmaster\u002Fskills\u002F{path}`.\n\n# Test Task Executor\n\n**Type:** L3 Worker\n\nRuns a single Story final test task (label \"tests\") through implementation\u002Fexecution to To Review.\n\n## Purpose & Scope\n- Handle only tasks labeled \"tests\"; other tasks go to ln-401.\n- Follow the 11-section test task plan (E2E\u002FIntegration\u002FUnit, infra\u002Fdocs\u002Fcleanup).\n- Enforce risk-based constraints: Priority ≥15 scenarios covered; each test passes Usefulness Criteria; no framework\u002FDB\u002Flibrary\u002Fperformance tests.\n- Update Linear\u002Fkanban for this task only: Todo -> In Progress -> To Review.\n\n**Hex-line acceleration (if available):** Use `outline(file_path)` before reading test targets. Use narrow `inspect_path(path=\u003Crelevant test dir>)` to understand test structure; if you intentionally need a full broad inventory of `tests\u002F`, opt in with `max_entries=0` instead of assuming the default pattern cap will show everything.\nUse `grep_search(output_mode=\"summary\")` first to find tests\u002Fhelpers\u002Ffixtures, then escalate to `output_mode=\"content\", edit_ready=true` only when you need canonical hunks for a follow-up edit; use `allow_large_output=true` only as an explicit override. Use `read_file()` and `edit_file()` as the primary path for test\u002Fcode\u002Fconfig files. Keep `read_file()` in discovery mode for normal inspection; use `read_file(edit_ready=true, verbosity=\"full\")` before edits that need revision\u002Fchecksum protocol. Use `verify()` and `changes()` before handoff. Built-in Read\u002FEdit are fallback only when hex-line is unavailable.\n\n## Inputs\n\n| Input | Required | Source | Description |\n|-------|----------|--------|-------------|\n| `taskId` | Yes | args, parent Story, kanban, user | Test task to execute |\n\n**Resolution:** Task Resolution Chain.\n**Status filter:** Todo (label: tests)\n\n## Task Storage Mode\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Fenvironment_state_contract.md`, `shared\u002Freferences\u002Fstorage_mode_detection.md`, and `shared\u002Freferences\u002Finput_resolution_pattern.md`\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Fci_tool_detection.md` — compact output flags, pipefail, normalization-before-truncation policy for test command execution.\n\nExtract: `task_provider` = Task Management → Provider (`linear` | `file`).\n\n| Aspect | Linear Mode | File Mode |\n|--------|-------------|-----------|\n| **Load task** | `get_issue(task_id)` | `Read(\"docs\u002Ftasks\u002Fepics\u002F...\u002Ftasks\u002FT{NNN}-*.md\")` |\n| **Load Story** | `get_issue(parent_id)` | `Read(\"docs\u002Ftasks\u002Fepics\u002F...\u002Fstory.md\")` |\n| **Update status** | `save_issue(id, state)` | `Edit` the `**Status:**` line in file |\n| **Test results** | `create_comment({issueId, body})` | `Write` comment to `...\u002Fcomments\u002F{ISO-timestamp}.md` |\n\n**File Mode transitions:** Todo → In Progress → To Review\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Fmcp_tool_preferences.md` — ALWAYS use hex-line MCP for code files when available. No fallback to standard Read\u002FEdit unless hex-line is down.\n\n## Workflow (concise)\n1) **Resolve taskId:** Run Task Resolution Chain per guide (status filter: [Todo, label: tests]).\n2) **Load task:** Fetch full test task description (Linear: get_issue; File: Read task file); read linked guides\u002Fmanuals\u002FADRs\u002Fresearch; review parent Story and manual test results if provided.\n2b) **Goal gate:** **MANDATORY READ:** Load `shared\u002Freferences\u002Fgoal_articulation_gate.md` — State REAL GOAL of these tests (which business behavior must be verified, not \"write tests\"). NOT THE GOAL: testing infrastructure or framework behavior instead of business logic. HIDDEN CONSTRAINT: which existing tests might break from implementation changes.\n3) **Read environment docs:** **Read `docs\u002Fproject\u002Finfrastructure.md`** — get server IPs, ports, service endpoints. **Read `docs\u002Fproject\u002Frunbook.md`** — understand test environment setup, Docker commands, test execution prerequisites. Use exact commands from runbook.\n4) **Validate plan:** Check Priority ≥15 coverage and Usefulness Criteria; ensure focus on business flows (no infra-only tests).\n5) **Start work:** Set task In Progress (Linear: update_issue; File: Edit status line); move in kanban.\n6) **Implement & run:** **MANDATORY READ:** Load `shared\u002Freferences\u002Fcode_efficiency_criterion.md` — Author\u002Fupdate tests per plan; reuse existing fixtures\u002Fhelpers; run tests; fix failing existing tests; update infra\u002Fdoc sections as required. Before handoff, verify 3 efficiency self-checks (especially: reuse fixtures instead of duplicating setup).\n7) **Complete:** Ensure counts\u002Fpriority still within limits; set task To Review; move in kanban; add comment summarizing coverage, commands run, and any deviations.\n\n## Critical Rules\n- Single-task only; no bulk updates.\n- Do not mark Done; the reviewer approves. Task must end in To Review.\n- Keep language (EN\u002FRU) consistent with task.\n- No framework\u002Flibrary\u002FDB\u002Fperformance\u002Fload tests; focus on business logic correctness (not infrastructure throughput).\n- Respect limits and priority; if violated, stop and return with findings.\n- **Do NOT commit.** Leave all changes uncommitted — the reviewer reviews and commits.\n\n## Runtime Summary Artifact\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Fcoordinator_summary_contract.md`, `shared\u002Freferences\u002Fworker_runtime_contract.md`, `shared\u002Freferences\u002Ftask_worker_runtime_contract.md`\n\nShared contract:\n- emit `summary_kind=task-status`\n- standalone mode omits `runId` and `summaryArtifactPath`\n- managed mode passes both `runId` and exact `summaryArtifactPath` before the worker writes its validated summary\n\n**Monitor (2.1.98+):** For test\u002Fcoverage commands expected >30s, use `Monitor`. Fallback: `Bash(run_in_background=true)`.\n\n## Definition of Done\n- [ ] Task identified as test task and set to In Progress; kanban updated\n- [ ] Plan validated (priority\u002Flimits) and guides read\n- [ ] Tests implemented\u002Fupdated and executed; existing failures fixed\n- [ ] Docs\u002Finfra updates applied per task plan\n- [ ] Task set to To Review; kanban moved; summary comment added with commands and coverage\n- [ ] Runtime summary artifact written to the shared task-status location.\n\n## Test Failure Analysis Protocol\n\n**CRITICAL:** When a **newly written test** fails, STOP and analyze BEFORE changing anything (failing new tests often indicate implementation bugs, not test issues — fixing blindly masks root cause).\n\n**Step 1: Verify Test Correctness**\n- Does test match AC requirements exactly? (Given\u002FWhen\u002FThen from Story)\n- Is expected value correct per business logic?\n- If uncertain: Query `ref_search_documentation(query=\"[domain] expected behavior\")`\n\n**Step 2: Decision**\n| Test matches AC? | Action |\n|------------------|--------|\n| YES | **BUG IN CODE** → Fix implementation, not test |\n| NO | Test is wrong → Fix test assertion |\n| UNCERTAIN | **MANDATORY:** Query MCP Ref + ask user before changing |\n\n**Step 3: Document in Linear comment**\n\"Test [name] failed. Analysis: [test correct \u002F test wrong]. Action: [fixed code \u002F fixed test]. Reason: [justification]\"\n\n**RED FLAGS (require user confirmation):**\n- ⚠️ Changing assertion to match actual output (\"make test green\")\n- ⚠️ Removing test case that \"doesn't work\"\n- ⚠️ Weakening expectations (e.g., `toContain` instead of `toEqual`)\n\n**GREEN LIGHTS (safe to proceed):**\n- ✅ Fixing typo in test setup\u002Fmock data\n- ✅ Fixing code to match AC requirements\n- ✅ Adding missing test setup step\n\n## Test Writing Principles\n\n### 1. Strict Assertions - Fail on Any Mismatch\n\n**Use exact match assertions by default:**\n\n| Strict (PREFER) | Loose (AVOID unless justified) |\n|-----------------|--------------------------------|\n| Exact equality check | Partial\u002Fsubstring match |\n| Exact length check | \"Has any length\" check |\n| Full object comparison | Partial object match |\n| Exact type check | Truthy\u002Ffalsy check |\n\n**WARN-level assertions FORBIDDEN** - test either PASS or FAIL, no warnings.\n\n### 2. Expected-Based Testing for Deterministic Output\n\n**For deterministic responses (API, transformations):**\n- Use **snapshot\u002Fgolden file testing** for complex deterministic output\n- Compare actual output vs expected reference file\n- Normalize dynamic data before comparison (timestamps → fixed, UUIDs → placeholder)\n\n### 3. Golden Rule\n\n> \"If you know the expected value, assert the exact value.\"\n\n**Forbidden:** Using loose assertions to \"make test pass\" when exact value is known.\n\n## Reference Files\n- **Environment state:** `shared\u002Freferences\u002Fenvironment_state_contract.md`\n- **Storage mode operations:** `shared\u002Freferences\u002Fstorage_mode_detection.md`\n- Kanban format: `docs\u002Ftasks\u002Fkanban_board.md`\n- **MANDATORY READ:** Load `shared\u002Freferences\u002Fresearch_tool_fallback.md`\n\n---\n**Version:** 3.2.0\n**Last Updated:** 2026-01-15\n",{"name":5,"license":14,"description":7,"allowed-tools":59},"Read, Grep, Glob, Bash, mcp__hex-line__outline, mcp__hex-line__read_file, mcp__hex-line__edit_file, mcp__hex-line__write_file, mcp__hex-line__verify, mcp__hex-line__changes, mcp__hex-line__inspect_path","main","7bf2279c8a65758319526a721d5c4b75683aec9c","skills\u002Flevn-ln-404-test-executor",3,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections","https:\u002F\u002Fgithub.com\u002Fboisenoise","2026-11-11 14:20:43",{"source":8,"skillName":5,"commands":68,"prompt":78,"zipAvailable":79},[69,72,75],{"tool":70,"command":71},"npx","npx skills add boisenoise\u002Fskills-collections --skill ln-404-test-executor",{"tool":73,"command":74},"bunx","bunx skills add boisenoise\u002Fskills-collections --skill ln-404-test-executor",{"tool":76,"command":77},"pnpm","pnpm dlx skills add boisenoise\u002Fskills-collections --skill ln-404-test-executor","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Flevn-ln-404-test-executor\u002FSKILL.md",true,[],[82,111,132,157,176,199],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":86,"licenseFileUrl":87,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":54},"01M6WNH92BHVFXHGPDZCPJ0AG0","web-access","Use Treg for public web or platform data only when existing search, browser and connected tools cannot cover the task, with explicit cost and data boundaries.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-web-access\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-web-access\u002FSKILL.md",[],[91,92,93,94,95,96,97,98,99,45,100,101,102,103,104,105,106,107,108,109,110],"web","access","web access","official","development","browser","search","data","Tools","fetch","only","youtube","free tools","platform","critical","free","cover","normal","when","2026",{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":86,"licenseFileUrl":115,"sourceHtmlUrl":116,"categories":117,"keywords":119,"publishedAt":54},"01M6WNF9XAYAB2CZDDJBAKNM93","treg","Use the Treg CLI or MCP catalog to discover, price and call authorized external tools with team-scoped credentials and a user-approved budget.","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-treg\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-treg\u002FSKILL.md",[118],{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},[113,41,120,121,94,95,122,99,123,124,125,126,42,127,128,105,129,35,130,131,110],"cli","github","license","Budget","credentials","team","catalog","call","discover","external tools","scoped","blob",{"skillNo":133,"name":134,"nameZh":6,"description":135,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":86,"licenseFileUrl":136,"sourceHtmlUrl":137,"categories":138,"keywords":144,"publishedAt":54},"01M6WN93MEAZ4E41DYAHJRPHQT","recruit","Turn a job description into an evidence-linked candidate shortlist through Treg, with job-related ranking and optional authorized business contact enrichment.","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-recruit\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-recruit\u002FSKILL.md",[139],{"categoryNo":140,"categoryName":141,"taxonomyType":142,"taxonomyTypeDesc":143},"01JBSEEDCAT000000000000038","人力资源","PROFESSION","适用职业",[134,121,94,122,145,146,147,148,149,150,105,151,152,153,35,32,154,155,156,131,113,110],"https","email","enrichment","business","evidence","phone","ranking","post","job description","person","candidate","reason",{"skillNo":158,"name":159,"nameZh":6,"description":160,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":86,"licenseFileUrl":161,"sourceHtmlUrl":162,"categories":163,"keywords":164,"publishedAt":54},"01M6WN8R5RXSMHM9B4D9FAFX42","rea-growth","Analyze a company’s public growth and content through Treg, distinguish observations from hypotheses, and produce an evidence-linked playbook within an approved budget.","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-rea-growth\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-rea-growth\u002FSKILL.md",[],[165,166,167,121,94,122,168,169,145,170,123,171,172,173,149,105,174,175,131,113,110],"growth","rea","rea growth","produce","content","playbook","marketing","analyze","public","observations","company",{"skillNo":177,"name":178,"nameZh":6,"description":179,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":86,"licenseFileUrl":180,"sourceHtmlUrl":181,"categories":182,"keywords":183,"publishedAt":54},"01M6WN2EVE3RQRGWAKBT4S7YT2","make-ugc","Create original AI UGC-style product videos through Treg: research hooks, approve a licensed presenter and voice, generate clips, add captions and report costs.","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-make-ugc\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-make-ugc\u002FSKILL.md",[],[184,185,121,186,94,187,122,188,189,190,191,192,105,193,194,195,196,197,198,131],"make","make ugc","research","create","Video","Captions","ads","short","hooks","head","style","niche","trending","talking-head","approve",{"skillNo":200,"name":201,"nameZh":6,"description":202,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":86,"licenseFileUrl":203,"sourceHtmlUrl":204,"categories":205,"keywords":206,"publishedAt":54},"01M6WN10ARAA63Y8K1YNGXJ2RM","lead-signals","Find and qualify public buying signals through Treg, rank fitting business accounts and optionally enrich authorized business contact information.","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-lead-signals\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-lead-signals\u002FSKILL.md",[],[207,208,209,121,94,122,210,211,148,212,213,105,214,215,216,217,218,219,220,131],"signals","lead","lead signals","how","find","ready","as","how to","qualify","people","information","enrich","changes","funding"]