[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77MECC74XFE400C386CTR7R":3,"skill-same:01M77MECC74XFE400C386CTR7R":60},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":38,"commitSha":39,"skillDirectory":40,"forksCount":14,"repositoryHtmlUrl":41,"repositoryHomepageUrl":6,"ownerHtmlUrl":42,"ownerBlogUrl":43,"ownerDescription":44,"updatedAt":45,"install":46,"resources":59},"01M77MECC74XFE400C386CTR7R","testing",null,"Skill validation framework PLUS daily test-suite health and regression\nintelligence. Validates skill conformance (frontmatter, manifest coverage,\nresolver coverage). Runs the project test suite in tiered phases (unit \u002F\nevals \u002F integration \u002F system health), classifies failures, and produces\na regression-aware report.","singhvedant\u002Ftbrain","singhvedant","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F71930695?v=4","01M77M5AXVZ7M5XWPANT3J9NS5","Vedant Singh","01M77M5AZ21DXDMR8ZPN3CPR07",0,"MIT","https:\u002F\u002Fgithub.com\u002Fsinghvedant\u002Ftbrain\u002Fblob\u002Fmain\u002Fskills\u002Ftesting\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: testing\nversion: 1.1.0\ndescription: |\n  Skill validation framework PLUS daily test-suite health and regression\n  intelligence. Validates skill conformance (frontmatter, manifest coverage,\n  resolver coverage). Runs the project test suite in tiered phases (unit \u002F\n  evals \u002F integration \u002F system health), classifies failures, and produces\n  a regression-aware report.\ntriggers:\n  - \"validate skills\"\n  - \"test skills\"\n  - \"skill health check\"\n  - \"run conformance tests\"\n  - \"run the tests\"\n  - \"how are the tests\"\n  - \"what's broken\"\n  - \"daily test run\"\ntools:\n  - search\n  - list_pages\nmutating: false\n---\n\n# Testing Skill — Validation + Daily Health & Regression Intelligence\n\n> **Convention:** see [conventions\u002Fquality.md](..\u002Fconventions\u002Fquality.md) for\n> the test-before-bulk pattern; this skill enforces it across the project's\n> own test suite.\n\n## Two modes\n\nThis skill has two related but distinct modes:\n\n1. **Skill conformance validation** — gbrain's own conformance bar\n   (the original 1.0 scope). Validates every skill has SKILL.md with\n   frontmatter, every reference exists, manifest + resolver coverage\n   round-trips.\n\n2. **Project test-suite health (v0.25.1 extension)** — runs the\n   project's tiered test suite and produces a regression-classified\n   report. Used by daily cron, container-restart bootstrap, and\n   \"how are the tests\" prompts.\n\nPick the mode by trigger.\n\n## Mode 1: Skill conformance validation\n\n### Contract\n\nThis mode guarantees:\n\n- Every skill directory has a `SKILL.md` file\n- Every `SKILL.md` has valid YAML frontmatter (`name`, `description`)\n- Every `SKILL.md` has required sections per\n  `test\u002Fskills-conformance.test.ts`\n- `skills\u002Fmanifest.json` lists every skill directory\n- `skills\u002FRESOLVER.md` references every skill in the manifest\n- `openclaw.plugin.json` `skills[]` round-trips with both\n- No MECE violations (duplicate triggers across skills)\n\n### Phases\n\n1. **Walk skills directory.** List all subdirs containing `SKILL.md`.\n2. **Validate frontmatter.** Parse YAML, check required fields.\n3. **Validate sections.** Check for the required headings.\n4. **Check manifest.** Every skill dir must be in `manifest.json`.\n5. **Check resolver.** Every manifest skill must have a RESOLVER row.\n6. **Check round-trip.** RESOLVER trigger ↔ frontmatter triggers.\n7. **Report results.**\n\n### Automation\n\n```bash\nbun test test\u002Fskills-conformance.test.ts test\u002Fresolver.test.ts\n```\n\nThe CI-gated check is the package.json `test` script.\n\n### Output format\n\n```\nSkill Validation Report\n========================\nSkills found:        N\nConformance:         N\u002FN pass\nManifest coverage:   N\u002FN\nResolver coverage:   N\u002FN\nRound-trip:          N\u002FN\nMECE violations:     N\n\nIssues:\n- \u003Cskill>: \u003Cissue>\n```\n\n## Mode 2: Project test-suite health (v0.25.1)\n\n### When to use\n\n- Daily test cron fires\n- User asks \"run the tests\" \u002F \"how are the tests\" \u002F \"what's broken\"\n- After significant code changes (often via cross-modal-review)\n- After container restart (bootstrap)\n- When something seems off and you want to verify system health\n\n### Test tiers\n\n| Tier | What it runs | Wall time | Gates |\n|------|--------------|-----------|-------|\n| **Unit** | `bun test` (deterministic, zero external calls) | \u003C2s | Every commit |\n| **Evals** | LLM-judge or quality evals | ~60s | Daily |\n| **Integration** | E2E tests against real Postgres | ~5m | Pre-ship + nightly |\n| **System health** | Disk \u002F memory \u002F CPU \u002F service liveness | \u003C10s | Daily |\n\n### Daily run protocol\n\nWhen the cron fires (or the user asks), do ALL of this:\n\n#### 1. Run unit tests\n\n```bash\nbun test 2>&1\n```\n\nParse: total passed, total failed, total skipped, file-level results.\n\n#### 2. Run evals (if the project has an evals config)\n\n```bash\n# Adapt to the project's eval config\nbun test --filter eval 2>&1\n```\n\nParse: same format. Note any flakes (tests that fail due to API\ntimeouts, not code bugs).\n\n#### 3. Run system health checks\n\n- Disk \u002F memory \u002F CPU\n- gbrain: `gbrain doctor --fast --json`\n- Database connection (if applicable)\n- Critical files exist (CLAUDE.md, AGENTS.md, etc.)\n\n#### 4. Git diff analysis (CRITICAL — regression intelligence)\n\n```bash\n# What changed since last test run?\ngit log --oneline --since=\"24 hours ago\"\n```\n\nFor each failing test:\n\n1. Check if the test itself was modified recently (test change, not\n   regression).\n2. Check if the code it tests was modified recently (possible\n   regression).\n3. Check if it's a known flake (API timeout, service down).\n4. Check if a dependency was updated (gbrain, bun, etc.).\n\n#### 5. Classify each failure\n\n| Classification | Marker | Action |\n|---------------|--------|--------|\n| **REGRESSION** — code changed, test broke | 🔴 | Flag with the commit that broke it |\n| **STALE** — test expects old behavior; code is correct | 🟡 | Fix the test, not the code |\n| **FLAKE** — API timeout, service down, LLM variance | ⚠️ | Note, don't alarm; retry once |\n| **NEW** — test was just added and isn't passing yet | 🟢 | Check if intentional |\n| **INFRA** — container restart wiped state | 🛠 | Run bootstrap, retest |\n\n#### 6. Report format\n\n```\n🧪 Daily Tests — YYYY-MM-DD\n\nUnit:   X\u002FY passed (Z skipped)\nEvals:  X\u002FY passed\nSystem: [health summary]\n\nREGRESSIONS:\n  🔴 \u003Ctest-name>: broke by commit \u003Csha> \"\u003Ccommit message>\"\n\nSTALE TESTS:\n  🟡 \u003Ctest-name>: expects X but code now does Y (commit \u003Csha>)\n\nFLAKES:\n  ⚠️ \u003Ctest-name>: timeout (retry passed)\n\n✅ ALL CLEAR  (when applicable)\n```\n\n#### 7. Auto-fix protocol\n\n**DO auto-fix:**\n\n- Test expects an old file path after a rename → update the test\n- Test expects an old version string → update\n- Test expects a file that was intentionally deleted → remove the test\n- Import path broke because file moved → fix the import\n\n**DO NOT auto-fix:**\n\n- Test expects behavior A but code now does B → ASK first. Maybe the\n  test is right and the code has a bug.\n- Security test failing → ALWAYS escalate, never auto-fix.\n- Test was skipped with a TODO → don't un-skip without understanding why.\n\nWhen uncertain: check the commit message that changed the code, check\nif there's a related PR or conversation, ask the user if still unclear.\n\n### State (regression history)\n\nTrack results in `~\u002F.gbrain\u002Ftest-state.json` for trend tracking:\n\n```json\n{\n  \"lastRun\": \"2026-04-16T13:37:00Z\",\n  \"unit\": { \"passed\": 1262, \"failed\": 31, \"skipped\": 8 },\n  \"evals\": { \"passed\": 17, \"failed\": 0 },\n  \"system\": { \"doctor\": \"ok\", \"gbrain\": \"0.25.1\" },\n  \"failureHistory\": [\n    { \"test\": \"\u003Cname>\", \"since\": \"2026-04-14\", \"classification\": \"stale\" }\n  ]\n}\n```\n\nThis enables:\n\n- Trend tracking (are we getting better or worse?)\n- Flake detection (same test fails intermittently)\n- Regression velocity (how fast do we break things after changes?)\n\n## Anti-Patterns\n\n- ❌ Skipping conformance validation after adding a new skill\n- ❌ Adding skills to `manifest.json` without adding to RESOLVER.md\n- ❌ Treating every red test as a regression. Classify first; many are\n  stale or flaky.\n- ❌ Auto-un-skipping a test without understanding why it was skipped\n- ❌ Auto-\"fixing\" a security test failure\n- ❌ Reporting \"all clear\" without actually running system health checks\n\n\n## Contract\n\nThis skill guarantees:\n\n- Routing matches the canonical triggers in the frontmatter.\n- Output written under the directories listed in `writes_to:` (when applicable).\n- Conventions referenced (`quality.md`, `brain-first.md`, `_brain-filing-rules.md`) are followed.\n- Privacy contract preserved: no real names, no fork-specific filesystem path literals, no upstream-fork references.\n\nThe full behavior contract is documented in the body sections above; this section exists for the conformance test.\n\n## Output Format\n\nThe skill's output shape is documented inline in the body sections above (see \"Output\", \"Brain page format\", or equivalent). The literal section header here exists for the conformance test (`test\u002Fskills-conformance.test.ts`).\n","# Testing Skill — Validation + Daily Health & Regression Intelligence\n\n> **Convention:** see [conventions\u002Fquality.md](..\u002Fconventions\u002Fquality.md) for\n> the test-before-bulk pattern; this skill enforces it across the project's\n> own test suite.\n\n## Two modes\n\nThis skill has two related but distinct modes:\n\n1. **Skill conformance validation** — gbrain's own conformance bar\n   (the original 1.0 scope). Validates every skill has SKILL.md with\n   frontmatter, every reference exists, manifest + resolver coverage\n   round-trips.\n\n2. **Project test-suite health (v0.25.1 extension)** — runs the\n   project's tiered test suite and produces a regression-classified\n   report. Used by daily cron, container-restart bootstrap, and\n   \"how are the tests\" prompts.\n\nPick the mode by trigger.\n\n## Mode 1: Skill conformance validation\n\n### Contract\n\nThis mode guarantees:\n\n- Every skill directory has a `SKILL.md` file\n- Every `SKILL.md` has valid YAML frontmatter (`name`, `description`)\n- Every `SKILL.md` has required sections per\n  `test\u002Fskills-conformance.test.ts`\n- `skills\u002Fmanifest.json` lists every skill directory\n- `skills\u002FRESOLVER.md` references every skill in the manifest\n- `openclaw.plugin.json` `skills[]` round-trips with both\n- No MECE violations (duplicate triggers across skills)\n\n### Phases\n\n1. **Walk skills directory.** List all subdirs containing `SKILL.md`.\n2. **Validate frontmatter.** Parse YAML, check required fields.\n3. **Validate sections.** Check for the required headings.\n4. **Check manifest.** Every skill dir must be in `manifest.json`.\n5. **Check resolver.** Every manifest skill must have a RESOLVER row.\n6. **Check round-trip.** RESOLVER trigger ↔ frontmatter triggers.\n7. **Report results.**\n\n### Automation\n\n```bash\nbun test test\u002Fskills-conformance.test.ts test\u002Fresolver.test.ts\n```\n\nThe CI-gated check is the package.json `test` script.\n\n### Output format\n\n```\nSkill Validation Report\n========================\nSkills found:        N\nConformance:         N\u002FN pass\nManifest coverage:   N\u002FN\nResolver coverage:   N\u002FN\nRound-trip:          N\u002FN\nMECE violations:     N\n\nIssues:\n- \u003Cskill>: \u003Cissue>\n```\n\n## Mode 2: Project test-suite health (v0.25.1)\n\n### When to use\n\n- Daily test cron fires\n- User asks \"run the tests\" \u002F \"how are the tests\" \u002F \"what's broken\"\n- After significant code changes (often via cross-modal-review)\n- After container restart (bootstrap)\n- When something seems off and you want to verify system health\n\n### Test tiers\n\n| Tier | What it runs | Wall time | Gates |\n|------|--------------|-----------|-------|\n| **Unit** | `bun test` (deterministic, zero external calls) | \u003C2s | Every commit |\n| **Evals** | LLM-judge or quality evals | ~60s | Daily |\n| **Integration** | E2E tests against real Postgres | ~5m | Pre-ship + nightly |\n| **System health** | Disk \u002F memory \u002F CPU \u002F service liveness | \u003C10s | Daily |\n\n### Daily run protocol\n\nWhen the cron fires (or the user asks), do ALL of this:\n\n#### 1. Run unit tests\n\n```bash\nbun test 2>&1\n```\n\nParse: total passed, total failed, total skipped, file-level results.\n\n#### 2. Run evals (if the project has an evals config)\n\n```bash\n# Adapt to the project's eval config\nbun test --filter eval 2>&1\n```\n\nParse: same format. Note any flakes (tests that fail due to API\ntimeouts, not code bugs).\n\n#### 3. Run system health checks\n\n- Disk \u002F memory \u002F CPU\n- gbrain: `gbrain doctor --fast --json`\n- Database connection (if applicable)\n- Critical files exist (CLAUDE.md, AGENTS.md, etc.)\n\n#### 4. Git diff analysis (CRITICAL — regression intelligence)\n\n```bash\n# What changed since last test run?\ngit log --oneline --since=\"24 hours ago\"\n```\n\nFor each failing test:\n\n1. Check if the test itself was modified recently (test change, not\n   regression).\n2. Check if the code it tests was modified recently (possible\n   regression).\n3. Check if it's a known flake (API timeout, service down).\n4. Check if a dependency was updated (gbrain, bun, etc.).\n\n#### 5. Classify each failure\n\n| Classification | Marker | Action |\n|---------------|--------|--------|\n| **REGRESSION** — code changed, test broke | 🔴 | Flag with the commit that broke it |\n| **STALE** — test expects old behavior; code is correct | 🟡 | Fix the test, not the code |\n| **FLAKE** — API timeout, service down, LLM variance | ⚠️ | Note, don't alarm; retry once |\n| **NEW** — test was just added and isn't passing yet | 🟢 | Check if intentional |\n| **INFRA** — container restart wiped state | 🛠 | Run bootstrap, retest |\n\n#### 6. Report format\n\n```\n🧪 Daily Tests — YYYY-MM-DD\n\nUnit:   X\u002FY passed (Z skipped)\nEvals:  X\u002FY passed\nSystem: [health summary]\n\nREGRESSIONS:\n  🔴 \u003Ctest-name>: broke by commit \u003Csha> \"\u003Ccommit message>\"\n\nSTALE TESTS:\n  🟡 \u003Ctest-name>: expects X but code now does Y (commit \u003Csha>)\n\nFLAKES:\n  ⚠️ \u003Ctest-name>: timeout (retry passed)\n\n✅ ALL CLEAR  (when applicable)\n```\n\n#### 7. Auto-fix protocol\n\n**DO auto-fix:**\n\n- Test expects an old file path after a rename → update the test\n- Test expects an old version string → update\n- Test expects a file that was intentionally deleted → remove the test\n- Import path broke because file moved → fix the import\n\n**DO NOT auto-fix:**\n\n- Test expects behavior A but code now does B → ASK first. Maybe the\n  test is right and the code has a bug.\n- Security test failing → ALWAYS escalate, never auto-fix.\n- Test was skipped with a TODO → don't un-skip without understanding why.\n\nWhen uncertain: check the commit message that changed the code, check\nif there's a related PR or conversation, ask the user if still unclear.\n\n### State (regression history)\n\nTrack results in `~\u002F.gbrain\u002Ftest-state.json` for trend tracking:\n\n```json\n{\n  \"lastRun\": \"2026-04-16T13:37:00Z\",\n  \"unit\": { \"passed\": 1262, \"failed\": 31, \"skipped\": 8 },\n  \"evals\": { \"passed\": 17, \"failed\": 0 },\n  \"system\": { \"doctor\": \"ok\", \"gbrain\": \"0.25.1\" },\n  \"failureHistory\": [\n    { \"test\": \"\u003Cname>\", \"since\": \"2026-04-14\", \"classification\": \"stale\" }\n  ]\n}\n```\n\nThis enables:\n\n- Trend tracking (are we getting better or worse?)\n- Flake detection (same test fails intermittently)\n- Regression velocity (how fast do we break things after changes?)\n\n## Anti-Patterns\n\n- ❌ Skipping conformance validation after adding a new skill\n- ❌ Adding skills to `manifest.json` without adding to RESOLVER.md\n- ❌ Treating every red test as a regression. Classify first; many are\n  stale or flaky.\n- ❌ Auto-un-skipping a test without understanding why it was skipped\n- ❌ Auto-\"fixing\" a security test failure\n- ❌ Reporting \"all clear\" without actually running system health checks\n\n\n## Contract\n\nThis skill guarantees:\n\n- Routing matches the canonical triggers in the frontmatter.\n- Output written under the directories listed in `writes_to:` (when applicable).\n- Conventions referenced (`quality.md`, `brain-first.md`, `_brain-filing-rules.md`) are followed.\n- Privacy contract preserved: no real names, no fork-specific filesystem path literals, no upstream-fork references.\n\nThe full behavior contract is documented in the body sections above; this section exists for the conformance test.\n\n## Output Format\n\nThe skill's output shape is documented inline in the body sections above (see \"Output\", \"Brain page format\", or equivalent). The literal section header here exists for the conformance test (`test\u002Fskills-conformance.test.ts`).\n",{"name":5,"tools":24,"version":27,"mutating":20,"triggers":28,"description":37},[25,26],"search","list_pages","1.1.0",[29,30,31,32,33,34,35,36],"validate skills","test skills","skill health check","run conformance tests","run the tests","how are the tests","what's broken","daily test run","Skill validation framework PLUS daily test-suite health and regression\nintelligence. Validates skill conformance (frontmatter, manifest coverage,\nresolver coverage). Runs the project test suite in tiered phases (unit \u002F\nevals \u002F integration \u002F system health), classifies failures, and produces\na regression-aware report.\n","main","6fd71a8e8b329f5375cf01a74a9da2af1909f4e0","skills\u002Ftesting","https:\u002F\u002Fgithub.com\u002Fsinghvedant\u002Ftbrain","https:\u002F\u002Fgithub.com\u002Fsinghvedant","singhvedant1701.github.io","Web\u002FApp developer\r\nCloud Computing\r\nAI and ML","2026-07-04 14:54:38",{"source":8,"skillName":5,"commands":47,"prompt":57,"zipAvailable":58},[48,51,54],{"tool":49,"command":50},"npx","npx skills add singhvedant\u002Ftbrain --skill testing",{"tool":52,"command":53},"bunx","bunx skills add singhvedant\u002Ftbrain --skill testing",{"tool":55,"command":56},"pnpm","pnpm dlx skills add singhvedant\u002Ftbrain --skill testing","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fsinghvedant\u002Ftbrain\u002Fblob\u002Fmain\u002Fskills\u002Ftesting\u002FSKILL.md",true,[],[61,67,73,80,87,94],{"skillNo":62,"name":63,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M77MH99TG5CXS6ZC5V519J27","query-helper","https:\u002F\u002Fgithub.com\u002Fsinghvedant\u002Ftbrain\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fskill-catalog\u002Fskills\u002Fquery-helper\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M77MH8A3A5PTQM0PQH6SCBA8","broken","https:\u002F\u002Fgithub.com\u002Fsinghvedant\u002Ftbrain\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fskill-catalog\u002Fskills\u002Fbroken\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M77MH6HHY2G5V0BXP8V316F8","brain-ops","Read, enrich, and write brain pages with source attribution.","https:\u002F\u002Fgithub.com\u002Fsinghvedant\u002Ftbrain\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fskill-catalog\u002Fskills\u002Fbrain-ops\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M77MH54BXVPFXK48DKBKFNRF","signal-detector","Always-on ambient signal capture for the OpenClaw reference fixture.","https:\u002F\u002Fgithub.com\u002Fsinghvedant\u002Ftbrain\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fopenclaw-reference-minimal\u002Fskills\u002Fsignal-detector\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M77MH3MPW52RQDQGTDR38MZT","query","Look up brain pages in the OpenClaw reference fixture.","https:\u002F\u002Fgithub.com\u002Fsinghvedant\u002Ftbrain\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fopenclaw-reference-minimal\u002Fskills\u002Fquery\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M77MH17X2DRV1DD6HV8Z89BA","context-now","ALWAYS-ON time-sensitivity discipline for the OpenClaw reference fixture.","https:\u002F\u002Fgithub.com\u002Fsinghvedant\u002Ftbrain\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fopenclaw-reference-minimal\u002Fskills\u002Fcontext-now\u002FSKILL.md",[],[]]