[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6AEHR89MBJABYGS1M2B3ZP6":3,"skill-same:01M6AEHR89MBJABYGS1M2B3ZP6":73},{"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":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":52,"repositoryHtmlUrl":53,"repositoryHomepageUrl":54,"ownerHtmlUrl":55,"ownerBlogUrl":56,"ownerDescription":57,"updatedAt":58,"install":59,"resources":72},"01M6AEHR89MBJABYGS1M2B3ZP6","eval-genius",null,"Decide whether an AI\u002FLLM\u002Fagent\u002Fretrieval system needs an eval, where it fits in the dev process, which one to run, and how to read the result; then design, gate, judge, and defend it. Not ordinary unit tests.","davila7\u002Fclaude-code-templates","davila7","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6216945?v=4","01M6ADEWWFPS191NFM0Y1EX1JH","Daniel Avila","01M6ADJHGM78PHQRD3XZTFDVKK",33286,"MIT","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdevelopment\u002Feval-genius\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],"eval genius","eval","process","result","which","judge","it","retrieval","unit","how to","tests","gate","design","read","decide","system","how","dev","run","unit tests","2026-11-10 10:12:30",false,"---\nname: eval-genius\ndescription: >-\n  Decide whether an AI\u002FLLM\u002Fagent\u002Fretrieval system needs an eval, where it fits in the\n  dev process, which one to run, and how to read the result; then design, gate, judge,\n  and defend it. Not ordinary unit tests.\n---\n\n# Eval Genius\n\nAn eval is a claim you are willing to defend under hostile audit. You measure to earn\nthe right to say \"this is better\" and have it hold when someone sharp pushes back.\nBehave like a measurement engineer: state the promise, fix the bar before looking, hold\neverything else constant, distrust the instrument first, report the number that hurts.\nAssume the user may be starting from zero; plain language first, jargon when it earns it.\n\n---\n\n## Step 0: Does this need an eval, and where does it go?\n\nThree questions decide it (`references\u002F00-start-here.md`): does the output vary (model,\nprompt, retriever)? will it change again, and would a quiet regression cost something?\nis a decision or a public claim coming? No to all: a hand spot check, stop. Yes to any:\nan eval, sized to the stage the project is in.\n\n| Stage the user is at | Instrument | Smallest useful version |\n|---|---|---|\n| Exploring prompts and models | Spot check | 10 inputs, eyeball |\n| First working version | Smoke eval | 20 to 50 real inputs, code-checked; **this run is the baseline** |\n| Changing one thing | Paired eval vs baseline | Same items both arms, per-item diff, bar written first |\n| Merging or shipping | CI gate | Held-out items, three-way outcome, a known-bad item that must fail |\n| Comparing or claiming publicly | Benchmark | Versioned dataset and harness, intervals, report |\n| In production | Monitor | Same scorer on sampled live traffic |\n\nBuild the first eval at \"first working version\", never before, rarely after. For a\nfirst-timer, run the one-afternoon recipe in `00-start-here.md` and touch nothing else.\n\n## Route the request\n\nIdentify the job, then load only that reference. Every job still passes through Step 1.\n\n| User needs to... | Load |\n|---|---|\n| Know if they need an eval, where it fits, which one, or how to start | `references\u002F00-start-here.md` |\n| Decide what to measure at all, or the ask is \"make it better\" | `references\u002F01-foundation.md` |\n| Pick a grader or metric for a task | `references\u002F02-grading-and-metrics.md` |\n| Use, prompt, or trust an LLM judge | `references\u002F03-judge-calibration.md` |\n| Choose between an existing benchmark and a custom one | `references\u002F04-search-vs-build.md` |\n| Assemble items, labels, negatives, splits; contamination, overfitting | `references\u002F05-dataset-construction.md` |\n| Write or fix the runner, scorer, or reporter | `references\u002F06-harness-design.md` |\n| Put an eval in CI or a release gate | `references\u002F07-gates-and-ci.md` |\n| Say whether a delta is real | `references\u002F08-statistics.md` |\n| Write results up, or retire a benchmark | `references\u002F09-reporting.md` |\n| Evaluate an agent, tool use, or multi-turn task | `references\u002F10-agentic-evals.md` |\n| Read a result file with no prior experience | `references\u002F11-reading-results.md` |\n\nTemplates in `templates\u002F` get copied into the project, never edited in place. Scripts in\n`scripts\u002F` are stdlib-only CLIs with `--help`, exiting nonzero with a readable message:\n`check_gate.py` (per-item diff of treatment vs baseline; exits 0 PASS, 1 FAIL,\n2 CANNOT-MEASURE; refuses a comparison across mismatched fixture or judge fingerprints),\n`paired_bootstrap.py` (paired bootstrap interval on the delta, cluster-aware),\n`judge_agreement.py` (Cohen's kappa and PASS precision\u002Frecall of a judge vs human labels),\n`hash_fixture.py` (the canonical fixture content hash the manifest's `fixture_hash` wants,\nso two runs hash the same fixture to the same string). Match effort to stakes: a spot check needs Step 0 and little else; a\nrelease gate needs the whole chain. Load references on demand, not all at once.\n\n---\n\n## Step 1: Foundation (five minutes, never skipped)\n\nCopy `templates\u002Fpreregistration.md` next to the fixture and fill it before touching\ndata or code. A first-timer fills promise, lever, baseline, and bar; the rest follows.\n\n1. **Promise.** One plain sentence: what does the system promise, what is \"better\"?\n2. **Variables.** Levers (what changes), outcomes (what is watched), controls (what is\n   frozen). One lever per comparison; an unclassifiable variable means stop.\n3. **Placement.** A decision point, a risky seam, or a public claim; elsewhere, a spot\n   check or nothing.\n4. **Weight.** Spot check, eval, benchmark, or monitor (Step 0 table).\n5. **Bar.** The threshold in numbers, the falsifier (what proves the change useless),\n   and the outlier rule. Written before any run.\n\nDone when all five fields are filled and a baseline is named.\n\n## Step 2: Choose the grader (deterministic first)\n\nPush every check that *can* be code-graded down to code: exact match, regex, schema,\ntest suite, threshold. Free text gets decomposed (required facts present, forbidden\ncontent absent, format) before any judge sees it. Reserve a model or human judge for\nthe edge no assertion captures. 80% deterministic \u002F 20% judged is trusted; 100% judged\nis an opinion with error bars. Report layers separately, never one blended number. A\njudge is an instrument: calibrate against human labels, blind it, randomize order, pin\nmodel and prompt hash (`references\u002F03-judge-calibration.md`).\n\n## Step 3: Build or adopt\n\nSearch before building; an established benchmark buys ground truth nobody in the room\ncooked. Build custom the moment the public one rewards a proxy the system does not\ntarget, reusing public plumbing. Score candidates on `templates\u002Fbenchmark-assessment-scorecard.md`:\nwhat it rewards, contamination, label-error ceiling, whether it exercises *this*\nmechanism, whether it is maintained.\n\n## Step 4: Run under hard rules (a run that breaks one is not a result)\n\n- **Freeze the fixture.** Same items, corpus, snapshot, seeds; only the lever varies.\n  Refuse comparisons across mismatched fingerprints.\n- **Three-way outcome.** PASS, FAIL, or CANNOT-MEASURE. A crash, missing baseline, or\n  fingerprint mismatch is CANNOT-MEASURE, never FAIL and never PASS (`check_gate.py`).\n- **Prove the treatment arm is live** before the run.\n- **Cover the negative space**: items where the right answer is to refuse or return nothing.\n- **Repeat and show spread.** Noise wider than the effect means no result yet.\n- **Verify the verifier.** A known-bad case must go red before green is trusted.\n\n## Step 5: Read the result (in this order)\n\nFull walk in `references\u002F11-reading-results.md`; each check gates the next.\n\n1. **Did it run?** Exit code before score; negative control failed.\n2. **Against the written bar**, not against hope. Above: candidate win. Below the\n   falsifier: rejected. Between: not established.\n3. **Bigger than noise?** Paired interval on the delta (`paired_bootstrap.py`);\n   interval includes zero means \"not established\", never \"no effect\".\n4. **Items, not averages.** Read regressions first; reproduce one flip by hand.\n5. **Surprised?** A 0%, a 99%, a thirty-point jump is a harness bug until proven\n   otherwise. Never tune the system against a suspect gauge; fix the gauge or stop.\n6. **Layers and cost separately.** A win that doubled cost is a trade.\n\n## Step 6: Report honestly\nNumbers are claims with tiers, measured \u002F estimated \u002F aspirational, never summed across\ntiers. Three sentences minimum: the bar and whether it was met; the delta with interval,\nn, and flip counts; the caveat that most weakens the claim. Say when a benchmark is\nself-run. Retire what fails its bar, in writing. Template: `templates\u002Feval-report.md`.\n\n---\n\n## Anti-patterns (named so they can be refused)\n\n- **Metric-first.** A dataset and scale chosen before the promise is written.\n- **Eval too early or too late.** Measuring a prototype still in flux, or a shipped\n  system with twenty unattributed changes behind it.\n- **Blended score.** One number hiding which layer moved.\n- **Post-hoc bar.** Threshold decided after the result is known.\n- **Fixture drift.** Comparing across corpora, caches, or snapshots.\n- **Cache blindness.** Reading a pre-built cache never exercises the write path.\n- **Silent crash.** Harness error recorded as a score.\n- **Oracle judge.** Uncalibrated model judge treated as ground truth.\n- **Rubric-author bias.** Whoever built the system also wrote the rubric, alone.\n- **Run until green.** Repeating a noisy eval until one run passes.\n- **Gate-set tuning \u002F overfitting.** Iterating on the held-out items the gate uses.\n- Run-completion checklist before calling anything done: `templates\u002Fquality-checklist.md`.\n\n---\n\n_Source: [alexgreensh\u002Feval-genius](https:\u002F\u002Fgithub.com\u002Falexgreensh\u002Feval-genius), Apache-2.0._\n","# Eval Genius\n\nAn eval is a claim you are willing to defend under hostile audit. You measure to earn\nthe right to say \"this is better\" and have it hold when someone sharp pushes back.\nBehave like a measurement engineer: state the promise, fix the bar before looking, hold\neverything else constant, distrust the instrument first, report the number that hurts.\nAssume the user may be starting from zero; plain language first, jargon when it earns it.\n\n---\n\n## Step 0: Does this need an eval, and where does it go?\n\nThree questions decide it (`references\u002F00-start-here.md`): does the output vary (model,\nprompt, retriever)? will it change again, and would a quiet regression cost something?\nis a decision or a public claim coming? No to all: a hand spot check, stop. Yes to any:\nan eval, sized to the stage the project is in.\n\n| Stage the user is at | Instrument | Smallest useful version |\n|---|---|---|\n| Exploring prompts and models | Spot check | 10 inputs, eyeball |\n| First working version | Smoke eval | 20 to 50 real inputs, code-checked; **this run is the baseline** |\n| Changing one thing | Paired eval vs baseline | Same items both arms, per-item diff, bar written first |\n| Merging or shipping | CI gate | Held-out items, three-way outcome, a known-bad item that must fail |\n| Comparing or claiming publicly | Benchmark | Versioned dataset and harness, intervals, report |\n| In production | Monitor | Same scorer on sampled live traffic |\n\nBuild the first eval at \"first working version\", never before, rarely after. For a\nfirst-timer, run the one-afternoon recipe in `00-start-here.md` and touch nothing else.\n\n## Route the request\n\nIdentify the job, then load only that reference. Every job still passes through Step 1.\n\n| User needs to... | Load |\n|---|---|\n| Know if they need an eval, where it fits, which one, or how to start | `references\u002F00-start-here.md` |\n| Decide what to measure at all, or the ask is \"make it better\" | `references\u002F01-foundation.md` |\n| Pick a grader or metric for a task | `references\u002F02-grading-and-metrics.md` |\n| Use, prompt, or trust an LLM judge | `references\u002F03-judge-calibration.md` |\n| Choose between an existing benchmark and a custom one | `references\u002F04-search-vs-build.md` |\n| Assemble items, labels, negatives, splits; contamination, overfitting | `references\u002F05-dataset-construction.md` |\n| Write or fix the runner, scorer, or reporter | `references\u002F06-harness-design.md` |\n| Put an eval in CI or a release gate | `references\u002F07-gates-and-ci.md` |\n| Say whether a delta is real | `references\u002F08-statistics.md` |\n| Write results up, or retire a benchmark | `references\u002F09-reporting.md` |\n| Evaluate an agent, tool use, or multi-turn task | `references\u002F10-agentic-evals.md` |\n| Read a result file with no prior experience | `references\u002F11-reading-results.md` |\n\nTemplates in `templates\u002F` get copied into the project, never edited in place. Scripts in\n`scripts\u002F` are stdlib-only CLIs with `--help`, exiting nonzero with a readable message:\n`check_gate.py` (per-item diff of treatment vs baseline; exits 0 PASS, 1 FAIL,\n2 CANNOT-MEASURE; refuses a comparison across mismatched fixture or judge fingerprints),\n`paired_bootstrap.py` (paired bootstrap interval on the delta, cluster-aware),\n`judge_agreement.py` (Cohen's kappa and PASS precision\u002Frecall of a judge vs human labels),\n`hash_fixture.py` (the canonical fixture content hash the manifest's `fixture_hash` wants,\nso two runs hash the same fixture to the same string). Match effort to stakes: a spot check needs Step 0 and little else; a\nrelease gate needs the whole chain. Load references on demand, not all at once.\n\n---\n\n## Step 1: Foundation (five minutes, never skipped)\n\nCopy `templates\u002Fpreregistration.md` next to the fixture and fill it before touching\ndata or code. A first-timer fills promise, lever, baseline, and bar; the rest follows.\n\n1. **Promise.** One plain sentence: what does the system promise, what is \"better\"?\n2. **Variables.** Levers (what changes), outcomes (what is watched), controls (what is\n   frozen). One lever per comparison; an unclassifiable variable means stop.\n3. **Placement.** A decision point, a risky seam, or a public claim; elsewhere, a spot\n   check or nothing.\n4. **Weight.** Spot check, eval, benchmark, or monitor (Step 0 table).\n5. **Bar.** The threshold in numbers, the falsifier (what proves the change useless),\n   and the outlier rule. Written before any run.\n\nDone when all five fields are filled and a baseline is named.\n\n## Step 2: Choose the grader (deterministic first)\n\nPush every check that *can* be code-graded down to code: exact match, regex, schema,\ntest suite, threshold. Free text gets decomposed (required facts present, forbidden\ncontent absent, format) before any judge sees it. Reserve a model or human judge for\nthe edge no assertion captures. 80% deterministic \u002F 20% judged is trusted; 100% judged\nis an opinion with error bars. Report layers separately, never one blended number. A\njudge is an instrument: calibrate against human labels, blind it, randomize order, pin\nmodel and prompt hash (`references\u002F03-judge-calibration.md`).\n\n## Step 3: Build or adopt\n\nSearch before building; an established benchmark buys ground truth nobody in the room\ncooked. Build custom the moment the public one rewards a proxy the system does not\ntarget, reusing public plumbing. Score candidates on `templates\u002Fbenchmark-assessment-scorecard.md`:\nwhat it rewards, contamination, label-error ceiling, whether it exercises *this*\nmechanism, whether it is maintained.\n\n## Step 4: Run under hard rules (a run that breaks one is not a result)\n\n- **Freeze the fixture.** Same items, corpus, snapshot, seeds; only the lever varies.\n  Refuse comparisons across mismatched fingerprints.\n- **Three-way outcome.** PASS, FAIL, or CANNOT-MEASURE. A crash, missing baseline, or\n  fingerprint mismatch is CANNOT-MEASURE, never FAIL and never PASS (`check_gate.py`).\n- **Prove the treatment arm is live** before the run.\n- **Cover the negative space**: items where the right answer is to refuse or return nothing.\n- **Repeat and show spread.** Noise wider than the effect means no result yet.\n- **Verify the verifier.** A known-bad case must go red before green is trusted.\n\n## Step 5: Read the result (in this order)\n\nFull walk in `references\u002F11-reading-results.md`; each check gates the next.\n\n1. **Did it run?** Exit code before score; negative control failed.\n2. **Against the written bar**, not against hope. Above: candidate win. Below the\n   falsifier: rejected. Between: not established.\n3. **Bigger than noise?** Paired interval on the delta (`paired_bootstrap.py`);\n   interval includes zero means \"not established\", never \"no effect\".\n4. **Items, not averages.** Read regressions first; reproduce one flip by hand.\n5. **Surprised?** A 0%, a 99%, a thirty-point jump is a harness bug until proven\n   otherwise. Never tune the system against a suspect gauge; fix the gauge or stop.\n6. **Layers and cost separately.** A win that doubled cost is a trade.\n\n## Step 6: Report honestly\nNumbers are claims with tiers, measured \u002F estimated \u002F aspirational, never summed across\ntiers. Three sentences minimum: the bar and whether it was met; the delta with interval,\nn, and flip counts; the caveat that most weakens the claim. Say when a benchmark is\nself-run. Retire what fails its bar, in writing. Template: `templates\u002Feval-report.md`.\n\n---\n\n## Anti-patterns (named so they can be refused)\n\n- **Metric-first.** A dataset and scale chosen before the promise is written.\n- **Eval too early or too late.** Measuring a prototype still in flux, or a shipped\n  system with twenty unattributed changes behind it.\n- **Blended score.** One number hiding which layer moved.\n- **Post-hoc bar.** Threshold decided after the result is known.\n- **Fixture drift.** Comparing across corpora, caches, or snapshots.\n- **Cache blindness.** Reading a pre-built cache never exercises the write path.\n- **Silent crash.** Harness error recorded as a score.\n- **Oracle judge.** Uncalibrated model judge treated as ground truth.\n- **Rubric-author bias.** Whoever built the system also wrote the rubric, alone.\n- **Run until green.** Repeating a noisy eval until one run passes.\n- **Gate-set tuning \u002F overfitting.** Iterating on the held-out items the gate uses.\n- Run-completion checklist before calling anything done: `templates\u002Fquality-checklist.md`.\n\n---\n\n_Source: [alexgreensh\u002Feval-genius](https:\u002F\u002Fgithub.com\u002Falexgreensh\u002Feval-genius), Apache-2.0._\n",{"name":5,"description":7},"main","2b749c82b5d11fac39d9a6e021ce3f5b8a541bd1","cli-tool\u002Fcomponents\u002Fskills\u002Fdevelopment\u002Feval-genius",3909,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates","https:\u002F\u002Faitmpl.com","https:\u002F\u002Fgithub.com\u002Fdavila7","https:\u002F\u002Fdanielavila.me","Building AI dev tools with LLMs","2026-11-11 11:53:30",{"source":8,"skillName":5,"commands":60,"prompt":70,"zipAvailable":71},[61,64,67],{"tool":62,"command":63},"npx","npx skills add davila7\u002Fclaude-code-templates --skill eval-genius",{"tool":65,"command":66},"bunx","bunx skills add davila7\u002Fclaude-code-templates --skill eval-genius",{"tool":68,"command":69},"pnpm","pnpm dlx skills add davila7\u002Fclaude-code-templates --skill eval-genius","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdevelopment\u002Feval-genius\u002FSKILL.md",true,[],[74,100,127,160,195,219],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":81,"publishedAt":44},"01M70NHBTQ8BV0A2SCAZXEPHCX","wealthville-pool-scoring","Score DeFi liquidity pools before providing liquidity. Returns a 0-100 pool score and an Enter\u002FHold\u002FExit\u002FReduce\u002FAvoid verdict with calibrated confidence for ~68,800 Solana pools and 575 EVM pools, plus a public miss-inclusive track record. Use when asked whether a pool is worth LPing into, which pools look best right now, or how accurate the scores have actually been.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fweb-data\u002Fwealthville-pool-scoring\u002FSKILL.md",[80],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[82,83,84,85,28,86,87,88,89,90,91,92,93,94,95,96,97,40,98,99],"scoring","pool","wealthville pool scoring","liquidity","for","exit","now","use","when","reduce","with","record","track","verdict","evm","solana","public","look",{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":107,"publishedAt":44},"01M70MB6VR8ERJ4EM8D5KHBMEV","technical-debt-auditor","Scans a codebase and produces a quantified technical debt report with a prioritized remediation plan. Analyzes dead code, TODO\u002FFIXME\u002FHACK markers, dependency staleness, complexity hotspots, code duplication signals, test coverage gaps, unused exports, and outdated patterns. Use this skill when the user asks to audit their codebase for tech debt, wants a health check of their code quality, says things like \"where should I focus refactoring\", \"find code smells\", \"audit my codebase\", \"what technical debt do we have\", \"prioritize cleanup work\", or asks about code quality metrics. Also trigger when the user mentions \"code rot\", \"legacy cleanup\", \"refactoring priorities\", or wants to understand the overall health of a project before a major effort. Trigger even if the user doesn't say \"technical debt\" explicitly — any request to systematically assess code quality and identify improvement priorities belongs here.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdevelopment\u002Ftechnical-debt-auditor\u002FSKILL.md",[106],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[108,109,110,111,112,113,114,115,116,117,118,90,119,120,121,122,123,124,125,126],"technical debt","debt","technical","technical debt auditor","auditor","coverage","complexity","markers","project","cleanup","unused","code","todo","work","plan","focus","signals","audit","dependency",{"skillNo":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":142,"publishedAt":44},"01M70KPYH9QNHCNME5GJQGE22K","readonly-sql-guard","Make an agent's database access provably read-only. Use when an agent runs caller-supplied SQL against a production\u002FERP\u002Fanalytics database (a \"query\" MCP tool, text-to-SQL, an admin console), or when reviewing DB-access code for write\u002FDDL\u002Fside-effect\u002Ftransaction-escape risks. Checks what a statement CALLS, not just its shape.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdatabase\u002Freadonly-sql-guard\u002FSKILL.md",[133,136,137],{"categoryNo":134,"categoryName":135,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":138,"categoryName":139,"taxonomyType":140,"taxonomyTypeDesc":141},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[143,144,145,146,147,148,149,86,150,151,152,153,154,155,156,89,157,158,90,159],"readonly","guard","sql guard","sql","readonly sql guard","erp","effect","read-only","db","just","tool","calls","only","MCP","access","database","query",{"skillNo":161,"name":162,"nameZh":6,"description":163,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":164,"licenseFileUrl":165,"sourceHtmlUrl":166,"categories":167,"keywords":171,"publishedAt":44},"01M6AFY6F7CC2BBZP1QD6VTNVC","web-artifacts-builder","Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn\u002Fui). Use for complex artifacts requiring state management, routing, or shadcn\u002Fui components - not for simple single-file HTML\u002FJSX artifacts.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FSKILL.md",[168],{"categoryNo":169,"categoryName":170,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",[172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,86,194],"artifacts builder","web","web artifacts builder","artifacts","builder","state","routing","state management","component","css","frontend","ui","Tools","file","components","shadcn","react","Tailwind","suite","jsx","html","single-file","ui components",{"skillNo":196,"name":197,"nameZh":6,"description":198,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":164,"licenseFileUrl":199,"sourceHtmlUrl":200,"categories":201,"keywords":206,"publishedAt":44},"01M6AFWF33SFV9Z3SF4PEEE4BF","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FSKILL.md",[202,205],{"categoryNo":203,"categoryName":204,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":169,"categoryName":170,"taxonomyType":21,"taxonomyTypeDesc":22},[207,208,209,210,211,173,212,182,183,213,214,215,216,86,217,92,218],"webapp testing","testing","webapp","browser","playwright","applications","debugging","toolkit","logs","screenshots","local","behavior",{"skillNo":220,"name":221,"nameZh":6,"description":222,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":164,"licenseFileUrl":223,"sourceHtmlUrl":224,"categories":225,"keywords":233,"publishedAt":44},"01M6AF67Q67JJJ5V51JR2P52KA","discernment-nudge","After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fdiscernment-nudge\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fdiscernment-nudge\u002FSKILL.md",[226,229,230],{"categoryNo":227,"categoryName":228,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":231,"categoryName":232,"taxonomyType":140,"taxonomyTypeDesc":141},"01JBSEEDCAT000000000000036","内容创作者",[234,235,236,237,42,238,239,240,175,241,185,119,242,243,244,245,246,155,247,90,248,249,250,251,252,40,253],"discernment nudge","nudge","interpretation","help","reasoning","data","writing","lookup","content","review","conversation","short","up","invoke","you","analysis","claims","argument","assemble","recommendations"]