[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7ERQ66VWCGCJ3QC69ESMMK4":3,"skill-same:01M7ERQ66VWCGCJ3QC69ESMMK4":51},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M7ERQ66VWCGCJ3QC69ESMMK4","web-consensus",null,"Use when a question has to be settled against the live web rather than from memory - researching a topic, proving or disproving a claim, checking whether something is still true, a sourced second opinion on a factual question - or when the user says \"research\", \"prove it\", \"with sources\", \"check if this is true\", \"still accurate?\".","jeancarlos\u002Fcode-jig","jeancarlos","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F713484?v=4","01M7ERGYQQEYJTXG5GXDY9SZVZ","Jean Souza","01M7ERGYRCBCN8GKJFCGEKQ2M1",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fjeancarlos\u002Fcode-jig\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fgolden\u002Fpersonal\u002Fskills\u002Fweb-consensus\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: web-consensus\ndescription: Use when a question has to be settled against the live web rather than from memory - researching a topic, proving or disproving a claim, checking whether something is still true, a sourced second opinion on a factual question - or when the user says \"research\", \"prove it\", \"with sources\", \"check if this is true\", \"still accurate?\".\n---\n\n# Web consensus\n\nCheap researchers gather evidence in parallel, a reviewer from another model family attacks it, the disputed points are researched again from scratch, a script checks every link and quote, and a judge on the strongest model writes the verdict from sources only.\n\n## Who does what\n\n| Step | Subagent role | Runs on |\n|---|---|---|\n| Evidence, cold verification | `explorer`, one per angle or question, in parallel | `bulk` tier: fast and cheap |\n| Challenge | `reviewer` | `review` tier: another model family |\n| Link and quote check | `harness check-sources` | no model |\n| Verdict | `judge` | `deep` tier: the strongest model |\n\nThis skill asks for subagents: every role in the table runs through `spawn_agent` with that `agent_type`, even when you wait for its result before the next step, because the point is a different model and a fresh context, not speed. Each subagent gets its own brief and nothing about the others, so no role can quietly agree with another, and never a fork of this conversation. You only route: write the evidence files, run the script, pass material between roles. Run the whole flow even when the answer looks obvious or one page settles it: \"it's a simple fact\", \"the docs already say it\" and \"one search is enough\" are the answers from memory this skill replaces. If `spawn_agent` is not available in this session, stop and say so: a consensus from one model playing every role is not this skill's output, so do not play the roles yourself.\n\n## Flow\n\n1. **Evidence.** One `explorer` per angle. Each returns claim \u002F URL \u002F exact quote triples and nothing else. Write them to `evidence-\u003Cangle>.jsonl` in the workspace, one JSON object per line: `{\"claim\": \"...\", \"url\": \"...\", \"quote\": \"...\"}`.\n   - `direct`: the question as asked.\n   - `disconfirming`: the strongest evidence that the expected answer is wrong: corrections, retractions, errata, dissenting primary sources.\n   - `primary-source`: official docs, specifications, source code, changelogs and papers only.\n   - `academic`, when the question has a research literature: papers, reproductions, negative results.\n\n   Vary the wording of the searches between angles. The same index returns very different results for differently worded questions.\n\n2. **Check.** `harness check-sources \"evidence-*.jsonl\"` (the command expands the pattern itself, so the same line works in PowerShell). It fetches each URL once and reports per claim: `ok` (the page contains the quote), `quote-missing`, `dead`, `blocked` (401\u002F403\u002F429: usually bot-blocking, not absence), `unreadable` (PDF or binary: quote unverified). It needs the network: in a sandbox, ask for escalation on the first run, not after a refusal. When the workspace is read-only, pipe the lines in and pass `-` as the file (`printf '%s\\n' \"$line1\" \"$line2\" | harness check-sources -`, in PowerShell `$lines | harness check-sources -`), and hand the evidence to the later roles inline in their briefs. One run covers every file. When it runs, the final reply quotes its summary line (`N claims: ...`) exactly as printed. If it still cannot run, nothing is checked: say so, the verdict's first line is `UNVERIFIED:` and no claim is agreed.\n\n3. **Challenge.** A `reviewer` reads the evidence files and the check report, and is told not to search. It rules on every claim with one line each, `OK`, `DOUBT` or `MISMATCH`, then lists the questions that would settle each dispute.\n\n4. **Cold verification.** For each of those questions, a fresh `explorer` gets only the question: no evidence and no challenge. Write its triples to `evidence-cold.jsonl` and run the check on it. When the challenge lists no disputes, skip this step and say so in the report; there is then only the first check report.\n\n5. **Verdict.** A `judge` gets the question, every evidence file, every check report (one, or two after cold verification) and the challenge. It answers in a short paragraph, then lists agreed, disputed and unsourced claims with URL and quote, its confidence, and what new evidence would change the answer. Relay the verdict; do not rewrite it, and never add that sources are independent.\n\n## Rules\n\n- A claim can only be agreed when `check-sources` says `ok`, or `unreadable` with the quote confirmed by a second source.\n- The searcher never dictates the answer alone. Evidence files from the same search are not independent sources; say how many distinct sites agree.\n- Prefer primary sources over secondary ones, and recent over old when the subject moves.\n- When results look stale, ask the user to start the session with live search (`codex -c web_search=\"live\"`).\n- If web search is not available in this session, say so and stop. Do not answer from memory.\n\n## Common mistakes\n\n| Mistake | Instead |\n|---|---|\n| Answering from one search because the question looks easy | Run every step; the user asked for sources checked by roles that did not write them. |\n| Forking this conversation into a researcher | A fresh brief; a fork re-reads everything and inherits your bias. |\n| Judging in the main session | The `judge` role exists so the verdict runs on the strongest model whatever tier this session uses. |\n| Treating `blocked` as `dead` | Say it was blocked; find a second source or quote it as unverified. |\n| Paraphrasing in the `quote` field | The check needs the exact words on the page. |\n","# Web consensus\n\nCheap researchers gather evidence in parallel, a reviewer from another model family attacks it, the disputed points are researched again from scratch, a script checks every link and quote, and a judge on the strongest model writes the verdict from sources only.\n\n## Who does what\n\n| Step | Subagent role | Runs on |\n|---|---|---|\n| Evidence, cold verification | `explorer`, one per angle or question, in parallel | `bulk` tier: fast and cheap |\n| Challenge | `reviewer` | `review` tier: another model family |\n| Link and quote check | `harness check-sources` | no model |\n| Verdict | `judge` | `deep` tier: the strongest model |\n\nThis skill asks for subagents: every role in the table runs through `spawn_agent` with that `agent_type`, even when you wait for its result before the next step, because the point is a different model and a fresh context, not speed. Each subagent gets its own brief and nothing about the others, so no role can quietly agree with another, and never a fork of this conversation. You only route: write the evidence files, run the script, pass material between roles. Run the whole flow even when the answer looks obvious or one page settles it: \"it's a simple fact\", \"the docs already say it\" and \"one search is enough\" are the answers from memory this skill replaces. If `spawn_agent` is not available in this session, stop and say so: a consensus from one model playing every role is not this skill's output, so do not play the roles yourself.\n\n## Flow\n\n1. **Evidence.** One `explorer` per angle. Each returns claim \u002F URL \u002F exact quote triples and nothing else. Write them to `evidence-\u003Cangle>.jsonl` in the workspace, one JSON object per line: `{\"claim\": \"...\", \"url\": \"...\", \"quote\": \"...\"}`.\n   - `direct`: the question as asked.\n   - `disconfirming`: the strongest evidence that the expected answer is wrong: corrections, retractions, errata, dissenting primary sources.\n   - `primary-source`: official docs, specifications, source code, changelogs and papers only.\n   - `academic`, when the question has a research literature: papers, reproductions, negative results.\n\n   Vary the wording of the searches between angles. The same index returns very different results for differently worded questions.\n\n2. **Check.** `harness check-sources \"evidence-*.jsonl\"` (the command expands the pattern itself, so the same line works in PowerShell). It fetches each URL once and reports per claim: `ok` (the page contains the quote), `quote-missing`, `dead`, `blocked` (401\u002F403\u002F429: usually bot-blocking, not absence), `unreadable` (PDF or binary: quote unverified). It needs the network: in a sandbox, ask for escalation on the first run, not after a refusal. When the workspace is read-only, pipe the lines in and pass `-` as the file (`printf '%s\\n' \"$line1\" \"$line2\" | harness check-sources -`, in PowerShell `$lines | harness check-sources -`), and hand the evidence to the later roles inline in their briefs. One run covers every file. When it runs, the final reply quotes its summary line (`N claims: ...`) exactly as printed. If it still cannot run, nothing is checked: say so, the verdict's first line is `UNVERIFIED:` and no claim is agreed.\n\n3. **Challenge.** A `reviewer` reads the evidence files and the check report, and is told not to search. It rules on every claim with one line each, `OK`, `DOUBT` or `MISMATCH`, then lists the questions that would settle each dispute.\n\n4. **Cold verification.** For each of those questions, a fresh `explorer` gets only the question: no evidence and no challenge. Write its triples to `evidence-cold.jsonl` and run the check on it. When the challenge lists no disputes, skip this step and say so in the report; there is then only the first check report.\n\n5. **Verdict.** A `judge` gets the question, every evidence file, every check report (one, or two after cold verification) and the challenge. It answers in a short paragraph, then lists agreed, disputed and unsourced claims with URL and quote, its confidence, and what new evidence would change the answer. Relay the verdict; do not rewrite it, and never add that sources are independent.\n\n## Rules\n\n- A claim can only be agreed when `check-sources` says `ok`, or `unreadable` with the quote confirmed by a second source.\n- The searcher never dictates the answer alone. Evidence files from the same search are not independent sources; say how many distinct sites agree.\n- Prefer primary sources over secondary ones, and recent over old when the subject moves.\n- When results look stale, ask the user to start the session with live search (`codex -c web_search=\"live\"`).\n- If web search is not available in this session, say so and stop. Do not answer from memory.\n\n## Common mistakes\n\n| Mistake | Instead |\n|---|---|\n| Answering from one search because the question looks easy | Run every step; the user asked for sources checked by roles that did not write them. |\n| Forking this conversation into a researcher | A fresh brief; a fork re-reads everything and inherits your bias. |\n| Judging in the main session | The `judge` role exists so the verdict runs on the strongest model whatever tier this session uses. |\n| Treating `blocked` as `dead` | Say it was blocked; find a second source or quote it as unverified. |\n| Paraphrasing in the `quote` field | The check needs the exact words on the page. |\n",{"name":5,"description":7},"main","a2dc094fb6f0ff71b419eb83322592dc2205a886","tests\u002Ffixtures\u002Fgolden\u002Fpersonal\u002Fskills\u002Fweb-consensus","https:\u002F\u002Fgithub.com\u002Fjeancarlos\u002Fcode-jig","https:\u002F\u002Fgithub.com\u002Fjeancarlos","jeansouza.dev","2026-11-14 06:47:58",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add jeancarlos\u002Fcode-jig --skill web-consensus",{"tool":37,"command":38},"bunx","bunx skills add jeancarlos\u002Fcode-jig --skill web-consensus",{"tool":40,"command":41},"pnpm","pnpm dlx skills add jeancarlos\u002Fcode-jig --skill web-consensus","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjeancarlos\u002Fcode-jig\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fgolden\u002Fpersonal\u002Fskills\u002Fweb-consensus\u002FSKILL.md",true,[45],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},".codex-harness","OTHER","其他",6,"https:\u002F\u002Fgithub.com\u002Fjeancarlos\u002Fcode-jig\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fgolden\u002Fpersonal\u002Fskills\u002Fweb-consensus\u002F.codex-harness",[52,59,66,73,80,87],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":19},"01M7ERQ34BFPG2AZKND979D6MM","skill-validate","Use when a SKILL.md is about to ship or was just edited, when a skill is reviewed or audited, when a skill seems ignored, skipped or misread by agents, or when the user says \"validate this skill\", \"lint the skill\", \"check my skill\", \"is this skill any good\".","https:\u002F\u002Fgithub.com\u002Fjeancarlos\u002Fcode-jig\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fgolden\u002Fpersonal\u002Fskills\u002Fskill-validate\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M7ERPZ4AKH7RW86WJAV07N05","regression-tests","Use when fixing a bug, changing behaviour or adding a feature in code that has tests, or when the user asks whether a change is covered by tests, wants regression tests, or wants coverage of the changed lines.","https:\u002F\u002Fgithub.com\u002Fjeancarlos\u002Fcode-jig\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fgolden\u002Fpersonal\u002Fskills\u002Fregression-tests\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"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},"01M7ERPW6EKD7SA8CMTBFQB7D4","redacao","Use when writing, rewriting or editing a technical article or blog post in Portuguese, or when the user says \"escreve um artigo\", \"reescreve o post\", \"redação\", \"pauta\", \"revisa o texto\", \"tira a cara de IA\".","https:\u002F\u002Fgithub.com\u002Fjeancarlos\u002Fcode-jig\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fgolden\u002Fpersonal\u002Fskills\u002Fredacao\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},"01M7ERPRV0XHDWATDY4M9XMF5C","improve","Use when the user asks to improve the harness, its rules, Guardian policy, skills or knowledge from experience on this machine, or says \"remember this for next time\", \"make this a rule\", \"teach the harness\".","https:\u002F\u002Fgithub.com\u002Fjeancarlos\u002Fcode-jig\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fgolden\u002Fpersonal\u002Fskills\u002Fimprove\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},"01M7ERPNXES66J7MJSP8W8A61X","hld-trace","Use when the user asks whether the code follows the high-level design (HLD), which requirements have tests, which are untested, or wants tests linked to requirement or work item IDs.","https:\u002F\u002Fgithub.com\u002Fjeancarlos\u002Fcode-jig\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fgolden\u002Fpersonal\u002Fskills\u002Fhld-trace\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},"01M7ERPJY5D2JDHYZ742QREY7E","grilling","Use when the user wants a plan, decision, design or idea stress-tested before committing to it, or says \"grill me\", \"grill this\", \"stress-test this\", \"poke holes in this\", \"what am I missing\". Do not fire on your own.","https:\u002F\u002Fgithub.com\u002Fjeancarlos\u002Fcode-jig\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fgolden\u002Fpersonal\u002Fskills\u002Fgrilling\u002FSKILL.md",[],[]]