[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75D2K1ME2TMG61S018PHREX":3,"skill-same:01M75D2K1ME2TMG61S018PHREX":48},{"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":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M75D2K1ME2TMG61S018PHREX","ijfw-critique",null,"Challenge decisions, surface counter-arguments, flag assumptions. Trigger: 'should I', 'is this right', 'critique', 'poke holes', 'second opinion', 'devil's advocate'. Auto-fired by ijfw-intent-router.","FerroxLabs\u002Fwayland-core","FerroxLabs","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F282419864?v=4","01M75CYVM226SP3XZWF1J1NE12","Ferrox Labs","01M75CYVMV004JEBXZQJR5MDR5",43,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FFerroxLabs\u002Fwayland-core\u002Fblob\u002Fmain\u002Fcrates\u002Fwayland-ijfw\u002Fsnapshots\u002Fijfw-source\u002Fclaude\u002Fskills\u002Fijfw-critique\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: ijfw-critique\ndescription: \"Challenge decisions, surface counter-arguments, flag assumptions. Trigger: 'should I', 'is this right', 'critique', 'poke holes', 'second opinion', 'devil's advocate'. Auto-fired by ijfw-intent-router.\"\n---\n\nBefore you agree, disagree. Before you advise, stress-test.\n\nWhen the user asks you to critique, review a decision, or give a second\nopinion -- or when the intent router flags critique intent -- follow this\npattern rather than answering from the same frame they asked from.\n\n## Four-step critique\n\n1. **Steelman first.** In one sentence, state the strongest version of the\n   current plan \u002F decision \u002F design. Not to flatter -- to make sure you're\n   critiquing the real thing, not a caricature.\n\n2. **Surface the assumptions.** Name 2-3 assumptions the plan rests on.\n   These are the load-bearing beliefs that, if wrong, collapse the argument.\n   Be specific: \"assumes traffic stays under 10k qps\", not \"assumes scale\".\n\n3. **Three concrete counter-arguments.** Each should be:\n   - *Non-obvious* (if the user already considered it, skip)\n   - *Bounded* (state when it applies; rarely are counter-arguments universal)\n   - *Actionable* (each comes with a \"watch for X\" or \"test by Y\")\n\n   Prefer counter-arguments that come from different angles: operational,\n   social\u002Forganizational, economic, correctness. One bug-class concern is\n   worth less than one operational + one social + one correctness concern.\n\n4. **State your verdict briefly.** After laying out the counters, give a\n   1-line recommendation: proceed \u002F proceed with X mitigation \u002F stop and\n   rework because Y. Own the verdict -- don't just hedge.\n\n## Refactor reframe (single-line trigger)\n\nWhen the user is mid-refactor and a fix feels hacky, or you catch yourself\npatching around a smell rather than removing it, run this prompt out loud:\n\n> *Knowing everything I know now, what would the elegant solution look like?*\n\nAnswer it briefly (3-5 lines). If the elegant version costs less than the\nhack you're about to ship, replace the hack. If it costs more than 2x, log\nthe elegant version as a follow-up and proceed with the pragmatic fix --\nbut only after you've named the debt explicitly.\n\nSkip this for trivial or obvious fixes; the point is to break frame on\nnon-trivial decisions, not to over-engineer.\n\n## When NOT to critique\n\n- The user is midway through implementing and needs help, not a critique.\n- The decision is reversible and cheap (just do it and see).\n- You lack the domain facts to form an opinion -- say so instead of guessing.\n- The question is \"how\" not \"whether\". How-to questions deserve how-to\n  answers, not a rehash of whether to do it at all.\n\n## Output shape\n\n```\nSteelman: \u003Cone-line strongest version>\n\nAssumptions:\n  1. \u003Cload-bearing belief>\n  2. \u003Cload-bearing belief>\n\nCounter-arguments:\n  1. \u003Cnon-obvious objection> -- applies when \u003Ccondition>; watch for \u003Csignal>.\n  2. \u003Cdifferent angle> -- applies when \u003Ccondition>; test with \u003Cmethod>.\n  3. \u003Cthird angle> -- applies when \u003Ccondition>; mitigate via \u003Capproach>.\n\nVerdict: \u003Cproceed|mitigate|rework> -- \u003Cone-line reason>\n\nAudit: stress-tested \u003CN> assumptions, \u003CN> angles (\u003Cangle-1> + \u003Cangle-2> + \u003Cangle-3>). Confidence: \u003Clow|med|high>.\n```\n\n### Worked example\n\n```\nSteelman: Rewriting the auth layer in Rust eliminates the class of memory bugs that caused last quarter's outages.\n\nAssumptions:\n  1. The team has enough Rust fluency to maintain the new code without slowdown.\n  2. The outages trace to memory bugs, not logic or config errors.\n\nCounter-arguments:\n  1. Operationally: Rust compile times and borrow-checker friction could double review cycles -- applies when the team has \u003C3 months Rust experience; watch for PR cycle time increasing past 2 days.\n  2. Socially: the auth team may resist a full rewrite when incremental hardening (address-sanitiser + fuzzing) could close the same risk at 20% of the effort -- applies when management is measuring velocity; test by asking the team to estimate both approaches.\n  3. Correctness: auth logic bugs (e.g. missing token expiry checks) are language-agnostic -- applies if the root-cause analysis is incomplete; mitigate by running a postmortem before deciding on the rewrite.\n\nVerdict: mitigate -- commission a 2-week root-cause analysis first; if the cause is confirmed memory-safety, Rust is the right call.\n\nAudit: stress-tested 2 assumptions, 3 angles (operational + social + correctness). Confidence: high.\n```\n\n## Tone\n\nDirect, not hedging. The user asked for a critique; they don't need\n\"this is just my opinion\". State the counter clearly. If they push back,\nthat's the signal to update or yield -- but make them do the work of\npushing back, not you.\n\nResume normal mode after.\n","Before you agree, disagree. Before you advise, stress-test.\n\nWhen the user asks you to critique, review a decision, or give a second\nopinion -- or when the intent router flags critique intent -- follow this\npattern rather than answering from the same frame they asked from.\n\n## Four-step critique\n\n1. **Steelman first.** In one sentence, state the strongest version of the\n   current plan \u002F decision \u002F design. Not to flatter -- to make sure you're\n   critiquing the real thing, not a caricature.\n\n2. **Surface the assumptions.** Name 2-3 assumptions the plan rests on.\n   These are the load-bearing beliefs that, if wrong, collapse the argument.\n   Be specific: \"assumes traffic stays under 10k qps\", not \"assumes scale\".\n\n3. **Three concrete counter-arguments.** Each should be:\n   - *Non-obvious* (if the user already considered it, skip)\n   - *Bounded* (state when it applies; rarely are counter-arguments universal)\n   - *Actionable* (each comes with a \"watch for X\" or \"test by Y\")\n\n   Prefer counter-arguments that come from different angles: operational,\n   social\u002Forganizational, economic, correctness. One bug-class concern is\n   worth less than one operational + one social + one correctness concern.\n\n4. **State your verdict briefly.** After laying out the counters, give a\n   1-line recommendation: proceed \u002F proceed with X mitigation \u002F stop and\n   rework because Y. Own the verdict -- don't just hedge.\n\n## Refactor reframe (single-line trigger)\n\nWhen the user is mid-refactor and a fix feels hacky, or you catch yourself\npatching around a smell rather than removing it, run this prompt out loud:\n\n> *Knowing everything I know now, what would the elegant solution look like?*\n\nAnswer it briefly (3-5 lines). If the elegant version costs less than the\nhack you're about to ship, replace the hack. If it costs more than 2x, log\nthe elegant version as a follow-up and proceed with the pragmatic fix --\nbut only after you've named the debt explicitly.\n\nSkip this for trivial or obvious fixes; the point is to break frame on\nnon-trivial decisions, not to over-engineer.\n\n## When NOT to critique\n\n- The user is midway through implementing and needs help, not a critique.\n- The decision is reversible and cheap (just do it and see).\n- You lack the domain facts to form an opinion -- say so instead of guessing.\n- The question is \"how\" not \"whether\". How-to questions deserve how-to\n  answers, not a rehash of whether to do it at all.\n\n## Output shape\n\n```\nSteelman: \u003Cone-line strongest version>\n\nAssumptions:\n  1. \u003Cload-bearing belief>\n  2. \u003Cload-bearing belief>\n\nCounter-arguments:\n  1. \u003Cnon-obvious objection> -- applies when \u003Ccondition>; watch for \u003Csignal>.\n  2. \u003Cdifferent angle> -- applies when \u003Ccondition>; test with \u003Cmethod>.\n  3. \u003Cthird angle> -- applies when \u003Ccondition>; mitigate via \u003Capproach>.\n\nVerdict: \u003Cproceed|mitigate|rework> -- \u003Cone-line reason>\n\nAudit: stress-tested \u003CN> assumptions, \u003CN> angles (\u003Cangle-1> + \u003Cangle-2> + \u003Cangle-3>). Confidence: \u003Clow|med|high>.\n```\n\n### Worked example\n\n```\nSteelman: Rewriting the auth layer in Rust eliminates the class of memory bugs that caused last quarter's outages.\n\nAssumptions:\n  1. The team has enough Rust fluency to maintain the new code without slowdown.\n  2. The outages trace to memory bugs, not logic or config errors.\n\nCounter-arguments:\n  1. Operationally: Rust compile times and borrow-checker friction could double review cycles -- applies when the team has \u003C3 months Rust experience; watch for PR cycle time increasing past 2 days.\n  2. Socially: the auth team may resist a full rewrite when incremental hardening (address-sanitiser + fuzzing) could close the same risk at 20% of the effort -- applies when management is measuring velocity; test by asking the team to estimate both approaches.\n  3. Correctness: auth logic bugs (e.g. missing token expiry checks) are language-agnostic -- applies if the root-cause analysis is incomplete; mitigate by running a postmortem before deciding on the rewrite.\n\nVerdict: mitigate -- commission a 2-week root-cause analysis first; if the cause is confirmed memory-safety, Rust is the right call.\n\nAudit: stress-tested 2 assumptions, 3 angles (operational + social + correctness). Confidence: high.\n```\n\n## Tone\n\nDirect, not hedging. The user asked for a critique; they don't need\n\"this is just my opinion\". State the counter clearly. If they push back,\nthat's the signal to update or yield -- but make them do the work of\npushing back, not you.\n\nResume normal mode after.\n",{"name":5,"description":7},"main","3d3856d40994705fe623903ab3587dc87fbf5421","crates\u002Fwayland-ijfw\u002Fsnapshots\u002Fijfw-source\u002Fclaude\u002Fskills\u002Fijfw-critique",17,"https:\u002F\u002Fgithub.com\u002FFerroxLabs\u002Fwayland-core","https:\u002F\u002Fgetwayland.com","https:\u002F\u002Fgithub.com\u002FFerroxLabs","https:\u002F\u002Fferroxlabs.com","AI research and development lab for cognitive research, LLM development, and applied agentic architecture. ","2026-11-03 21:55:30",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add FerroxLabs\u002Fwayland-core --skill ijfw-critique",{"tool":40,"command":41},"bunx","bunx skills add FerroxLabs\u002Fwayland-core --skill ijfw-critique",{"tool":43,"command":44},"pnpm","pnpm dlx skills add FerroxLabs\u002Fwayland-core --skill ijfw-critique","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FFerroxLabs\u002Fwayland-core\u002Fblob\u002Fmain\u002Fcrates\u002Fwayland-ijfw\u002Fsnapshots\u002Fijfw-source\u002Fclaude\u002Fskills\u002Fijfw-critique\u002FSKILL.md",true,[],[49,55,61,67,73,79],{"skillNo":50,"name":51,"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":52,"categories":53,"keywords":54,"publishedAt":19},"01M75D4C2W8YAJQ0WZ3B2871XB","imagine","https:\u002F\u002Fgithub.com\u002FFerroxLabs\u002Fwayland-core\u002Fblob\u002Fmain\u002Fcrates\u002Fwcore-cli\u002Ftests\u002Ffixtures\u002Fportability\u002Fgrok\u002Fskills\u002Fimagine\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"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":58,"categories":59,"keywords":60,"publishedAt":19},"01M75D4A7H12BDX7S15PH7C67X","help","https:\u002F\u002Fgithub.com\u002FFerroxLabs\u002Fwayland-core\u002Fblob\u002Fmain\u002Fcrates\u002Fwcore-cli\u002Ftests\u002Ffixtures\u002Fportability\u002Fgrok\u002Fskills\u002Fhelp\u002FSKILL.md",[],[],{"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},"01M75D49DSW0AD9KXYD7AXARDZ","create-skill","https:\u002F\u002Fgithub.com\u002FFerroxLabs\u002Fwayland-core\u002Fblob\u002Fmain\u002Fcrates\u002Fwcore-cli\u002Ftests\u002Ffixtures\u002Fportability\u002Fgrok\u002Fskills\u002Fcreate-skill\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},"01M75D48H154QZPZFBYN32TT38","code-review","https:\u002F\u002Fgithub.com\u002FFerroxLabs\u002Fwayland-core\u002Fblob\u002Fmain\u002Fcrates\u002Fwcore-cli\u002Ftests\u002Ffixtures\u002Fportability\u002Fgrok\u002Fskills\u002Fcode-review\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"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":76,"categories":77,"keywords":78,"publishedAt":19},"01M75D46881EDMJT48ESBHZHG3","check-work","https:\u002F\u002Fgithub.com\u002FFerroxLabs\u002Fwayland-core\u002Fblob\u002Fmain\u002Fcrates\u002Fwcore-cli\u002Ftests\u002Ffixtures\u002Fportability\u002Fgrok\u002Fskills\u002Fcheck-work\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M75D43YWCNMXBF92MR8A6PBX","self-promoting","A peer skill that claims its own trust in every way it can.","https:\u002F\u002Fgithub.com\u002FFerroxLabs\u002Fwayland-core\u002Fblob\u002Fmain\u002Fcrates\u002Fwcore-cli\u002Ftests\u002Ffixtures\u002Fportability-exec\u002Fskills\u002Fself-promoting\u002FSKILL.md",[],[]]