[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EPD88JG2X9BV798NWV89PC":3,"skill-same:01M7EPD88JG2X9BV798NWV89PC":94},{"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":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M7EPD88JG2X9BV798NWV89PC","hand-test",null,"Hand the user ONE chat-native test after a completed build\u002Fswing — run-card's rigor delivered in the chat (nothing to open), 3–5 DO\u002FSEE-checkbox steps they tick as they flit. Use when laying a test\u002Fverification on the user: \"hand-test\", \"lay a test on me\", \"how do I check\u002Fverify this\", \"give me steps to confirm it works\", or after building something they'll verify by hand. NOT run-card (a paste-ready FILE for touching foreign systems), NOT rolls (status reports), NOT a CI runner.","inputloop\u002Fgarden","inputloop","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F339507215?v=4","01M7ENYT15EMVBAV30YXPQDYE2","Inputloop","01M7ENYT1SM9WM5PSMQDC9PE2G",0,"GPL-3.0","https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Fhand-test\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: hand-test\ndescription: >\n  Hand the user ONE chat-native test after a completed build\u002Fswing — run-card's rigor delivered in the chat (nothing to open), 3–5 DO\u002FSEE-checkbox steps they tick as they flit. Use when laying a test\u002Fverification on the user: \"hand-test\", \"lay a test on me\", \"how do I check\u002Fverify this\", \"give me steps to confirm it works\", or after building something they'll verify by hand. NOT run-card (a paste-ready FILE for touching foreign systems), NOT rolls (status reports), NOT a CI runner.\n---\n\n# hand-test — a chat-native test-program, handed to the keeper\n\nA **hand-test** gives the user *one* small test to run after a completed unit of work, delivered **in the\nchat** so they never navigate away, never open a file, never parse code-vs-markdown in a pager. It carries\n`run-card`'s spine (ordered steps · exact expected results · a clean\u002Fpass check) but is sized for a person\nwho is jumping around and must not lose the chat.\n\n## When to use\n- After you finish a build the user will verify **by hand** — a feature, a fix, a cross-fabric change.\n- Ration it: **one hand-test per completed unit** (\"swing\"). Not after every edit; not a wall of checks.\n- Do **not** use it for running against a foreign\u002Fproduction system you didn't build — that is `run-card`\n  (a paste-ready, auditable file). Do not use it for status reporting — that is `rolls`.\n\n## The form (keep it exactly this shape)\nA titled card, **3–5 steps**, closing in one line. No preamble, no \"why\" inline (offer it on ask — extra\nprose is noise that hides signal).\n\n```\nHAND-TEST — \u003Cthe claim this proves> (\u003Cwhat unit\u002Fswing>)\nRun at \u003Cthe working directory>.\n\n① \u003Cwhat this step proves>\n   \u003CONE fenced, copy-paste command>\n   - [ ] SEE `\u003Cthe exact string\u002Fshape to look for>`  → \u003Cpass condition, ≤5 words>\n\n② …\n③ …\n\nall ✓ ⇒ \u003Cthe claim> holds.\n```\n\n- **DO = one fenced command.** The user's only terminal act is paste + enter. No `cd`-then-open-then-read.\n- **`- [ ] SEE …` is a checkbox**, not prose. It carries the *exact* expected output next to the command\n  so verification is a glance-compare, and the user ticks it inline as they go. It does **not** report back\n  to you — it is *their* progress marker while they flit. (Mirror in a widget only if you also keep the\n  plain-chat version.)\n- **Close with one line**: `all ✓ ⇒ \u003Cclaim> holds.`\n\n## Non-negotiables\n1. **Prove every DO yourself first.** Run each command in your sandbox before handing it. A hand-test that\n   fails on the user's machine is worse than none — it spends their focus and their trust.\n2. **Prereqs are proven, not assumed.** Name the real interpreter invocation and pin the working directory.\n   Watch the user's actual toolchain — e.g. an interpreter not on `PATH`, a path with spaces that bites in\n   bash, a relative `require`\u002Fimport that needs the right CWD, a stricter compiler on their host than in\n   your sandbox. If in doubt, lead with a one-time `alias`\u002FPATH line.\n3. **Chat-resident.** Never \"go read `some.md`\". The steps and expected outputs live in the chat message so\n   they inherit real rendering (headings, fences) — code and prose never blur.\n4. **Self-locating.** Because each step is self-contained (do \u002F see \u002F pass), flitting away and back costs\n   nothing: the chat still says what to paste, what to see, and how to know.\n5. **Un-pedantic.** 3–5 steps, five-word pass conditions, no ceremony. Over-instruction is the failure mode.\n\n## Why this shape (the reading model it serves)\nPeople who move fast between the chat and a terminal read differently: the **chat is the reading surface**\nand every file-open is a flit-away cost plus a parse burden. They **copy-paste rather than navigate**, they\nverify by **expected-beside-actual**, they filter hard so **rationed + high-signal** wins, and many are\n**spatial thinkers** for whom an aligned DO \u002F SEE \u002F ✓ layout reads faster than a paragraph. Design to that.\n\n## Interlocks\n- `run-card` — the ancestor; use it (not this) for careful, auditable runs against systems you didn't build.\n- `rolls` — status\u002Fclose reports; a hand-test proves, a roll summarizes.\n- `takushi` — the last-mile delivery; a hand-test is one clean thing that must land where the user can see\n  it (the chat) and be acted on without you in the room.\n\n\n## How this skill can fail (falsifiers)\n\n- **An unproven DO.** fails if a step's command was not run in the sandbox before handing; check: each fenced command appears in an earlier tool call of the session, with the output its SEE line quotes.\n- **SEE does not match.** fails if the keeper's output differs from the SEE string; check: put their output beside the SEE line. The first suspects are the toolchain prereqs (interpreter, PATH, working directory).\n- **Too big.** fails if the card has more than 5 steps or asks the keeper to open a file; check: count the steps and look for \"open\" or \"read \u003Cfile>\".\n\n\u003C!-- footer: minted by bin\u002Fft1mt from conventions\u002Fhouse.env and conventions\u002FFOOTERS.org; edit those, not this -->\n*Version 1.1.0: edition revised from 1.0.1 on 2026-10-10; spine: 2026-09-11.*\n\nCopyright 2026 Corwin Brust \u003Ccorwin@bru.st> and Contributors; CC-BY-SA4: https:\u002F\u002Fcreativecommons.org\u002Flicenses\u002Fby-sa\u002F4.0\u002F (scripts GPL-3.0-or-later); Mentat (for Corwin; claude-opus-5-5)\n\u003C!-- \u002Ffooter -->\n","# hand-test — a chat-native test-program, handed to the keeper\n\nA **hand-test** gives the user *one* small test to run after a completed unit of work, delivered **in the\nchat** so they never navigate away, never open a file, never parse code-vs-markdown in a pager. It carries\n`run-card`'s spine (ordered steps · exact expected results · a clean\u002Fpass check) but is sized for a person\nwho is jumping around and must not lose the chat.\n\n## When to use\n- After you finish a build the user will verify **by hand** — a feature, a fix, a cross-fabric change.\n- Ration it: **one hand-test per completed unit** (\"swing\"). Not after every edit; not a wall of checks.\n- Do **not** use it for running against a foreign\u002Fproduction system you didn't build — that is `run-card`\n  (a paste-ready, auditable file). Do not use it for status reporting — that is `rolls`.\n\n## The form (keep it exactly this shape)\nA titled card, **3–5 steps**, closing in one line. No preamble, no \"why\" inline (offer it on ask — extra\nprose is noise that hides signal).\n\n```\nHAND-TEST — \u003Cthe claim this proves> (\u003Cwhat unit\u002Fswing>)\nRun at \u003Cthe working directory>.\n\n① \u003Cwhat this step proves>\n   \u003CONE fenced, copy-paste command>\n   - [ ] SEE `\u003Cthe exact string\u002Fshape to look for>`  → \u003Cpass condition, ≤5 words>\n\n② …\n③ …\n\nall ✓ ⇒ \u003Cthe claim> holds.\n```\n\n- **DO = one fenced command.** The user's only terminal act is paste + enter. No `cd`-then-open-then-read.\n- **`- [ ] SEE …` is a checkbox**, not prose. It carries the *exact* expected output next to the command\n  so verification is a glance-compare, and the user ticks it inline as they go. It does **not** report back\n  to you — it is *their* progress marker while they flit. (Mirror in a widget only if you also keep the\n  plain-chat version.)\n- **Close with one line**: `all ✓ ⇒ \u003Cclaim> holds.`\n\n## Non-negotiables\n1. **Prove every DO yourself first.** Run each command in your sandbox before handing it. A hand-test that\n   fails on the user's machine is worse than none — it spends their focus and their trust.\n2. **Prereqs are proven, not assumed.** Name the real interpreter invocation and pin the working directory.\n   Watch the user's actual toolchain — e.g. an interpreter not on `PATH`, a path with spaces that bites in\n   bash, a relative `require`\u002Fimport that needs the right CWD, a stricter compiler on their host than in\n   your sandbox. If in doubt, lead with a one-time `alias`\u002FPATH line.\n3. **Chat-resident.** Never \"go read `some.md`\". The steps and expected outputs live in the chat message so\n   they inherit real rendering (headings, fences) — code and prose never blur.\n4. **Self-locating.** Because each step is self-contained (do \u002F see \u002F pass), flitting away and back costs\n   nothing: the chat still says what to paste, what to see, and how to know.\n5. **Un-pedantic.** 3–5 steps, five-word pass conditions, no ceremony. Over-instruction is the failure mode.\n\n## Why this shape (the reading model it serves)\nPeople who move fast between the chat and a terminal read differently: the **chat is the reading surface**\nand every file-open is a flit-away cost plus a parse burden. They **copy-paste rather than navigate**, they\nverify by **expected-beside-actual**, they filter hard so **rationed + high-signal** wins, and many are\n**spatial thinkers** for whom an aligned DO \u002F SEE \u002F ✓ layout reads faster than a paragraph. Design to that.\n\n## Interlocks\n- `run-card` — the ancestor; use it (not this) for careful, auditable runs against systems you didn't build.\n- `rolls` — status\u002Fclose reports; a hand-test proves, a roll summarizes.\n- `takushi` — the last-mile delivery; a hand-test is one clean thing that must land where the user can see\n  it (the chat) and be acted on without you in the room.\n\n\n## How this skill can fail (falsifiers)\n\n- **An unproven DO.** fails if a step's command was not run in the sandbox before handing; check: each fenced command appears in an earlier tool call of the session, with the output its SEE line quotes.\n- **SEE does not match.** fails if the keeper's output differs from the SEE string; check: put their output beside the SEE line. The first suspects are the toolchain prereqs (interpreter, PATH, working directory).\n- **Too big.** fails if the card has more than 5 steps or asks the keeper to open a file; check: count the steps and look for \"open\" or \"read \u003Cfile>\".\n\n\u003C!-- footer: minted by bin\u002Fft1mt from conventions\u002Fhouse.env and conventions\u002FFOOTERS.org; edit those, not this -->\n*Version 1.1.0: edition revised from 1.0.1 on 2026-10-10; spine: 2026-09-11.*\n\nCopyright 2026 Corwin Brust \u003Ccorwin@bru.st> and Contributors; CC-BY-SA4: https:\u002F\u002Fcreativecommons.org\u002Flicenses\u002Fby-sa\u002F4.0\u002F (scripts GPL-3.0-or-later); Mentat (for Corwin; claude-opus-5-5)\n\u003C!-- \u002Ffooter -->\n",{"name":5,"description":7},"main","0b0a0f665f67605c3bc1d43500eea26ef3079a97","skills\u002Fhand-test","https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden","https:\u002F\u002Fgithub.com\u002Finputloop","2026-10-14 18:29:39",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add inputloop\u002Fgarden --skill hand-test",{"tool":36,"command":37},"bunx","bunx skills add inputloop\u002Fgarden --skill hand-test",{"tool":39,"command":40},"pnpm","pnpm dlx skills add inputloop\u002Fgarden --skill hand-test","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Fhand-test\u002FSKILL.md",true,[44,50,53,56,62,66,70,74,78,81,84,88,91],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},".arc\u002F2026-09\u002Fsignature-2026-09-23_pre-header-pass.asc","OTHER","其他",659,"https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Fhand-test\u002F.arc\u002F2026-09\u002Fsignature-2026-09-23_pre-header-pass.asc",{"path":51,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":52},".arc\u002F2026-09\u002Fsignature-2026-09-24_162126Z_pre-manifest.asc","https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Fhand-test\u002F.arc\u002F2026-09\u002Fsignature-2026-09-24_162126Z_pre-manifest.asc",{"path":54,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":55},".arc\u002F2026-09\u002Fsignature-2026-09-27_203833Z_pre-manifest.asc","https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Fhand-test\u002F.arc\u002F2026-09\u002Fsignature-2026-09-27_203833Z_pre-manifest.asc",{"path":57,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":60,"sourceHtmlUrl":61},".arc\u002F2026-09\u002FSKILL-2026-09-11_Archived-by-rcw-01dwoah4hj9uxpj4dacwrb2p.md","REFERENCE","参考文档",4336,"https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Fhand-test\u002F.arc\u002F2026-09\u002FSKILL-2026-09-11_Archived-by-rcw-01dwoah4hj9uxpj4dacwrb2p.md",{"path":63,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":64,"sourceHtmlUrl":65},".arc\u002F2026-09\u002FSKILL-2026-09-27_pre-hardening.md",4806,"https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Fhand-test\u002F.arc\u002F2026-09\u002FSKILL-2026-09-27_pre-hardening.md",{"path":67,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":68,"sourceHtmlUrl":69},".arc\u002F2026-09\u002Fskill-manifest-2026-09-23_pre-header-pass",319,"https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Fhand-test\u002F.arc\u002F2026-09\u002Fskill-manifest-2026-09-23_pre-header-pass",{"path":71,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":72,"sourceHtmlUrl":73},".arc\u002F2026-09\u002Fskill-manifest-2026-09-24_162126Z_pre-manifest",564,"https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Fhand-test\u002F.arc\u002F2026-09\u002Fskill-manifest-2026-09-24_162126Z_pre-manifest",{"path":75,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":76,"sourceHtmlUrl":77},".arc\u002F2026-09\u002Fskill-manifest-2026-09-27_203833Z_pre-manifest",77,"https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Fhand-test\u002F.arc\u002F2026-09\u002Fskill-manifest-2026-09-27_203833Z_pre-manifest",{"path":79,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":80},".arc\u002F2026-10\u002Fsignature-2026-10-10_104825Z_pre-manifest.asc","https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Fhand-test\u002F.arc\u002F2026-10\u002Fsignature-2026-10-10_104825Z_pre-manifest.asc",{"path":82,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":76,"sourceHtmlUrl":83},".arc\u002F2026-10\u002Fskill-manifest-2026-10-10_104825Z_pre-manifest","https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Fhand-test\u002F.arc\u002F2026-10\u002Fskill-manifest-2026-10-10_104825Z_pre-manifest",{"path":85,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":86,"sourceHtmlUrl":87},".arc\u002Freceipts\u002Faw2ri-2026-09.log",202,"https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Fhand-test\u002F.arc\u002Freceipts\u002Faw2ri-2026-09.log",{"path":89,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":90},".signature.asc","https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Fhand-test\u002F.signature.asc",{"path":92,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":76,"sourceHtmlUrl":93},".skill-manifest","https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Fhand-test\u002F.skill-manifest",[95,101,107,114,121,128],{"skillNo":96,"name":97,"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":98,"categories":99,"keywords":100,"publishedAt":19},"01M7EPTX6X52ZPGVQZHKVJ7FAZ","alpha","https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Flane-d\u002Fbr1in\u002Fours\u002Fskills\u002Falpha\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"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":104,"categories":105,"keywords":106,"publishedAt":19},"01M7EPTWCTS80QHFQ2ND3A1CW1","gamma","https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Flane-d\u002Fbr1in\u002Fours\u002FSOFT-SKILLS\u002Fgamma\u002FSKILL.md",[],[],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":19},"01M7EPTV3K3SCTRP0DR6BMMKR0","quiet","A fixture skill that declares no preferences, so skill.quiet.* has no reader.","https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Flane-a\u002Fdeclared\u002Fsoft\u002Fquiet\u002FSKILL.md",[],[],{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":120,"publishedAt":19},"01M7EPTSG0VE67F6PFAC0XJDQ4","demo","A fixture skill for tests\u002Fprefs-declared-spec.rb; it declares two preferences inline.","https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Flane-a\u002Fdeclared\u002Fsoft\u002Fdemo\u002FSKILL.md",[],[],{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":127,"publishedAt":19},"01M7EPTP0PM5WPTFBHPXBCFM5C","concise","Synthesized by polygram from memory tag 'concise'. explicitly flagged. Review and tighten this description before relying on it for triggering.","https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fconcise\u002FSKILL.md",[],[],{"skillNo":129,"name":130,"nameZh":6,"description":131,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":132,"categories":133,"keywords":134,"publishedAt":19},"01M7EPTAETQ62DJA8ZFEEBBZF0","writing-forms","Which writing form a dated deliverable takes in the shop, and the five techniques every form shares. Use whenever someone is about to write a dated deliverable — \"which form is this?\", \"write it up\", \"land a note \u002F card \u002F model \u002F lens\", \"what shape does a … take\", \"is there a form for this\", or when a new PREFIX-date-slug filename is about to be minted. Carries the rule that a deliverable picks ONE form and says so in its filename, points at the register c\u002Fwf (columns d\u002Fc\u002Fwf) as the source of truth, names the most-used forms, the five cross-cutting techniques (two piles · cite at the act · a falsifier on every concern · the pair rule · his words), how a new form is born, and the fence on notes other sessions wrote. Not rolls (report kinds and their guards), not reformat-prompt (the REFORMAT pair), not run-card (the RUNCARD), not skill-creator (skills). Owns the FORM, not the content.","https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-forms\u002FSKILL.md",[],[]]