[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EPPD9ZNPZMN652EEWZTMC7":3,"skill-same:01M7EPPD9ZNPZMN652EEWZTMC7":122},{"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":30,"commitSha":31,"skillDirectory":32,"forksCount":14,"repositoryHtmlUrl":33,"repositoryHomepageUrl":6,"ownerHtmlUrl":34,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":35,"install":36,"resources":49},"01M7EPPD9ZNPZMN652EEWZTMC7","skill-metrics",null,"Keep a time series of what each shipped thing in the garden is doing — one row per interesting event (ITEM STATE CUR LAST DATE NOTE), one file per item holding its last STATE, and content-keyed archives of the current and previous version of its constituent. Use when benchmarking or checking a skill, plugin, tool or package and the result should be remembered: \"log this result\", \"what state is polygram in\", \"which skills are RED\", \"when did skill-sign last change\", \"benchmark the skills\", \"record the garden run\", \"skill metrics\", \"show the metrics log\", \"what was the previous version\". Ships the implementation (scripts\u002Fsk2mt, POSIX sh, plus the house library sh1lib.sh), a SPEC, and a suite with a second reader in Python — nothing to re-implement from notes or host config. Reads model POSIX grep over item names (exact names, -e\u002F-E\u002F-F, -i -v -x -c -l -q). Not a dashboard, not a token counter by itself, not a test runner — it remembers what a runner found.","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\u002Fskill-metrics\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: skill-metrics\ndescription: >\n  Keep a time series of what each shipped thing in the garden is doing — one row per interesting event (ITEM STATE CUR LAST DATE NOTE), one file per item holding its last STATE, and content-keyed archives of the current and previous version of its constituent. Use when benchmarking or checking a skill, plugin, tool or package and the result should be remembered: \"log this result\", \"what state is polygram in\", \"which skills are RED\", \"when did skill-sign last change\", \"benchmark the skills\", \"record the garden run\", \"skill metrics\", \"show the metrics log\", \"what was the previous version\". Ships the implementation (scripts\u002Fsk2mt, POSIX sh, plus the house library sh1lib.sh), a SPEC, and a suite with a second reader in Python — nothing to re-implement from notes or host config. Reads model POSIX grep over item names (exact names, -e\u002F-E\u002F-F, -i -v -x -c -l -q). Not a dashboard, not a token counter by itself, not a test runner — it remembers what a runner found.\nmetadata:\n  c4_status: mint-unblessed\n  c4_minted: 2026-09-22\n  c4_born_of: Corwin's 2026-09-22 ask for routine per-skill benchmarking as a skill and an MCP wiring surface\n  c4_ships_tool: scripts\u002Fsk2mt + scripts\u002Fsh1lib.sh + SPEC.md + tests.sh + tests\u002Ftest_spec.py\n---\n\n# skill-metrics\n\nA small store that remembers what happened to each thing the garden ships. It keeps *change*,\nnot noise: a row is written only when an item's STATE changes or its constituent's bytes change.\n\n## The store, in one look\n\n    metrics\u002Flog                    ITEM STATE CUR LAST DATE NOTE   (one event per line)\n    metrics\u002Fskill-metrics\u002FITEM     the last STATE, nothing else — `cat` it\n    metrics\u002Farchive\u002FITEM\u002FH-NAME    archived constituent, H = first 16 hex of its sha256\n\n- **ITEM** — the name people use for it: `polygram`, `skill-sign`, `c4`, `card-games.el`.\n- **STATE** — one word: `GREEN`, `RED`, `LOOK`, `OK`, `FAULT`, `1234B`.\n- **CUR \u002F LAST** — the archived current and previous constituent, or `NONE`. The constituent is the\n  full deliverable when there is one, else the most user-facing interface (a skill's `SKILL.md`).\n- **NOTE** — the rest of the line: measures, counts, the reason.\n\nThe whole contract is `SPEC.md`. Read it before changing anything here.\n\n## Doing things\n\nRun from the directory that holds `metrics\u002F`, or pass `-C DIR`, or set `SKILL_METRICS_ROOT`.\n\n    sh scripts\u002Fsk2mt init                                  # the only command that creates a store\n    sh scripts\u002Fsk2mt set skill-sign OK --file skills\u002Fskill-sign\u002FSKILL.md --note \"lint ok; 4296B\"\n    sh scripts\u002Fsk2mt state skill-sign                      # -> OK\n    sh scripts\u002Fsk2mt state                                 # every item, \"ITEM STATE\"\n    sh scripts\u002Fsk2mt state -e '^gf-'                       # a pattern (BRE; -E for ERE)\n    sh scripts\u002Fsk2mt last polygram c4                      # a word list: exact names\n    sh scripts\u002Fsk2mt items --state RED                     # which items are RED right now\n    sh scripts\u002Fsk2mt say polygram                          # one plain-English sentence\n    sh scripts\u002Fsk2mt table                                 # latest rows, aligned\n    sh scripts\u002Fsk2mt log skill-sign                        # full history\n    sh scripts\u002Fsk2mt check                                 # is the store self-consistent?\n\nField views are `state cur last date note row`. Patterns match item *names*; to filter by\nwhat an item *is*, add `--state WORD`. Exit codes are grep's: 0 found, 1 none, 2 error —\nplus 3 for NOTVISIBLE (no store where you pointed).\n\n**Without the tool.** `cat metrics\u002Fskill-metrics\u002Fpolygram` and `grep -l -x RED metrics\u002Fskill-metrics\u002F*`\nwork on their own. That is deliberate: the store must outlive its scripts.\n\n## Rules this carries\n\n1. **A root you named is never created for you.** Only `init` creates. A typo and a first run look\n   the same from inside; refusing is the only honest answer.\n2. **Append-only.** No command rewrites or removes a log line. Mistakes are corrected by a new row.\n3. **Content, not location.** Archive names carry their hash; `check` re-hashes every one it names.\n4. **Word lists are exact names.** GNU `grep -w` is refused on purpose: names carry `-` and `.`, and\n   GNU word-matching would find `layered` inside `gf-02-layered-assurance`.\n5. **Report in words.** When a human asked, answer with `say`, not with rows.\n\n## Testing it\n\n    sh tests.sh              # shell checks against SPEC.md, then the Python second reader\n    sh tests.sh --prove-red  # the harness must go red on a planted wrong expectation\n    python3 tests\u002Ftest_sh1lib.py --prove-red  # sh1lib.sh directly: all three sl_hash branches, every helper\n\n## Where it plugs in\n\n- **The garden kit** (`bin\u002Fgd1ck` in AS4CE0001) runs every suite and benchmark and records each\n  result through `sk2mt set`. `gd1ck` is the runner; this skill is the memory.\n- **MCP.** A server that wants these answers should run `scripts\u002Fsk2mt` (read views only) rather\n  than re-implement the format — one implementation, many callers. Not wired yet; see the\n  plugin README's usage section for the state of that.\n\n## How this skill can fail (falsifiers)\n\n- **A root created for you.** fails if any command but `init` creates a store; check: `sh scripts\u002Fsk2mt -C \u002Ftmp\u002Fnone state; echo $?` prints 3, and `\u002Ftmp\u002Fnone` stays empty.\n- **History rewritten.** fails if a log line changes or disappears; check: save `metrics\u002Flog`, run your commands, then `head -n $(wc -l \u003C SAVED) metrics\u002Flog | cmp - SAVED`.\n- **An archive does not match its name.** fails if a constituent's sha256 prefix differs from its `H-` name; check: `sh scripts\u002Fsk2mt check`.\n- **The readers disagree with SPEC.md.** fails if the shell or Python reader departs from the spec; check: `sh tests.sh` (46\u002F46 on 2026-09-27) and `sh tests.sh --prove-red`.\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: 2026-09-22.*\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","# skill-metrics\n\nA small store that remembers what happened to each thing the garden ships. It keeps *change*,\nnot noise: a row is written only when an item's STATE changes or its constituent's bytes change.\n\n## The store, in one look\n\n    metrics\u002Flog                    ITEM STATE CUR LAST DATE NOTE   (one event per line)\n    metrics\u002Fskill-metrics\u002FITEM     the last STATE, nothing else — `cat` it\n    metrics\u002Farchive\u002FITEM\u002FH-NAME    archived constituent, H = first 16 hex of its sha256\n\n- **ITEM** — the name people use for it: `polygram`, `skill-sign`, `c4`, `card-games.el`.\n- **STATE** — one word: `GREEN`, `RED`, `LOOK`, `OK`, `FAULT`, `1234B`.\n- **CUR \u002F LAST** — the archived current and previous constituent, or `NONE`. The constituent is the\n  full deliverable when there is one, else the most user-facing interface (a skill's `SKILL.md`).\n- **NOTE** — the rest of the line: measures, counts, the reason.\n\nThe whole contract is `SPEC.md`. Read it before changing anything here.\n\n## Doing things\n\nRun from the directory that holds `metrics\u002F`, or pass `-C DIR`, or set `SKILL_METRICS_ROOT`.\n\n    sh scripts\u002Fsk2mt init                                  # the only command that creates a store\n    sh scripts\u002Fsk2mt set skill-sign OK --file skills\u002Fskill-sign\u002FSKILL.md --note \"lint ok; 4296B\"\n    sh scripts\u002Fsk2mt state skill-sign                      # -> OK\n    sh scripts\u002Fsk2mt state                                 # every item, \"ITEM STATE\"\n    sh scripts\u002Fsk2mt state -e '^gf-'                       # a pattern (BRE; -E for ERE)\n    sh scripts\u002Fsk2mt last polygram c4                      # a word list: exact names\n    sh scripts\u002Fsk2mt items --state RED                     # which items are RED right now\n    sh scripts\u002Fsk2mt say polygram                          # one plain-English sentence\n    sh scripts\u002Fsk2mt table                                 # latest rows, aligned\n    sh scripts\u002Fsk2mt log skill-sign                        # full history\n    sh scripts\u002Fsk2mt check                                 # is the store self-consistent?\n\nField views are `state cur last date note row`. Patterns match item *names*; to filter by\nwhat an item *is*, add `--state WORD`. Exit codes are grep's: 0 found, 1 none, 2 error —\nplus 3 for NOTVISIBLE (no store where you pointed).\n\n**Without the tool.** `cat metrics\u002Fskill-metrics\u002Fpolygram` and `grep -l -x RED metrics\u002Fskill-metrics\u002F*`\nwork on their own. That is deliberate: the store must outlive its scripts.\n\n## Rules this carries\n\n1. **A root you named is never created for you.** Only `init` creates. A typo and a first run look\n   the same from inside; refusing is the only honest answer.\n2. **Append-only.** No command rewrites or removes a log line. Mistakes are corrected by a new row.\n3. **Content, not location.** Archive names carry their hash; `check` re-hashes every one it names.\n4. **Word lists are exact names.** GNU `grep -w` is refused on purpose: names carry `-` and `.`, and\n   GNU word-matching would find `layered` inside `gf-02-layered-assurance`.\n5. **Report in words.** When a human asked, answer with `say`, not with rows.\n\n## Testing it\n\n    sh tests.sh              # shell checks against SPEC.md, then the Python second reader\n    sh tests.sh --prove-red  # the harness must go red on a planted wrong expectation\n    python3 tests\u002Ftest_sh1lib.py --prove-red  # sh1lib.sh directly: all three sl_hash branches, every helper\n\n## Where it plugs in\n\n- **The garden kit** (`bin\u002Fgd1ck` in AS4CE0001) runs every suite and benchmark and records each\n  result through `sk2mt set`. `gd1ck` is the runner; this skill is the memory.\n- **MCP.** A server that wants these answers should run `scripts\u002Fsk2mt` (read views only) rather\n  than re-implement the format — one implementation, many callers. Not wired yet; see the\n  plugin README's usage section for the state of that.\n\n## How this skill can fail (falsifiers)\n\n- **A root created for you.** fails if any command but `init` creates a store; check: `sh scripts\u002Fsk2mt -C \u002Ftmp\u002Fnone state; echo $?` prints 3, and `\u002Ftmp\u002Fnone` stays empty.\n- **History rewritten.** fails if a log line changes or disappears; check: save `metrics\u002Flog`, run your commands, then `head -n $(wc -l \u003C SAVED) metrics\u002Flog | cmp - SAVED`.\n- **An archive does not match its name.** fails if a constituent's sha256 prefix differs from its `H-` name; check: `sh scripts\u002Fsk2mt check`.\n- **The readers disagree with SPEC.md.** fails if the shell or Python reader departs from the spec; check: `sh tests.sh` (46\u002F46 on 2026-09-27) and `sh tests.sh --prove-red`.\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: 2026-09-22.*\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,"metadata":24,"description":29},{"c4_minted":25,"c4_status":26,"c4_born_of":27,"c4_ships_tool":28},1790035200000,"mint-unblessed","Corwin's 2026-09-22 ask for routine per-skill benchmarking as a skill and an MCP wiring surface","scripts\u002Fsk2mt + scripts\u002Fsh1lib.sh + SPEC.md + tests.sh + tests\u002Ftest_spec.py","Keep a time series of what each shipped thing in the garden is doing — one row per interesting event (ITEM STATE CUR LAST DATE NOTE), one file per item holding its last STATE, and content-keyed archives of the current and previous version of its constituent. Use when benchmarking or checking a skill, plugin, tool or package and the result should be remembered: \"log this result\", \"what state is polygram in\", \"which skills are RED\", \"when did skill-sign last change\", \"benchmark the skills\", \"record the garden run\", \"skill metrics\", \"show the metrics log\", \"what was the previous version\". Ships the implementation (scripts\u002Fsk2mt, POSIX sh, plus the house library sh1lib.sh), a SPEC, and a suite with a second reader in Python — nothing to re-implement from notes or host config. Reads model POSIX grep over item names (exact names, -e\u002F-E\u002F-F, -i -v -x -c -l -q). Not a dashboard, not a token counter by itself, not a test runner — it remembers what a runner found.\n","main","0b0a0f665f67605c3bc1d43500eea26ef3079a97","skills\u002Fskill-metrics","https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden","https:\u002F\u002Fgithub.com\u002Finputloop","2026-10-14 18:29:39",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add inputloop\u002Fgarden --skill skill-metrics",{"tool":42,"command":43},"bunx","bunx skills add inputloop\u002Fgarden --skill skill-metrics",{"tool":45,"command":46},"pnpm","pnpm dlx skills add inputloop\u002Fgarden --skill skill-metrics","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Fskill-metrics\u002FSKILL.md",true,[50,56,59,62,68,72,76,80,83,86,90,93,96,102,106,110,114,118],{"path":51,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":55},".arc\u002F2026-09\u002Fsignature-2026-09-23_pre-header-pass.asc","OTHER","其他",659,"https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Fskill-metrics\u002F.arc\u002F2026-09\u002Fsignature-2026-09-23_pre-header-pass.asc",{"path":57,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":58},".arc\u002F2026-09\u002Fsignature-2026-09-24_162128Z_pre-manifest.asc","https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Fskill-metrics\u002F.arc\u002F2026-09\u002Fsignature-2026-09-24_162128Z_pre-manifest.asc",{"path":60,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":61},".arc\u002F2026-09\u002Fsignature-2026-09-27_203835Z_pre-manifest.asc","https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Fskill-metrics\u002F.arc\u002F2026-09\u002Fsignature-2026-09-27_203835Z_pre-manifest.asc",{"path":63,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":66,"sourceHtmlUrl":67},".arc\u002F2026-09\u002FSKILL-2026-09-27_pre-hardening.md","REFERENCE","参考文档",5509,"https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Fskill-metrics\u002F.arc\u002F2026-09\u002FSKILL-2026-09-27_pre-hardening.md",{"path":69,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":70,"sourceHtmlUrl":71},".arc\u002F2026-09\u002FSKILL-2026-09-27_pre-selfcheck.md",6212,"https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Fskill-metrics\u002F.arc\u002F2026-09\u002FSKILL-2026-09-27_pre-selfcheck.md",{"path":73,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":74,"sourceHtmlUrl":75},".arc\u002F2026-09\u002Fskill-manifest-2026-09-23_pre-header-pass",485,"https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Fskill-metrics\u002F.arc\u002F2026-09\u002Fskill-manifest-2026-09-23_pre-header-pass",{"path":77,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":78,"sourceHtmlUrl":79},".arc\u002F2026-09\u002Fskill-manifest-2026-09-24_162128Z_pre-manifest",730,"https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Fskill-metrics\u002F.arc\u002F2026-09\u002Fskill-manifest-2026-09-24_162128Z_pre-manifest",{"path":81,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":74,"sourceHtmlUrl":82},".arc\u002F2026-09\u002Fskill-manifest-2026-09-27_203835Z_pre-manifest","https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Fskill-metrics\u002F.arc\u002F2026-09\u002Fskill-manifest-2026-09-27_203835Z_pre-manifest",{"path":84,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":85},".arc\u002F2026-10\u002Fsignature-2026-10-10_104828Z_pre-manifest.asc","https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Fskill-metrics\u002F.arc\u002F2026-10\u002Fsignature-2026-10-10_104828Z_pre-manifest.asc",{"path":87,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":88,"sourceHtmlUrl":89},".arc\u002F2026-10\u002Fskill-manifest-2026-10-10_104828Z_pre-manifest",574,"https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Fskill-metrics\u002F.arc\u002F2026-10\u002Fskill-manifest-2026-10-10_104828Z_pre-manifest",{"path":91,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":92},".signature.asc","https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Fskill-metrics\u002F.signature.asc",{"path":94,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":88,"sourceHtmlUrl":95},".skill-manifest","https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Fskill-metrics\u002F.skill-manifest",{"path":97,"resourceType":98,"resourceTypeDesc":99,"sizeBytes":100,"sourceHtmlUrl":101},"scripts\u002Fsh1lib.sh","SCRIPT","脚本",2934,"https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Fskill-metrics\u002Fscripts\u002Fsh1lib.sh",{"path":103,"resourceType":98,"resourceTypeDesc":99,"sizeBytes":104,"sourceHtmlUrl":105},"scripts\u002Fsk2mt",13472,"https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Fskill-metrics\u002Fscripts\u002Fsk2mt",{"path":107,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":108,"sourceHtmlUrl":109},"SPEC.md",5579,"https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Fskill-metrics\u002FSPEC.md",{"path":111,"resourceType":98,"resourceTypeDesc":99,"sizeBytes":112,"sourceHtmlUrl":113},"tests.sh",6611,"https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Fskill-metrics\u002Ftests.sh",{"path":115,"resourceType":98,"resourceTypeDesc":99,"sizeBytes":116,"sourceHtmlUrl":117},"tests\u002Ftest_sh1lib.py",9562,"https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Fskill-metrics\u002Ftests\u002Ftest_sh1lib.py",{"path":119,"resourceType":98,"resourceTypeDesc":99,"sizeBytes":120,"sourceHtmlUrl":121},"tests\u002Ftest_spec.py",6893,"https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Fskill-metrics\u002Ftests\u002Ftest_spec.py",[123,129,135,142,149,156],{"skillNo":124,"name":125,"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":126,"categories":127,"keywords":128,"publishedAt":19},"01M7EPTX6X52ZPGVQZHKVJ7FAZ","alpha","https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Flane-d\u002Fbr1in\u002Fours\u002Fskills\u002Falpha\u002FSKILL.md",[],[],{"skillNo":130,"name":131,"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":132,"categories":133,"keywords":134,"publishedAt":19},"01M7EPTWCTS80QHFQ2ND3A1CW1","gamma","https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Flane-d\u002Fbr1in\u002Fours\u002FSOFT-SKILLS\u002Fgamma\u002FSKILL.md",[],[],{"skillNo":136,"name":137,"nameZh":6,"description":138,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":139,"categories":140,"keywords":141,"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":143,"name":144,"nameZh":6,"description":145,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":146,"categories":147,"keywords":148,"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":150,"name":151,"nameZh":6,"description":152,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":153,"categories":154,"keywords":155,"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":157,"name":158,"nameZh":6,"description":159,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":160,"categories":161,"keywords":162,"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",[],[]]