[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75VBAXD8G41T4BPWRX2P94S":3,"skill-same:01M75VBAXD8G41T4BPWRX2P94S":46},{"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":30,"updatedAt":31,"install":32,"resources":45},"01M75VBAXD8G41T4BPWRX2P94S","glyphsteer",null,"Use when steering retrieval with hidden in-band glyph markers — an LLM annotates a corpus with a controlled emoji\u002Fglyph vocabulary that biases search (lexical facet + dense direction) but is stripped from returned text; also for grading a RAG corpus and searching with grade badges, and for authoring\u002Fpersisting a glyph \"legend\". Triggers on \"glyphsteer\", \"emoji annotation\", \"hidden retrieval markers\", \"steer RAG\", \"grade a corpus\", \"facet by sentiment\u002Fgrade\", \"glyph legend\", \"annotate corpus for search\".","sancovp\u002Fchaincompiler","sancovp","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F147458096?v=4","01M74F2EFE4Q0KF1Y5AY27HVNB","Isaac Wostrel-Rubin","01M75V171K7FNNX91AY22XG37A",0,"MIT","https:\u002F\u002Fgithub.com\u002Fsancovp\u002Fchaincompiler\u002Fblob\u002Fmain\u002Fskills\u002Fglyphsteer\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: glyphsteer\ndescription: Use when steering retrieval with hidden in-band glyph markers — an LLM annotates a corpus with a controlled emoji\u002Fglyph vocabulary that biases search (lexical facet + dense direction) but is stripped from returned text; also for grading a RAG corpus and searching with grade badges, and for authoring\u002Fpersisting a glyph \"legend\". Triggers on \"glyphsteer\", \"emoji annotation\", \"hidden retrieval markers\", \"steer RAG\", \"grade a corpus\", \"facet by sentiment\u002Fgrade\", \"glyph legend\", \"annotate corpus for search\".\n---\n\n# GlyphSteer — how to use it\n\nDual-regime retrieval steering via **compiled in-band glyph annotations**. An LLM writes a\ncontrolled glyph vocabulary onto a corpus; the markers steer retrieval and then **vanish\nfrom the output**. Package: `glyphsteer`, with its `grammar` extra for the syntax gate. It is HoneyC pointed at the\nindex — a glyph code is a HoneyC chain — and a cousin of Anthropic's Contextual Retrieval (the embedded form differs\nfrom the displayed form), with a compiled, controlled vocabulary in place of free text.\n\n**Run its Python** from a plugin install with `uv run --no-project --with \"glyphsteer[grammar]==0.3.6\" --with \"agent-skilltree>=0.4.0\" python3` — pipe a block in as `python3 - \u003C\u003C'PY'` … `PY` — and from a clone of the public repository where `.\u002Finstall.sh` ran, with the clone's `python3`.\n\n**Run `glyphsteer`** from a plugin install as `uvx --from glyphsteer==0.3.6 glyphsteer …`, and from a clone where `.\u002Finstall.sh` ran, as `glyphsteer …` in the environment it installed into.\n\n**Run `skilltree`** from a plugin install as `uvx --from \"agent-skilltree>=0.4.0\" skilltree …`, and from a clone where `.\u002Finstall.sh` ran, as `skilltree …` in the environment it installed into.\n\n> A `packages\u002F...` path below is in a clone of the public repository: run it from the clone's\n> root (`...\u002Fchaincompiler`).\n\n## The mental model (3 facts)\n\n1. **Sidecar split** — a chunk has two representations that need not match:\n   `indexed-form = clean ⊕ glyph_code` (what gets matched) vs `returned-form = clean`\n   (what the reader sees). The marker steers findability, then disappears.\n2. **One axis, two renderings** — FTS5's tokenizer **drops emoji**, so each axis carries\n   BOTH: a **glyph** (emoji = the *dense* marker, a learned direction) AND a **tag** (ASCII\n   sentinel like `gsxnegative` = the *lexical* marker, a rare max-IDF facet). You facet with\n   the glyph; the library resolves it to its tag internally.\n3. **The vocabulary is the gate** — annotation only counts if the glyph is in the vocab;\n   unknown glyphs are dropped (syntax-only discipline, like the `*CC` compilers).\n\n## Quickstart — annotate, index, facet, return clean (zero deps)\n\n```python\nfrom glyphsteer import SENTIMENT, Chunk, RuleAnnotator, annotate_chunk, build_index, search\n\ncorpus = [Chunk(\"a\", \"the deploy pipeline passed and works great\"),\n          Chunk(\"b\", \"the deploy pipeline crashed, this is broken and terrible\")]\n\nann = RuleAnnotator.keyword(SENTIMENT, {\n    SENTIMENT.by_name(\"positive\").glyph: [\"great\", \"works\", \"passed\"],\n    SENTIMENT.by_name(\"negative\").glyph: [\"broken\", \"terrible\", \"crashed\"],\n})\nchunks = [annotate_chunk(c, ann, SENTIMENT) for c in corpus]   # attaches the glyph code\ncon = build_index(chunks, SENTIMENT)                            # 2nd arg = the vocab\nneg = SENTIMENT.by_name(\"negative\").glyph\nhits = search(con, \"deploy\", facet=neg, vocab=SENTIMENT)       # facet by a glyph\nprint(hits[0][\"text\"])   # CLEAN text — the glyph is NOT in it (the hide)\n```\n\nKey calls: `annotate_chunk(chunk, annotator, vocab)` · `build_index(chunks, vocab)` ·\n`search(con, query, facet=glyph, vocab=...)` · `facet_only(con, glyph, vocab=...)`.\nThe hide invariant: `from glyphsteer import check_hidden; assert check_hidden(chunk, vocab)`.\nFrom the shell, over a JSONL corpus: `glyphsteer vocab` (the sentiment vocabulary) ·\n`glyphsteer annotate corpus.jsonl -k 😡=failed,broke` · `glyphsteer query corpus.jsonl \"deployment\" -f 😡`.\n\n## Grade a corpus, search shows grades (the flagship)\n\n`GRADE` is a built-in quality vocabulary (🏆 excellent \u002F ✅ good \u002F ⚠️ fair \u002F ❌ poor). An LLM\ngrades each chunk; search returns the grade badge and can facet to a grade.\n\n```python\nfrom glyphsteer import GRADE, GRADE_RANK, Chunk, build_index, search, grade_label\nfrom glyphsteer.index import facet_only\nEXC, POOR = GRADE.by_name(\"excellent\").glyph, GRADE.by_name(\"poor\").glyph\ncorpus = [Chunk(\"c1\", \"use parameterized queries to prevent SQL injection\", code=EXC),\n          Chunk(\"c2\", \"just concatenate user input into the SQL string\", code=POOR)]\ncon = build_index(corpus, GRADE)\nfor h in search(con, \"SQL\", vocab=GRADE):\n    print(grade_label(GRADE, h[\"code\"]), h[\"text\"])     # badge + clean text\naudit = facet_only(con, POOR, vocab=GRADE)              # the \"what's bad\" view\n```\nGrading rides the **lexical** regime — a grade is a filter\u002Fdisplay label, NOT a semantic\ndirection (quality ≠ sentiment: a correct chunk can be grim, an upbeat one can be junk).\nRunnable demo, from a clone: `python3 packages\u002Fglyphsteer\u002Fexperiments\u002Fgrade_demo.py`.\n\n## Author your own glyph language + keep a legend\n\nAn LLM can invent its own vocabulary, persist it, and accumulate a master legend.\n\n```python\nfrom glyphsteer import author, save_legend, load_legend, merge, render_legend\nV = author([                                   # tags auto-derived; raises on collision\n    {\"name\": \"claim\",    \"glyph\": \"📌\", \"description\": \"a factual assertion\"},\n    {\"name\": \"evidence\", \"glyph\": \"🔬\", \"description\": \"supporting data\"},\n])\nsave_legend(V, \"legend.json\")                  # persist the glyph↔meaning↔tag table\nV2 = load_legend(\"legend.json\")\nmaster = merge(V, author([{\"name\": \"risk\", \"glyph\": \"☢️\"}]))   # last-author-wins\nprint(render_legend(master))\n```\n\n## Wire it into ChainCompiler's skill search\n\n`skilltree.search` facets the skill corpus by glyph (SkillTree is `agent-skilltree`, which\nthe uv line above names). **The legend you pass MUST contain the\nglyph you facet on** — here we use the built-in `GRADE` vocab (which defines 🏆) and save it\nas the legend. Put `glyphs: 🏆` in a SKILL.md's frontmatter, then:\n\n```python\nfrom skilltree.search import build_index, search\nfrom glyphsteer import GRADE, save_legend\nsave_legend(GRADE, \"grade_legend.json\")                   # the facet glyph (🏆) lives here\ncon = build_index(\"path\u002Fto\u002Fskill\u002Ftree\", vocab=GRADE)      # reads `glyphs:` frontmatter → tags\ntrusted = search(con, \"deploy\", facet=\"🏆\", vocab=GRADE)   # only 🏆-graded skills; badge returned\n```\nCLI: `skilltree search ROOT \"query\" --facet 🏆 --legend grade_legend.json`.\n(Facet on any glyph defined in the legend — your own authored vocab works the same way.)\n\n## Syntax consistency (rulecatcher under it)\n\nA glyph code is a little DSL, so it goes through ChainCompiler's lint\u002Fgate engine\n(**rulecatcher**, via `chaincompiler.bridge`) — the same gate the `*CC` compilers use; the\n`grammar` extra brings ChainCompiler and rulecatcher (the uv line above names it). Three verdicts:\n`ok` · `orthogonal` (known glyphs, wrong order → steerable) · `syntax_break` (foreign token → fatal).\n\n```python\nfrom glyphsteer import GlyphGrammar, SENTIMENT\nwith GlyphGrammar(SENTIMENT) as gg:\n    gg.lint(SENTIMENT.code([SENTIMENT.by_name(\"positive\").glyph,\n                            SENTIMENT.by_name(\"urgent\").glyph])).verdict   # \"ok\"\n    lint = gg.lint(\"🔥😊\")           # urgent before positive\n    lint.verdict, lint.fix          # \"orthogonal\", \"😊🔥\"  (canonical reorder)\n    gg.lint_chain(\"gsxpositive -> gsxbogus\").verdict                       # \"syntax_break\"\n```\nGating is over the ASCII **tag** rendering (rulecatcher drops emoji, same as FTS5), so `lint`\nfirst refuses, as `syntax_break`, whatever in a code is neither a vocabulary glyph nor the\nseparator — an unknown glyph, a word — and names it. Pass a grammar to annotation to auto-canonicalize: `annotate_chunk(chunk, ann, vocab, grammar=gg)`\n(reorders `orthogonal`, raises on `syntax_break`).\n\n## Dense regime\nThe emoji-direction half needs an embedding model and has caveats (some models collapse all\nemoji to one token). See the **glyphsteer-dense** skill before using it.\n\n## Verify your understanding (run this, from a clone of the public repository where `.\u002Finstall.sh` ran)\n```bash\npython3 packages\u002Fglyphsteer\u002Fexperiments\u002Fgrade_demo.py\npython3 -m pytest packages\u002Fglyphsteer -q\n```\nFull design, in the clone: `packages\u002Fglyphsteer\u002Fimplementation_plan.md`.\n","# GlyphSteer — how to use it\n\nDual-regime retrieval steering via **compiled in-band glyph annotations**. An LLM writes a\ncontrolled glyph vocabulary onto a corpus; the markers steer retrieval and then **vanish\nfrom the output**. Package: `glyphsteer`, with its `grammar` extra for the syntax gate. It is HoneyC pointed at the\nindex — a glyph code is a HoneyC chain — and a cousin of Anthropic's Contextual Retrieval (the embedded form differs\nfrom the displayed form), with a compiled, controlled vocabulary in place of free text.\n\n**Run its Python** from a plugin install with `uv run --no-project --with \"glyphsteer[grammar]==0.3.6\" --with \"agent-skilltree>=0.4.0\" python3` — pipe a block in as `python3 - \u003C\u003C'PY'` … `PY` — and from a clone of the public repository where `.\u002Finstall.sh` ran, with the clone's `python3`.\n\n**Run `glyphsteer`** from a plugin install as `uvx --from glyphsteer==0.3.6 glyphsteer …`, and from a clone where `.\u002Finstall.sh` ran, as `glyphsteer …` in the environment it installed into.\n\n**Run `skilltree`** from a plugin install as `uvx --from \"agent-skilltree>=0.4.0\" skilltree …`, and from a clone where `.\u002Finstall.sh` ran, as `skilltree …` in the environment it installed into.\n\n> A `packages\u002F...` path below is in a clone of the public repository: run it from the clone's\n> root (`...\u002Fchaincompiler`).\n\n## The mental model (3 facts)\n\n1. **Sidecar split** — a chunk has two representations that need not match:\n   `indexed-form = clean ⊕ glyph_code` (what gets matched) vs `returned-form = clean`\n   (what the reader sees). The marker steers findability, then disappears.\n2. **One axis, two renderings** — FTS5's tokenizer **drops emoji**, so each axis carries\n   BOTH: a **glyph** (emoji = the *dense* marker, a learned direction) AND a **tag** (ASCII\n   sentinel like `gsxnegative` = the *lexical* marker, a rare max-IDF facet). You facet with\n   the glyph; the library resolves it to its tag internally.\n3. **The vocabulary is the gate** — annotation only counts if the glyph is in the vocab;\n   unknown glyphs are dropped (syntax-only discipline, like the `*CC` compilers).\n\n## Quickstart — annotate, index, facet, return clean (zero deps)\n\n```python\nfrom glyphsteer import SENTIMENT, Chunk, RuleAnnotator, annotate_chunk, build_index, search\n\ncorpus = [Chunk(\"a\", \"the deploy pipeline passed and works great\"),\n          Chunk(\"b\", \"the deploy pipeline crashed, this is broken and terrible\")]\n\nann = RuleAnnotator.keyword(SENTIMENT, {\n    SENTIMENT.by_name(\"positive\").glyph: [\"great\", \"works\", \"passed\"],\n    SENTIMENT.by_name(\"negative\").glyph: [\"broken\", \"terrible\", \"crashed\"],\n})\nchunks = [annotate_chunk(c, ann, SENTIMENT) for c in corpus]   # attaches the glyph code\ncon = build_index(chunks, SENTIMENT)                            # 2nd arg = the vocab\nneg = SENTIMENT.by_name(\"negative\").glyph\nhits = search(con, \"deploy\", facet=neg, vocab=SENTIMENT)       # facet by a glyph\nprint(hits[0][\"text\"])   # CLEAN text — the glyph is NOT in it (the hide)\n```\n\nKey calls: `annotate_chunk(chunk, annotator, vocab)` · `build_index(chunks, vocab)` ·\n`search(con, query, facet=glyph, vocab=...)` · `facet_only(con, glyph, vocab=...)`.\nThe hide invariant: `from glyphsteer import check_hidden; assert check_hidden(chunk, vocab)`.\nFrom the shell, over a JSONL corpus: `glyphsteer vocab` (the sentiment vocabulary) ·\n`glyphsteer annotate corpus.jsonl -k 😡=failed,broke` · `glyphsteer query corpus.jsonl \"deployment\" -f 😡`.\n\n## Grade a corpus, search shows grades (the flagship)\n\n`GRADE` is a built-in quality vocabulary (🏆 excellent \u002F ✅ good \u002F ⚠️ fair \u002F ❌ poor). An LLM\ngrades each chunk; search returns the grade badge and can facet to a grade.\n\n```python\nfrom glyphsteer import GRADE, GRADE_RANK, Chunk, build_index, search, grade_label\nfrom glyphsteer.index import facet_only\nEXC, POOR = GRADE.by_name(\"excellent\").glyph, GRADE.by_name(\"poor\").glyph\ncorpus = [Chunk(\"c1\", \"use parameterized queries to prevent SQL injection\", code=EXC),\n          Chunk(\"c2\", \"just concatenate user input into the SQL string\", code=POOR)]\ncon = build_index(corpus, GRADE)\nfor h in search(con, \"SQL\", vocab=GRADE):\n    print(grade_label(GRADE, h[\"code\"]), h[\"text\"])     # badge + clean text\naudit = facet_only(con, POOR, vocab=GRADE)              # the \"what's bad\" view\n```\nGrading rides the **lexical** regime — a grade is a filter\u002Fdisplay label, NOT a semantic\ndirection (quality ≠ sentiment: a correct chunk can be grim, an upbeat one can be junk).\nRunnable demo, from a clone: `python3 packages\u002Fglyphsteer\u002Fexperiments\u002Fgrade_demo.py`.\n\n## Author your own glyph language + keep a legend\n\nAn LLM can invent its own vocabulary, persist it, and accumulate a master legend.\n\n```python\nfrom glyphsteer import author, save_legend, load_legend, merge, render_legend\nV = author([                                   # tags auto-derived; raises on collision\n    {\"name\": \"claim\",    \"glyph\": \"📌\", \"description\": \"a factual assertion\"},\n    {\"name\": \"evidence\", \"glyph\": \"🔬\", \"description\": \"supporting data\"},\n])\nsave_legend(V, \"legend.json\")                  # persist the glyph↔meaning↔tag table\nV2 = load_legend(\"legend.json\")\nmaster = merge(V, author([{\"name\": \"risk\", \"glyph\": \"☢️\"}]))   # last-author-wins\nprint(render_legend(master))\n```\n\n## Wire it into ChainCompiler's skill search\n\n`skilltree.search` facets the skill corpus by glyph (SkillTree is `agent-skilltree`, which\nthe uv line above names). **The legend you pass MUST contain the\nglyph you facet on** — here we use the built-in `GRADE` vocab (which defines 🏆) and save it\nas the legend. Put `glyphs: 🏆` in a SKILL.md's frontmatter, then:\n\n```python\nfrom skilltree.search import build_index, search\nfrom glyphsteer import GRADE, save_legend\nsave_legend(GRADE, \"grade_legend.json\")                   # the facet glyph (🏆) lives here\ncon = build_index(\"path\u002Fto\u002Fskill\u002Ftree\", vocab=GRADE)      # reads `glyphs:` frontmatter → tags\ntrusted = search(con, \"deploy\", facet=\"🏆\", vocab=GRADE)   # only 🏆-graded skills; badge returned\n```\nCLI: `skilltree search ROOT \"query\" --facet 🏆 --legend grade_legend.json`.\n(Facet on any glyph defined in the legend — your own authored vocab works the same way.)\n\n## Syntax consistency (rulecatcher under it)\n\nA glyph code is a little DSL, so it goes through ChainCompiler's lint\u002Fgate engine\n(**rulecatcher**, via `chaincompiler.bridge`) — the same gate the `*CC` compilers use; the\n`grammar` extra brings ChainCompiler and rulecatcher (the uv line above names it). Three verdicts:\n`ok` · `orthogonal` (known glyphs, wrong order → steerable) · `syntax_break` (foreign token → fatal).\n\n```python\nfrom glyphsteer import GlyphGrammar, SENTIMENT\nwith GlyphGrammar(SENTIMENT) as gg:\n    gg.lint(SENTIMENT.code([SENTIMENT.by_name(\"positive\").glyph,\n                            SENTIMENT.by_name(\"urgent\").glyph])).verdict   # \"ok\"\n    lint = gg.lint(\"🔥😊\")           # urgent before positive\n    lint.verdict, lint.fix          # \"orthogonal\", \"😊🔥\"  (canonical reorder)\n    gg.lint_chain(\"gsxpositive -> gsxbogus\").verdict                       # \"syntax_break\"\n```\nGating is over the ASCII **tag** rendering (rulecatcher drops emoji, same as FTS5), so `lint`\nfirst refuses, as `syntax_break`, whatever in a code is neither a vocabulary glyph nor the\nseparator — an unknown glyph, a word — and names it. Pass a grammar to annotation to auto-canonicalize: `annotate_chunk(chunk, ann, vocab, grammar=gg)`\n(reorders `orthogonal`, raises on `syntax_break`).\n\n## Dense regime\nThe emoji-direction half needs an embedding model and has caveats (some models collapse all\nemoji to one token). See the **glyphsteer-dense** skill before using it.\n\n## Verify your understanding (run this, from a clone of the public repository where `.\u002Finstall.sh` ran)\n```bash\npython3 packages\u002Fglyphsteer\u002Fexperiments\u002Fgrade_demo.py\npython3 -m pytest packages\u002Fglyphsteer -q\n```\nFull design, in the clone: `packages\u002Fglyphsteer\u002Fimplementation_plan.md`.\n",{"name":5,"description":7},"main","5117640090da92f427e1e21b431cfb53e7a3fb13","skills\u002Fglyphsteer","https:\u002F\u002Fgithub.com\u002Fsancovp\u002Fchaincompiler","https:\u002F\u002Fgithub.com\u002Fsancovp","https:\u002F\u002Fisaacwr.carrd.co\u002F","AKA Olivus Victory-Promise\r\n\r\nAI Agents, Tools, and Infrastructure","2026-11-13 21:35:40",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add sancovp\u002Fchaincompiler --skill glyphsteer",{"tool":38,"command":39},"bunx","bunx skills add sancovp\u002Fchaincompiler --skill glyphsteer",{"tool":41,"command":42},"pnpm","pnpm dlx skills add sancovp\u002Fchaincompiler --skill glyphsteer","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fsancovp\u002Fchaincompiler\u002Fblob\u002Fmain\u002Fskills\u002Fglyphsteer\u002FSKILL.md",true,[],[47,54,61,68,75,82],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":19},"01M75VCHMSPK8F1DNMR01SH2NJ","skill2framework","Turn an already-built AIOS\u002Fpackage into a framework chapter — narrative blog + deep-dive blog → chapter → {aios}-volume index skill → plugin → folded into the author's SkillTome.","https:\u002F\u002Fgithub.com\u002Fsancovp\u002Fchaincompiler\u002Fblob\u002Fmain\u002Fskills\u002Fskill2framework\u002Fskill2framework\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":57,"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},"01M75VCDVAZBN85DC6V38A7Y8Z","package-plugin","WHAT: package a framework as a Claude Code PLUGIN (its operational face) — run skill2framework.package_plugin to assemble plugin.json + skills\u002F{aios}-volume\u002FSKILL.md + the chapter bundled under resources\u002F, with the skill's chapter links repathed to the bundle. WHEN: when a framework skill + chapter exist and need the installable plugin, or when the user says package the framework \u002F plugin \u002F skill2framework (any of).","https:\u002F\u002Fgithub.com\u002Fsancovp\u002Fchaincompiler\u002Fblob\u002Fmain\u002Fskills\u002Fskill2framework\u002Fpackage-plugin\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M75VC9VRVDQ2PAT69P8PNB7G","narrative-blog","WHAT: produce Blog 1 of a framework CHAPTER — the narrative chapter-opener — for an already-built AIOS\u002Fpackage by reconstructing its journey from its own dir (CLAUDE.md, README, dev log) and FILLING skill2framework.JourneyCore, then rendering with render_blog1 (never hand-write the blog). WHEN: when making a framework\u002Fchapter from something already built, when you need the story post that opens a chapter, or when the user says blog organ \u002F narrative blog \u002F skill2framework (any of).","https:\u002F\u002Fgithub.com\u002Fsancovp\u002Fchaincompiler\u002Fblob\u002Fmain\u002Fskills\u002Fskill2framework\u002Fnarrative-blog\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M75VC59SRRK5DZEWRZQV6SFW","framework-skill","WHAT: generate the FRAMEWORK SKILL for an already-built AIOS — the {aios}-volume (its SkillVolume face): one skill that indexes the AIOS's skills + rules + how they relate (as a diagram), gives a decision tree for what to do when, and ROUTES the agent into the AIOS dir. WHEN: when producing the index\u002Frouter face of a framework package, or when the user says framework skill \u002F volume \u002F skill2framework (any of).","https:\u002F\u002Fgithub.com\u002Fsancovp\u002Fchaincompiler\u002Fblob\u002Fmain\u002Fskills\u002Fskill2framework\u002Fframework-skill\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M75VC0VS9AMREV5RMBVZ0RQK","fold-into-tome","WHAT: the TERMINAL stage — fold a finished framework into the author's SkillTome (the top-level holder + search of all their frameworks) by running skill2framework.fold_into_tome, which registers the framework as a row on a tome volume node's generated ## Frameworks table via skilltree's bind op. WHEN: when a framework package is finished and must be registered in the author's tome\u002Fvolume, or when the user says fold into the tome \u002F nomicon \u002F skill2framework fold (any of).","https:\u002F\u002Fgithub.com\u002Fsancovp\u002Fchaincompiler\u002Fblob\u002Fmain\u002Fskills\u002Fskill2framework\u002Ffold-into-tome\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M75VBWYNPC80Y0HJC6WQKGQD","deepdive-blog","WHAT: produce Blog 2 of a framework CHAPTER — the mechanical deep-dive ('how it actually works') — for an already-built AIOS\u002Fpackage by reading its impl docs (README architecture sections, design docs, the code's module docstrings) and assembling a faithful mechanics-only article that links back to Blog 1. WHEN: when producing the deep-dive half of a chapter, when you need the technical how-it-works post Blog 1 links to, or when the user says blog 2 \u002F deep dive \u002F skill2framework (any of).","https:\u002F\u002Fgithub.com\u002Fsancovp\u002Fchaincompiler\u002Fblob\u002Fmain\u002Fskills\u002Fskill2framework\u002Fdeepdive-blog\u002FSKILL.md",[],[]]