[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F90WV19MCWWJFESM2BNHNN":3,"skill-same:01M7F90WV19MCWWJFESM2BNHNN":47},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":31,"ownerHtmlUrl":32,"ownerBlogUrl":31,"ownerDescription":6,"updatedAt":33,"install":34,"resources":46},"01M7F90WV19MCWWJFESM2BNHNN","new-surface",null,"Add a surface: render the graph sub-agent and promote Surface + verification Rule + Check into the graph.","steepy-it\u002Fsteepy-formula","steepy-it","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F299579966?v=4","01M7F8VT4D9JWJZDQFATW4K3YB","Steepy","01M7F8VT4ZR70KR69DV1RR1Q8W",5,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fsteepy-it\u002Fsteepy-formula\u002Fblob\u002Fmain\u002Fskills\u002Fnew-surface\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: new-surface\ndescription: 'Add a surface: render the graph sub-agent and promote Surface + verification Rule + Check into the graph.'\nuser-invocable: true\nargument-hint: 'surface name and its path'\n---\n\n# new-surface\n\nAdd a surface: render the graph-mode sub-agent and promote the Surface into the canonical Stable\nKnowledge Graph — no standards doc and no routing table exist.\n\n> **Engine root:** this skill's base directory is `\u003Cengine-root>\u002Fskills\u002Fnew-surface\u002F`; engine\n> scripts live two levels up, at `\u003Cengine-root>\u002Fscripts\u002F`. Resolve them relative to the base\n> directory your harness reports for this skill.\n\n## Procedure\n\n1. **Gather inputs** — if the user has not provided all four pieces of information, ask for them before proceeding:\n   - **Surface name** — short, lowercase, hyphen-separated identifier (e.g. `api`, `admin-dashboard`).\n   - **Surface path** — workspace-relative path to the surface codebase (e.g. `apps\u002Fapi`).\n   - **Specialist agent** — semantic agent identifier, defaulting to `\u003Cname>-agent` only when the user accepts it.\n   - **Test command** — the command used to run tests for this surface (e.g. `vitest run`, `pytest`).\n\n2. **Declare the hub mode.** Run `steepy-formula hub-mode` and quote its `mode:` line —\n   `graph`, `migrate`, or `none`, each printed with one `evidence:` line. The command always\n   exits 0: it is a declaration, not a gate, and this prose never re-implements its detection —\n   the command is the single authority. The declared mode routes the rest of the run:\n\n   | Declared mode | Route |\n   |---------------|-------|\n   | `graph` | Continue with Steps 3–6 — the graph promotion; never create a standards doc. |\n   | `migrate` | Stop and tell the user to run the `graph-migrate` skill (invoke it the way your harness invokes skills) before any other workflow. |\n   | `none` | No hub to add a surface to — tell the user to run the `init` skill (invoke it the way your harness invokes skills) first, and stop. |\n\n3. **Render the specialist agent** — create `.claude\u002Fagents\u002F\u003Csurface-name>-agent.md` from the\n   graph-mode agent template `\u003Cengine-root>\u002Ftemplates\u002Fsurface-agent-graph.md` by substituting\n   `{{name}}` and `{{path}}` agent-side (refuse to overwrite an existing agent file — surface\n   the conflict to the user instead). That template's per-task guidance points the agent at\n   the deterministic surface target — `steepy-formula context resolve\n   --target apex:\u003CprojectId>:surface:\u003Cslug(name)>`, with `--path {{path}}` as the alternative\n   where a topology bridge exists — never at a standards doc, because there\n   is none. Binding is deterministic: surface `\u003Cname>` → agent file\n   `.claude\u002Fagents\u002F\u003Cname>-agent.md`.\n\n4. **Build the structural promotion scenario (nothing applied).** The shipped\n   `promotion create` command carries only typed knowledge candidates\n   (`term`\u002F`rule`\u002F`decision`\u002F`readme`) and cannot express a Surface — drive the shipped\n   structural-promotion helper instead; it works on an initialized graph (ADD operations whose\n   target already exists in the stable graph are skipped and reported, so only the genuinely\n   new nodes and edges ride the scenario). Write the surface into\n   `.formula\u002Fwork\u002Fnew-surface-\u003Csurface-name>.json` — a local, gitignored work artifact:\n\n   ```json\n   {\n     \"project\": { \"id\": \"\u003CprojectId>\" },\n     \"surfaces\": [\n       { \"name\": \"\u003Csurface-name>\", \"path\": \"\u003Csurface-path>\",\n         \"testCommand\": \"\u003Ctest-command>\" }\n     ]\n   }\n   ```\n\n   - `\u003CprojectId>` is the project id the Step 2 declaration echoed on its `project:` line\n     (the CLI's fixed resolution chain — in an initialized repo it comes from\n     `.formula\u002Fconfig.json`); the helper requires the file's `project.id` and its `--project`\n     flag to agree.\n   - `testCommand` is the test command the user confirmed in Step 1 — from it the helper\n     derives the surface's verification Rule (`APPLIES_TO` → the Surface) and its Check with\n     the command persisted as the `ext_v1_command` extension property (`VERIFIED_BY` from the\n     Rule). That property is where graph-aware skills read the surface's test command from the\n     resolved context.\n\n   Then create the draft scenario:\n\n   ```bash\n   node \u003Cengine-root>\u002Fscripts\u002Fstructural-promotion.mjs \\\n     --project \u003CprojectId> --port docker \\\n     --input .formula\u002Fwork\u002Fnew-surface-\u003Csurface-name>.json new-surface-\u003Csurface-name>\n   ```\n\n   The helper maps the input into plain ADD operations — the Surface (with `PART_OF` → the\n   Project root, whose own ADD is skipped as already present), the verification Rule with\n   `APPLIES_TO` → the Surface, and the Check with `ext_v1_command` and `VERIFIED_BY` — and\n   creates the DRAFT scenario through the core promotion lifecycle. Nothing is applied here;\n   record the scenario id it reports.\n\n5. **Preview and human gate.**\n\n   ```bash\n   steepy-formula promotion preview new-surface-\u003Csurface-name>\n   ```\n\n   The typed diff report IS the preview: show it to the user. Approval is explicit, never\n   assumed — one question with a clear yes\u002Fchange\u002Fno choice; never proceed on silence. On\n   **yes**, commit the transaction:\n\n   ```bash\n   steepy-formula promotion apply new-surface-\u003Csurface-name> --yes [--approver \u003Cname>]\n   ```\n\n   That yes IS the human gate, and the agent applies directly on it: pass `--yes` only after\n   the human's explicit yes, in an interactive session, for exactly the scenario just\n   previewed. A change re-previews and needs a new yes; a no applies nothing. The CLI refuses\n   (exit 20) an apply whose base revision moved after the preview. `--approver` names the\n   human who said yes (default: the OS user).\n\n6. **Verify** — run the graph coherence gate, then a resolver spot-check:\n\n   ```bash\n   steepy-formula graph validate\n   steepy-formula context resolve --target apex:\u003CprojectId>:surface:\u003Cslug(name)>\n   ```\n\n   `graph validate` must come back clean, and the resolved context must return the new\n   Surface, its verification Rule, and its Check carrying the approved test command as\n   `ext_v1_command`. (`--path \u003Csurface-path>` answers only where a topology bridge exists;\n   on a curated-only graph it exits 10 UNRESOLVED — expected, not a failure.) If either\n   gate fails, fix the graph before considering the task complete.\n","# new-surface\n\nAdd a surface: render the graph-mode sub-agent and promote the Surface into the canonical Stable\nKnowledge Graph — no standards doc and no routing table exist.\n\n> **Engine root:** this skill's base directory is `\u003Cengine-root>\u002Fskills\u002Fnew-surface\u002F`; engine\n> scripts live two levels up, at `\u003Cengine-root>\u002Fscripts\u002F`. Resolve them relative to the base\n> directory your harness reports for this skill.\n\n## Procedure\n\n1. **Gather inputs** — if the user has not provided all four pieces of information, ask for them before proceeding:\n   - **Surface name** — short, lowercase, hyphen-separated identifier (e.g. `api`, `admin-dashboard`).\n   - **Surface path** — workspace-relative path to the surface codebase (e.g. `apps\u002Fapi`).\n   - **Specialist agent** — semantic agent identifier, defaulting to `\u003Cname>-agent` only when the user accepts it.\n   - **Test command** — the command used to run tests for this surface (e.g. `vitest run`, `pytest`).\n\n2. **Declare the hub mode.** Run `steepy-formula hub-mode` and quote its `mode:` line —\n   `graph`, `migrate`, or `none`, each printed with one `evidence:` line. The command always\n   exits 0: it is a declaration, not a gate, and this prose never re-implements its detection —\n   the command is the single authority. The declared mode routes the rest of the run:\n\n   | Declared mode | Route |\n   |---------------|-------|\n   | `graph` | Continue with Steps 3–6 — the graph promotion; never create a standards doc. |\n   | `migrate` | Stop and tell the user to run the `graph-migrate` skill (invoke it the way your harness invokes skills) before any other workflow. |\n   | `none` | No hub to add a surface to — tell the user to run the `init` skill (invoke it the way your harness invokes skills) first, and stop. |\n\n3. **Render the specialist agent** — create `.claude\u002Fagents\u002F\u003Csurface-name>-agent.md` from the\n   graph-mode agent template `\u003Cengine-root>\u002Ftemplates\u002Fsurface-agent-graph.md` by substituting\n   `{{name}}` and `{{path}}` agent-side (refuse to overwrite an existing agent file — surface\n   the conflict to the user instead). That template's per-task guidance points the agent at\n   the deterministic surface target — `steepy-formula context resolve\n   --target apex:\u003CprojectId>:surface:\u003Cslug(name)>`, with `--path {{path}}` as the alternative\n   where a topology bridge exists — never at a standards doc, because there\n   is none. Binding is deterministic: surface `\u003Cname>` → agent file\n   `.claude\u002Fagents\u002F\u003Cname>-agent.md`.\n\n4. **Build the structural promotion scenario (nothing applied).** The shipped\n   `promotion create` command carries only typed knowledge candidates\n   (`term`\u002F`rule`\u002F`decision`\u002F`readme`) and cannot express a Surface — drive the shipped\n   structural-promotion helper instead; it works on an initialized graph (ADD operations whose\n   target already exists in the stable graph are skipped and reported, so only the genuinely\n   new nodes and edges ride the scenario). Write the surface into\n   `.formula\u002Fwork\u002Fnew-surface-\u003Csurface-name>.json` — a local, gitignored work artifact:\n\n   ```json\n   {\n     \"project\": { \"id\": \"\u003CprojectId>\" },\n     \"surfaces\": [\n       { \"name\": \"\u003Csurface-name>\", \"path\": \"\u003Csurface-path>\",\n         \"testCommand\": \"\u003Ctest-command>\" }\n     ]\n   }\n   ```\n\n   - `\u003CprojectId>` is the project id the Step 2 declaration echoed on its `project:` line\n     (the CLI's fixed resolution chain — in an initialized repo it comes from\n     `.formula\u002Fconfig.json`); the helper requires the file's `project.id` and its `--project`\n     flag to agree.\n   - `testCommand` is the test command the user confirmed in Step 1 — from it the helper\n     derives the surface's verification Rule (`APPLIES_TO` → the Surface) and its Check with\n     the command persisted as the `ext_v1_command` extension property (`VERIFIED_BY` from the\n     Rule). That property is where graph-aware skills read the surface's test command from the\n     resolved context.\n\n   Then create the draft scenario:\n\n   ```bash\n   node \u003Cengine-root>\u002Fscripts\u002Fstructural-promotion.mjs \\\n     --project \u003CprojectId> --port docker \\\n     --input .formula\u002Fwork\u002Fnew-surface-\u003Csurface-name>.json new-surface-\u003Csurface-name>\n   ```\n\n   The helper maps the input into plain ADD operations — the Surface (with `PART_OF` → the\n   Project root, whose own ADD is skipped as already present), the verification Rule with\n   `APPLIES_TO` → the Surface, and the Check with `ext_v1_command` and `VERIFIED_BY` — and\n   creates the DRAFT scenario through the core promotion lifecycle. Nothing is applied here;\n   record the scenario id it reports.\n\n5. **Preview and human gate.**\n\n   ```bash\n   steepy-formula promotion preview new-surface-\u003Csurface-name>\n   ```\n\n   The typed diff report IS the preview: show it to the user. Approval is explicit, never\n   assumed — one question with a clear yes\u002Fchange\u002Fno choice; never proceed on silence. On\n   **yes**, commit the transaction:\n\n   ```bash\n   steepy-formula promotion apply new-surface-\u003Csurface-name> --yes [--approver \u003Cname>]\n   ```\n\n   That yes IS the human gate, and the agent applies directly on it: pass `--yes` only after\n   the human's explicit yes, in an interactive session, for exactly the scenario just\n   previewed. A change re-previews and needs a new yes; a no applies nothing. The CLI refuses\n   (exit 20) an apply whose base revision moved after the preview. `--approver` names the\n   human who said yes (default: the OS user).\n\n6. **Verify** — run the graph coherence gate, then a resolver spot-check:\n\n   ```bash\n   steepy-formula graph validate\n   steepy-formula context resolve --target apex:\u003CprojectId>:surface:\u003Cslug(name)>\n   ```\n\n   `graph validate` must come back clean, and the resolved context must return the new\n   Surface, its verification Rule, and its Check carrying the approved test command as\n   `ext_v1_command`. (`--path \u003Csurface-path>` answers only where a topology bridge exists;\n   on a curated-only graph it exits 10 UNRESOLVED — expected, not a failure.) If either\n   gate fails, fix the graph before considering the task complete.\n",{"name":5,"description":7,"argument-hint":24,"user-invocable":25},"surface name and its path",true,"main","a5e0492607593191c2b0a1c603cf421996b5e22f","skills\u002Fnew-surface",0,"https:\u002F\u002Fgithub.com\u002Fsteepy-it\u002Fsteepy-formula","https:\u002F\u002Fwww.steepy.it","https:\u002F\u002Fgithub.com\u002Fsteepy-it","2026-10-27 16:48:08",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":25},[36,39,42],{"tool":37,"command":38},"npx","npx skills add steepy-it\u002Fsteepy-formula --skill new-surface",{"tool":40,"command":41},"bunx","bunx skills add steepy-it\u002Fsteepy-formula --skill new-surface",{"tool":43,"command":44},"pnpm","pnpm dlx skills add steepy-it\u002Fsteepy-formula --skill new-surface","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fsteepy-it\u002Fsteepy-formula\u002Fblob\u002Fmain\u002Fskills\u002Fnew-surface\u002FSKILL.md",[],[48,55,62,69,76,83],{"skillNo":49,"name":50,"nameZh":6,"description":51,"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},"01M7F91BV8VJM3DS4SA9ZMHMXB","web-check","Run the web surface checks.","https:\u002F\u002Fgithub.com\u002Fsteepy-it\u002Fsteepy-formula\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fgood-hub\u002F.claude\u002Fskills\u002Fweb-check\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M7F917VTJWS90304QDH1C3R8","review","Verify implemented work against its spec with real evidence before any \"done\" claim. Checks the spec's success criteria, runs the surface test command, and runs `steepy-formula graph validate` through the deterministic inline evidence capture.","https:\u002F\u002Fgithub.com\u002Fsteepy-it\u002Fsteepy-formula\u002Fblob\u002Fmain\u002Fskills\u002Freview\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M7F910RRMBN04529ZQZZW76Q","plan","Turn a local working spec into a step-by-step implementation plan. Each step names the owning surface and specialist agent and the surface test command; the plan is written into .formula\u002Fwork\u002Fplans\u002F as a gitignored work artifact.","https:\u002F\u002Fgithub.com\u002Fsteepy-it\u002Fsteepy-formula\u002Fblob\u002Fmain\u002Fskills\u002Fplan\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M7F90QA1DXYPVFD08V5HFYY1","loop-engineer","Validate and authorize a gear-4 goal contract, invoke the packaged deterministic loop controller, report its result, and hand off terminal evidence to review.","https:\u002F\u002Fgithub.com\u002Fsteepy-it\u002Fsteepy-formula\u002Fblob\u002Fmain\u002Fskills\u002Floop-engineer\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M7F90EZHJZKYXEWTJ3BWKWRK","init","Graph-first init — gate on a provisioned Stable Knowledge Graph before writing anything, interview the governed structure, scaffold the disk-minimal harness assets, and land the initial graph through a promotion scenario. Never invents Rules from stack detection.","https:\u002F\u002Fgithub.com\u002Fsteepy-it\u002Fsteepy-formula\u002Fblob\u002Fmain\u002Fskills\u002Finit\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M7F908EYQDZ71GA3TQZ0613E","inception","Turn an idea and its starting materials into a minimal, verified, runnable application before the graph binding exists — reconnaissance, architecture decisions, verified versions, one human approval, bootstrap of one representative path, and final verification — then hand off to init and discovery.","https:\u002F\u002Fgithub.com\u002Fsteepy-it\u002Fsteepy-formula\u002Fblob\u002Fmain\u002Fskills\u002Finception\u002FSKILL.md",[],[]]