[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DF9FFAAA2GKHYPA3YS0D03":3,"skill-same:01M7DF9FFAAA2GKHYPA3YS0D03":76},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":20,"frontMatter":21,"refName":22,"commitSha":23,"skillDirectory":24,"forksCount":13,"repositoryHtmlUrl":25,"repositoryHomepageUrl":6,"ownerHtmlUrl":26,"ownerBlogUrl":27,"ownerDescription":28,"updatedAt":29,"install":30,"resources":43},"01M7DF9FFAAA2GKHYPA3YS0D03","agent-asset-authoring",null,"hazeliscoding\u002Faxiomarium","hazeliscoding","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F23608664?v=4","01M7DF4EBP9VTZCZQF6H21P07B","Hazel Granados","01M7DF4ECQBAXTHVFKYWBRZ16Q",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhazeliscoding\u002Faxiomarium\u002Fblob\u002Fmain\u002Fskills\u002Fagent-asset-authoring\u002Fskill.md",[],[],"2026-11-15 14:19:17",false,"# Agent asset authoring\n\nYou're adding or changing an asset in an Axiomarium vault. An asset is one folder with a manifest, `asset.yaml`, and one Markdown content file. `axm validate` checks everything below, so follow it and the asset passes the first time.\n\n## Before you write\n\nEach of these questions can mean the asset shouldn't exist. Answer them first.\n\n- **Could tooling enforce it instead?** A test, a lint rule, a database constraint, a pre-commit hook or a CI check beats an instruction the model may ignore. When one could, tell the user which one before you write anything, even if you write the asset too.\n- **Does an asset already cover it?** Run `axm list`, and extend the existing asset instead of adding a near-duplicate.\n- **For a skill:** when exactly should it activate? If you can't say it in one sentence, it will fire at the wrong time.\n- **For a hook:** should it block, warn or only gather evidence? Prefer warning. Block only destructive actions.\n- **For a policy:** what enforces each rule? If nothing does, say so rather than pretend.\n\n## Pick the kind\n\n| Kind | Folder | Content file | Block in `asset.yaml` |\n|---|---|---|---|\n| agent: a specialist with its own instructions | `agents\u002F` | `agent.md` | none |\n| skill: knowledge the model loads when relevant | `skills\u002F` | `skill.md` | `skill`: `use_when` |\n| hook: runs when the harness hits an event | `hooks\u002F` | `hook.md` | `hook`: `event`, `command`, `response` |\n| policy: rules for which decisions go where | `policies\u002F` | `policy.md` | `policy`: `rules` |\n| workflow: steps across several assets | `workflows\u002F` | `workflow.md` | none |\n| experiment: a hypothesis and its method | `experiments\u002F` | `experiment.md` | none |\n\nThe folder is `\u003Ckind folder>\u002F\u003Cname>\u002F`, and the name is kebab-case. Create the folder with the asset, never as an empty placeholder.\n\n## Write the manifest\n\n```yaml\n# yaml-language-server: $schema=..\u002F..\u002Fschemas\u002Fasset.schema.json\nname: release-notes\nkind: skill\nversion: 0.1.0\ndescription: >-\n  Writes release notes from merged pull requests, grouped by user-visible change.\nmaturity: experimental\nsupports:\n  claude-code: experimental\n  generic: full\npermissions:\n  filesystem: read\n  shell: read-only\n  network: none\nside_effects: none\ninputs:\n  - merged-pull-requests\noutputs:\n  - release-notes\nevals:\n  trigger: false\n  behavioral: false\n  regression: false\nskill:\n  use_when: >-\n    Preparing a release, or asked to summarize what changed since the last tag.\n```\n\n- **name** matches the folder, and **kind** matches the kind folder.\n- **version** is SemVer, starting at `0.1.0`. Bump it when the asset's behavior changes. Quote any version that YAML would read as a number, such as `\"1.0\"`.\n- **description** says what the asset does, in one or two sentences.\n- **maturity** starts at `experimental`. Raise it only when the evidence `registry\u002Fmaturity.yaml` requires exists: usage entries in `docs\u002Fdogfooding.md` that link to the asset, and eval files. `axm validate` fails a claim without its evidence.\n- **supports** lists the harnesses the asset is meant for: `experimental` while it's unproven there, `partial` once it works with known gaps, `full` once it works as intended. `generic` means the content works as plain instructions anywhere.\n- **permissions** and **side_effects** state the most the asset needs and the worst it can change. Don't round down.\n- **inputs** and **outputs** are kebab-case nouns.\n- **evals**: set a flag to `true` only when the asset's `evals\u002F\u003Ctype>\u002F` folder has files.\n- **The block** for skills, hooks and policies:\n  - a skill's `use_when` is the activation sentence from above;\n  - a hook has an `event` (`session-start`, `before-edit` or `after-edit`), the `command` the harness runs, and a `response` (`block`, `warn` or `evidence`);\n  - a policy has `rules`, each with a kebab-case `id`, the `rule` in one sentence, and `enforced_by`: the asset folders that enforce it, or `[]` when nothing does yet.\n\nYAML is read with the 1.2 core schema, so `yes` and `on` are strings, not booleans.\n\n## Write the content\n\n- Address the agent that will read it: \"You review…\", \"When you write code that…\".\n- Cover when to use it, what to do, what to produce, and the rules. Cut everything else: the content costs context every time it loads.\n- Keep it vendor neutral. Never put harness files such as `.claude\u002F`, `.agents\u002F` or `.github\u002F` in the asset; adapters generate those.\n\n## Check it\n\nRun `axm validate`. Each error names the file, the line and the field, with the allowed values or the missing evidence. Fix it and run it again until it reports 0 errors, then check that `axm list` shows the asset.\n",{},"main","861fae887ada469d0bc15da404ddb640e4369de8","skills\u002Fagent-asset-authoring","https:\u002F\u002Fgithub.com\u002Fhazeliscoding\u002Faxiomarium","https:\u002F\u002Fgithub.com\u002Fhazeliscoding","https:\u002F\u002Fhazeliscoding.dev\u002F","Full-stack .NET dev (she\u002Fthey) | Clean code, scalable systems, and cozy vibes 💻✨","2026-10-06 12:10:38",{"source":7,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add hazeliscoding\u002Faxiomarium --skill agent-asset-authoring",{"tool":36,"command":37},"bunx","bunx skills add hazeliscoding\u002Faxiomarium --skill agent-asset-authoring",{"tool":39,"command":40},"pnpm","pnpm dlx skills add hazeliscoding\u002Faxiomarium --skill agent-asset-authoring","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhazeliscoding\u002Faxiomarium\u002Fblob\u002Fmain\u002Fskills\u002Fagent-asset-authoring\u002Fskill.md",true,[44,50,54,58,62,65,69,72],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"asset.yaml","REFERENCE","参考文档",822,"https:\u002F\u002Fgithub.com\u002Fhazeliscoding\u002Faxiomarium\u002Fblob\u002Fmain\u002Fskills\u002Fagent-asset-authoring\u002Fasset.yaml",{"path":51,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":52,"sourceHtmlUrl":53},"evals\u002Fbehavioral\u002Fnew-hook\u002Feval.yaml",653,"https:\u002F\u002Fgithub.com\u002Fhazeliscoding\u002Faxiomarium\u002Fblob\u002Fmain\u002Fskills\u002Fagent-asset-authoring\u002Fevals\u002Fbehavioral\u002Fnew-hook\u002Feval.yaml",{"path":55,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":56,"sourceHtmlUrl":57},"evals\u002Fbehavioral\u002Fnew-hook\u002Frepo\u002FREADME.md",54,"https:\u002F\u002Fgithub.com\u002Fhazeliscoding\u002Faxiomarium\u002Fblob\u002Fmain\u002Fskills\u002Fagent-asset-authoring\u002Fevals\u002Fbehavioral\u002Fnew-hook\u002Frepo\u002FREADME.md",{"path":59,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":60,"sourceHtmlUrl":61},"evals\u002Fbehavioral\u002Fnew-skill\u002Feval.yaml",555,"https:\u002F\u002Fgithub.com\u002Fhazeliscoding\u002Faxiomarium\u002Fblob\u002Fmain\u002Fskills\u002Fagent-asset-authoring\u002Fevals\u002Fbehavioral\u002Fnew-skill\u002Feval.yaml",{"path":63,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":56,"sourceHtmlUrl":64},"evals\u002Fbehavioral\u002Fnew-skill\u002Frepo\u002FREADME.md","https:\u002F\u002Fgithub.com\u002Fhazeliscoding\u002Faxiomarium\u002Fblob\u002Fmain\u002Fskills\u002Fagent-asset-authoring\u002Fevals\u002Fbehavioral\u002Fnew-skill\u002Frepo\u002FREADME.md",{"path":66,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":67,"sourceHtmlUrl":68},"evals\u002Fbehavioral\u002Fprefers-tooling\u002Feval.yaml",565,"https:\u002F\u002Fgithub.com\u002Fhazeliscoding\u002Faxiomarium\u002Fblob\u002Fmain\u002Fskills\u002Fagent-asset-authoring\u002Fevals\u002Fbehavioral\u002Fprefers-tooling\u002Feval.yaml",{"path":70,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":56,"sourceHtmlUrl":71},"evals\u002Fbehavioral\u002Fprefers-tooling\u002Frepo\u002FREADME.md","https:\u002F\u002Fgithub.com\u002Fhazeliscoding\u002Faxiomarium\u002Fblob\u002Fmain\u002Fskills\u002Fagent-asset-authoring\u002Fevals\u002Fbehavioral\u002Fprefers-tooling\u002Frepo\u002FREADME.md",{"path":73,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":74,"sourceHtmlUrl":75},"evals\u002Ftrigger\u002Fprompts.yaml",3439,"https:\u002F\u002Fgithub.com\u002Fhazeliscoding\u002Faxiomarium\u002Fblob\u002Fmain\u002Fskills\u002Fagent-asset-authoring\u002Fevals\u002Ftrigger\u002Fprompts.yaml",[77,83,89,94,99,106],{"skillNo":78,"name":79,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":18},"01M7DF9HAHB9WKTF8FPCJ2WW6D","deploy","https:\u002F\u002Fgithub.com\u002Fhazeliscoding\u002Faxiomarium\u002Fblob\u002Fmain\u002Ftests\u002FAxiomarium.Tests\u002FFixtures\u002Ftriggers\u002Fvault\u002Fskills\u002Fdeploy\u002Fskill.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":18},"01M7DF9C1XCE5SZP4P6ZSB7BFF","release-notes","https:\u002F\u002Fgithub.com\u002Fhazeliscoding\u002Faxiomarium\u002Fblob\u002Fmain\u002Fskills\u002Fagent-asset-authoring\u002Fevals\u002Fbehavioral\u002Fprefers-tooling\u002Frepo\u002Fskills\u002Frelease-notes\u002Fskill.md",[],[],{"skillNo":90,"name":85,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":18},"01M7DF9AN5C414Q06SD40YX4T9","https:\u002F\u002Fgithub.com\u002Fhazeliscoding\u002Faxiomarium\u002Fblob\u002Fmain\u002Fskills\u002Fagent-asset-authoring\u002Fevals\u002Fbehavioral\u002Fnew-skill\u002Frepo\u002Fskills\u002Frelease-notes\u002Fskill.md",[],[],{"skillNo":95,"name":85,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":18},"01M7DF97CZ3JBHJXBWR5YW7WS2","https:\u002F\u002Fgithub.com\u002Fhazeliscoding\u002Faxiomarium\u002Fblob\u002Fmain\u002Fskills\u002Fagent-asset-authoring\u002Fevals\u002Fbehavioral\u002Fnew-hook\u002Frepo\u002Fskills\u002Frelease-notes\u002Fskill.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":18},"01M7DF95HJ68HNYJ8JNV86DPTJ","api-style","MARKER repo\u002Fsrc\u002F.claude\u002Fskills\u002Fapi-style\u002FSKILL.md How the shop's API code is written.","https:\u002F\u002Fgithub.com\u002Fhazeliscoding\u002Faxiomarium\u002Fblob\u002Fmain\u002Fscenarios\u002Fskills-and-hooks\u002Frepo\u002Fsrc\u002F.claude\u002Fskills\u002Fapi-style\u002FSKILL.md",[],[],{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":18},"01M7DF93RA751HKZB0D9T7HGVR","typescript","MARKER repo\u002F.claude\u002Fskills\u002Ftypescript\u002FSKILL.md Conventions for TypeScript files.","https:\u002F\u002Fgithub.com\u002Fhazeliscoding\u002Faxiomarium\u002Fblob\u002Fmain\u002Fscenarios\u002Fskills-and-hooks\u002Frepo\u002F.claude\u002Fskills\u002Ftypescript\u002FSKILL.md",[],[]]