[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79D00CV9BEXQQXJ46YYD6E4":3,"skill-same:01M79D00CV9BEXQQXJ46YYD6E4":56},{"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":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M79D00CV9BEXQQXJ46YYD6E4","writing-for-agents",null,"Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","JanMichaelSE\u002Fagentic-marketplace","JanMichaelSE","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F55473580?v=4","01M79CW862FGHY91NG8DDRRFJC","Jan M Montalvo","01M79CW86M2NJQNRZ41VP9AJ51",1,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FJanMichaelSE\u002Fagentic-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fproductivity\u002Fskills\u002Fwriting-for-agents\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: writing-for-agents\ndescription: Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.\n---\n\n# Writing for Agents\n\nReference for writing any document an agent consumes — a skill, an `AGENTS.md`\nor `CLAUDE.md`, or a document reached by a pointer. The packaging differs; the\nwriting does not: the same levers make each one predictable — the agent taking\nthe same process every run, not producing the same output.\n\nWhen the document is a skill, read [SKILL-MECHANICS.md](SKILL-MECHANICS.md) for\nfrontmatter, invocation choice, and router skills.\n\n## Context pointers\n\nA **context pointer** is a reference held in the agent's context that names\nout-of-context material and encodes the condition for reaching it. A skill's\ndescription is one; a line in `AGENTS.md` naming a document is the same object.\nThe pointer's wording, not its target, decides when the agent reaches the\nmaterial and how reliably. A must-have target behind a weakly worded pointer is\na variance bug: sharpen the wording first, and inline the material only if that\nfails.\n\nA pointer states what the material is and lists the **branches** that should\ntrigger reaching it. Every word of an always-loaded pointer costs on every turn,\nso prune it harder than the body:\n\n- **Front-load the leading word** — the pointer is where it does its triggering work.\n- **Use one trigger per branch.** Collapse synonyms that name one branch.\n- **Cut identity the body already carries.**\n\n## The two loads\n\nEvery document and pointer spends one of two budgets:\n\n- **Context load** — the cost of always-loaded material on the agent's window:\n  an `AGENTS.md` line, a skill description, or anything present every turn.\n- **Cognitive load** — the cost on the human: which documents exist and when to\n  reach for each. The human is the index. It is the price of human agency; spend\n  it where human judgement matters and remove it where it does not.\n\nMaterial reached only through a pointer escapes context load at the price of the\npointer's own line; material with no pointer rides entirely on cognitive load.\n\n## Information hierarchy\n\nA document combines **steps** (ordered agent actions) and **reference**\n(definitions, rules, or facts consulted on demand). Put each item at the lowest\nrung the agent can reliably reach:\n\n1. **In-file step** — what the agent does, in order.\n2. **In-file reference** — material consulted on demand.\n3. **Disclosed reference** — material in another file, reached only through a\n   clearly worded context pointer.\n\n**Progressive disclosure** moves material down the ladder so the top stays\nlegible. Inline what every branch needs; disclose material only some branches\nreach. **Co-location** decides what sits beside a concept once it is on a rung:\nkeep its definition, rules, and caveats together. **Sprawl** is the failure mode\nwhen a document remains too long even though every line is live; disclose\nreference and split by branch or sequence to cure it.\n\n## Steps and completion criteria\n\nEvery step ends on a **completion criterion** — the condition that tells the\nagent the work is done. It needs both:\n\n- **Clarity** — an observable bound that distinguishes done from not done.\n  Sharpen it before splitting a sequence to counter **premature completion**.\n- **Demand** — an appropriately exhaustive requirement. Demand drives the\n  **legwork** the agent performs, whether the document has steps or flat\n  reference.\n\nThe strongest criteria are both checkable and exhaustive.\n\n## When to split\n\nSplitting spends one of the two loads, so make the cut earn it:\n\n- **By sequence** — split steps only when visible post-completion steps make the\n  current step rush and a sharper completion criterion does not fix it.\n- **By invocation** — for skill-specific guidance, read\n  [SKILL-MECHANICS.md](SKILL-MECHANICS.md).\n\n## Leading words\n\nA **leading word** is a compact concept already present in the model's\npretraining that the agent thinks with while running the document — _lesson_,\n_fog of war_, or _tracer bullets_. It anchors execution in the body and\ninvocation in a pointer with fewer tokens than repeated explanation.\n\nHunt for chances to refactor repeated ideas into a leading word where it changes\nbehaviour:\n\n- \"fast, deterministic, low-overhead\" becomes _tight_.\n- \"a loop you believe in\" becomes _red_: a fuzzy gate becomes binary and observable.\n\nUse a positive target. **Negation** activates the behaviour it tries to ban, so\nkeep a prohibition only for an unavoidable hard guardrail and pair it with the\ndesired action.\n\n## Pruning\n\n- Keep each meaning in a **single source of truth**. **Duplication** costs\n  maintenance and inflates a meaning's prominence.\n- Treat the environment as a source of truth too. A document that restates a\n  cheap lookup in configuration, source, or `--help` output is a **cache**;\n  cache only unwritten conventions, reasons, and non-obvious gotchas.\n- Check every line for **relevance**. Remove stale or unrelated material before\n  it settles into **sediment**.\n- Hunt **no-ops** sentence by sentence: if deleting it does not change agent\n  behaviour from the default, delete it instead of trimming it.\n","# Writing for Agents\n\nReference for writing any document an agent consumes — a skill, an `AGENTS.md`\nor `CLAUDE.md`, or a document reached by a pointer. The packaging differs; the\nwriting does not: the same levers make each one predictable — the agent taking\nthe same process every run, not producing the same output.\n\nWhen the document is a skill, read [SKILL-MECHANICS.md](SKILL-MECHANICS.md) for\nfrontmatter, invocation choice, and router skills.\n\n## Context pointers\n\nA **context pointer** is a reference held in the agent's context that names\nout-of-context material and encodes the condition for reaching it. A skill's\ndescription is one; a line in `AGENTS.md` naming a document is the same object.\nThe pointer's wording, not its target, decides when the agent reaches the\nmaterial and how reliably. A must-have target behind a weakly worded pointer is\na variance bug: sharpen the wording first, and inline the material only if that\nfails.\n\nA pointer states what the material is and lists the **branches** that should\ntrigger reaching it. Every word of an always-loaded pointer costs on every turn,\nso prune it harder than the body:\n\n- **Front-load the leading word** — the pointer is where it does its triggering work.\n- **Use one trigger per branch.** Collapse synonyms that name one branch.\n- **Cut identity the body already carries.**\n\n## The two loads\n\nEvery document and pointer spends one of two budgets:\n\n- **Context load** — the cost of always-loaded material on the agent's window:\n  an `AGENTS.md` line, a skill description, or anything present every turn.\n- **Cognitive load** — the cost on the human: which documents exist and when to\n  reach for each. The human is the index. It is the price of human agency; spend\n  it where human judgement matters and remove it where it does not.\n\nMaterial reached only through a pointer escapes context load at the price of the\npointer's own line; material with no pointer rides entirely on cognitive load.\n\n## Information hierarchy\n\nA document combines **steps** (ordered agent actions) and **reference**\n(definitions, rules, or facts consulted on demand). Put each item at the lowest\nrung the agent can reliably reach:\n\n1. **In-file step** — what the agent does, in order.\n2. **In-file reference** — material consulted on demand.\n3. **Disclosed reference** — material in another file, reached only through a\n   clearly worded context pointer.\n\n**Progressive disclosure** moves material down the ladder so the top stays\nlegible. Inline what every branch needs; disclose material only some branches\nreach. **Co-location** decides what sits beside a concept once it is on a rung:\nkeep its definition, rules, and caveats together. **Sprawl** is the failure mode\nwhen a document remains too long even though every line is live; disclose\nreference and split by branch or sequence to cure it.\n\n## Steps and completion criteria\n\nEvery step ends on a **completion criterion** — the condition that tells the\nagent the work is done. It needs both:\n\n- **Clarity** — an observable bound that distinguishes done from not done.\n  Sharpen it before splitting a sequence to counter **premature completion**.\n- **Demand** — an appropriately exhaustive requirement. Demand drives the\n  **legwork** the agent performs, whether the document has steps or flat\n  reference.\n\nThe strongest criteria are both checkable and exhaustive.\n\n## When to split\n\nSplitting spends one of the two loads, so make the cut earn it:\n\n- **By sequence** — split steps only when visible post-completion steps make the\n  current step rush and a sharper completion criterion does not fix it.\n- **By invocation** — for skill-specific guidance, read\n  [SKILL-MECHANICS.md](SKILL-MECHANICS.md).\n\n## Leading words\n\nA **leading word** is a compact concept already present in the model's\npretraining that the agent thinks with while running the document — _lesson_,\n_fog of war_, or _tracer bullets_. It anchors execution in the body and\ninvocation in a pointer with fewer tokens than repeated explanation.\n\nHunt for chances to refactor repeated ideas into a leading word where it changes\nbehaviour:\n\n- \"fast, deterministic, low-overhead\" becomes _tight_.\n- \"a loop you believe in\" becomes _red_: a fuzzy gate becomes binary and observable.\n\nUse a positive target. **Negation** activates the behaviour it tries to ban, so\nkeep a prohibition only for an unavoidable hard guardrail and pair it with the\ndesired action.\n\n## Pruning\n\n- Keep each meaning in a **single source of truth**. **Duplication** costs\n  maintenance and inflates a meaning's prominence.\n- Treat the environment as a source of truth too. A document that restates a\n  cheap lookup in configuration, source, or `--help` output is a **cache**;\n  cache only unwritten conventions, reasons, and non-obvious gotchas.\n- Check every line for **relevance**. Remove stale or unrelated material before\n  it settles into **sediment**.\n- Hunt **no-ops** sentence by sentence: if deleting it does not change agent\n  behaviour from the default, delete it instead of trimming it.\n",{"name":5,"description":7},"main","d9e185f133b5cbcd785341095a241d0c64d8310d","plugins\u002Fproductivity\u002Fskills\u002Fwriting-for-agents",0,"https:\u002F\u002Fgithub.com\u002FJanMichaelSE\u002Fagentic-marketplace","https:\u002F\u002Fgithub.com\u002FJanMichaelSE","Software Developer | B.S. Computer Science ","2026-11-14 06:36:51",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add JanMichaelSE\u002Fagentic-marketplace --skill writing-for-agents",{"tool":38,"command":39},"bunx","bunx skills add JanMichaelSE\u002Fagentic-marketplace --skill writing-for-agents",{"tool":41,"command":42},"pnpm","pnpm dlx skills add JanMichaelSE\u002Fagentic-marketplace --skill writing-for-agents","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJanMichaelSE\u002Fagentic-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fproductivity\u002Fskills\u002Fwriting-for-agents\u002FSKILL.md",true,[46,52],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"agents\u002Fopenai.yaml","REFERENCE","参考文档",102,"https:\u002F\u002Fgithub.com\u002FJanMichaelSE\u002Fagentic-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fproductivity\u002Fskills\u002Fwriting-for-agents\u002Fagents\u002Fopenai.yaml",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"SKILL-MECHANICS.md",1584,"https:\u002F\u002Fgithub.com\u002FJanMichaelSE\u002Fagentic-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fproductivity\u002Fskills\u002Fwriting-for-agents\u002FSKILL-MECHANICS.md",[57,64,71,78,85,92],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":19},"01M79D1SP72BJKFZDHH2W0VT9G","ui-ux-pro-max","UI\u002FUX design intelligence for web and mobile. Local database with 79 searchable styles (88 catalog entries), 192 color palettes, 74 font pairings, 192 product types, 119 UX guidelines, 105 curated icon entries, 17 GSAP motion presets, and 25 chart types across 22 stacks (React, Next.js, Vue, Nuxt, Svelte, Astro, SwiftUI, React Native, Flutter, Tailwind, shadcn\u002Fui, Jetpack Compose, Angular, Laravel, JavaFX, WPF, WinUI, Avalonia, Uno Platform, UWP, Three.js, and HTML\u002FCSS). Use when designing, building, or reviewing UI: pages, components, color schemes, typography, layout, accessibility, animation, or data visualization.","https:\u002F\u002Fgithub.com\u002FJanMichaelSE\u002Fagentic-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fui-ux\u002Fskills\u002Fui-ux-pro-max\u002FSKILL.md",[],[],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":19},"01M79D1NPRNKYC0GNSPQBG02AD","figma-mcp","Implement or compare UI against Figma designs using an available Figma MCP integration. Use for Figma-backed implementation, design-token extraction, or visual-parity gap analysis; Figma MCP access is optional and must already be configured by the user.","https:\u002F\u002Fgithub.com\u002FJanMichaelSE\u002Fagentic-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fui-ux\u002Fskills\u002Ffigma-mcp\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M79D1HW8E8EBKHYD0VRPAGDB","improve-codebase-architecture","Find evidence-based, active-change architecture improvements using shared design and domain-modeling guidance. Use when a user wants to reduce architectural friction, deepen a module, or make a current change safer, more testable, and easier to navigate.","https:\u002F\u002Fgithub.com\u002FJanMichaelSE\u002Fagentic-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fsoftware-architecture\u002Fskills\u002Fimprove-codebase-architecture\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M79D1E9DJ22BZN68FGNEY6H9","domain-modeling","Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing GLOSSARY.md or CONTEXT.md, or recording or editing an ADR.","https:\u002F\u002Fgithub.com\u002FJanMichaelSE\u002Fagentic-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fsoftware-architecture\u002Fskills\u002Fdomain-modeling\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M79D1BWY6DT3SDNRVRJV73PH","codebase-design","Provide the shared vocabulary and discipline for designing deep modules with clear interfaces and seams. Use when a user wants to design or improve a module, find deepening opportunities, choose a seam, or make code more testable and AI-navigable.","https:\u002F\u002Fgithub.com\u002FJanMichaelSE\u002Fagentic-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fsoftware-architecture\u002Fskills\u002Fcodebase-design\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":19},"01M79D176DSM0779MS5PCW022A","test-coverage-review","MUST invoke to review whether added or updated tests cover code changes in a diff. Checks new logic, branches, error paths, and regression risk, producing a change-to-test matrix. Use requirements-to-tests-traceability for acceptance-criteria mapping and orchestrated-review for bundled reviews.","https:\u002F\u002Fgithub.com\u002FJanMichaelSE\u002Fagentic-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Freview-toolkit\u002Fskills\u002Ftest-coverage-review\u002FSKILL.md",[],[]]