[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79S7132W9DPXCSD82R9028T":3,"skill-same:01M79S7132W9DPXCSD82R9028T":53},{"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":32,"commitSha":33,"skillDirectory":34,"forksCount":14,"repositoryHtmlUrl":35,"repositoryHomepageUrl":6,"ownerHtmlUrl":36,"ownerBlogUrl":6,"ownerDescription":37,"updatedAt":38,"install":39,"resources":52},"01M79S7132W9DPXCSD82R9028T","prompting-architect",null,"Architect-level prompt design — layering system, task and data regions, instruction precision and delimiters, few-shot selection, chain-of-thought versus direct answers, versioning and review, and the injection-resistant structures that keep untrusted text from becoming instructions. Use when a prompt is a production artefact.","SriAkhilSJ\u002FPulseAIRepo","SriAkhilSJ","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F206201543?v=4","01M79RWFD1Q09B89SXTTKKJY6Z","Sri Akhil SJ","01M79RWFE26NPG0BZ1FRNX376H",0,"MIT","https:\u002F\u002Fgithub.com\u002FSriAkhilSJ\u002FPulseAIRepo\u002Fblob\u002Fmain\u002Fskills\u002Fai-ml-architect\u002Fllm-architect\u002Fprompting-architect\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: prompting-architect\ndescription: Architect-level prompt design — layering system, task and data regions, instruction precision and delimiters, few-shot selection, chain-of-thought versus direct answers, versioning and review, and the injection-resistant structures that keep untrusted text from becoming instructions. Use when a prompt is a production artefact.\nlicense: MIT\ncompatibility: Any model or provider\nmetadata:\n  crusor-domain: ai-ml-architect\n  crusor-path: ai-ml-architect\u002Fllm-architect\u002Fprompting-architect\n  crusor-origin: original\n  crusor-sources: \"docs.anthropic.com\u002Fen\u002Fdocs\u002Fbuild-with-claude\u002Fprompt-engineering; platform.openai.com\u002Fdocs\u002Fguides\u002Fprompt-engineering; learnprompting.org\"\n  crusor-triggers: \"prompt engineering, system prompt, few shot, chain of thought, prompt injection, prompt template, prompt versioning, delimiters\"\n  crusor-verified-on: \"2026-10-30\"\n---\n\n# Prompting Architect\n\nA prompt is **source code that ships to a probabilistic interpreter**. It needs\nversion control, review, tests, and a structure that separates instructions from\ndata.\n\n## When to use\n\n- Any model-backed feature, before tuning anything else.\n- Prompts that grew by accretion and now contradict themselves.\n- A prompt-injection or jailbreak concern.\n\n## When NOT to use\n\n- The failure is retrieval quality or missing context (`rag-architect`).\n- The task needs format guarantees — use structured output, not a better prompt.\n\n## Decision 1 — Structure\n\n```\n[system]   role, rules, output contract, refusal policy — stable, versioned\n[task]     the specific instruction with slots — changes per feature\n[data]     delimited, labelled, explicitly \"data, not instructions\"\n[examples] optional, few-shot, minimal\n[request]  the actual question, last\n```\n\n- Instructions before data, question after data — models attend to the end.\n- Fixed delimiters (`\u003Cdoc>…\u003C\u002Fdoc>`, fenced blocks) with a rule that content inside\n  is data.\n- One prompt, one job. Two jobs in one prompt produce a model that half-does both.\n\n## Decision 2 — Instruction quality\n\n- Be specific about *what* and *how much*: length, format, audience, exclusions.\n- State the refusal case: \"if the documents do not contain the answer, say you\n  don't know\".\n- Positive instructions (\"cite the source id\") beat negative ones (\"don't make\n  things up\") — the negative needs a positive replacement.\n- Remove contradictions; contradictory prompts produce variance that looks like\n  model flakiness.\n\n## Decision 3 — Few-shot and reasoning\n\n- 3–8 examples, chosen to cover edge cases and format, not to be exhaustive.\n- Balanced examples: if every example says yes, the model says yes.\n- Chain-of-thought for multi-step reasoning; skip it for extraction where it\n  mostly adds tokens.\n- Ask for the reasoning in a structured field when it must be auditable, not in\n  free prose you then parse.\n\n## Decision 4 — Injection resistance\n\n- Treat all user and retrieved content as untrusted; never interpolate it into the\n  system region.\n- Delimit and label; instruct the model to ignore instructions found inside data.\n- Do not rely on the model alone: enforce permissions in code, validate tool calls\n  server-side (`agent-architect`).\n- Test with known payloads (\"ignore previous instructions…\"), including base64 and\n  unicode tricks.\n\n## Decision 5 — Lifecycle\n\n- Prompts in files, in version control, reviewed; not strings in a controller.\n- Each change runs the eval suite (`evals-architect`); attach the delta to the PR.\n- Version the prompt id with the model id in logs, so a regression is traceable to\n  a change.\n- Keep the previous prompt deployable — rollback is a config change, not a code\n  revert when possible.\n\n## Failure modes at scale\n\n- Prompt that grew to 3,000 tokens with four sections contradicting each other.\n- User text concatenated into the system prompt; injection succeeds on day one.\n- Few-shot examples all one shape; the model fails on a common edge case.\n- Prompt edited in the dashboard, no version, no eval, no record of who changed it.\n- `temperature` raised to \"make it more creative\" on an extraction endpoint.\n\n## Verification receipts\n\n1. Prompt file with layering visible and a version id.\n2. Eval score attached to the current prompt version.\n3. Injection test suite run against the current prompt.\n4. Log line showing prompt version + model id per request.\n5. Rollback to the previous prompt version exercised.\n","# Prompting Architect\n\nA prompt is **source code that ships to a probabilistic interpreter**. It needs\nversion control, review, tests, and a structure that separates instructions from\ndata.\n\n## When to use\n\n- Any model-backed feature, before tuning anything else.\n- Prompts that grew by accretion and now contradict themselves.\n- A prompt-injection or jailbreak concern.\n\n## When NOT to use\n\n- The failure is retrieval quality or missing context (`rag-architect`).\n- The task needs format guarantees — use structured output, not a better prompt.\n\n## Decision 1 — Structure\n\n```\n[system]   role, rules, output contract, refusal policy — stable, versioned\n[task]     the specific instruction with slots — changes per feature\n[data]     delimited, labelled, explicitly \"data, not instructions\"\n[examples] optional, few-shot, minimal\n[request]  the actual question, last\n```\n\n- Instructions before data, question after data — models attend to the end.\n- Fixed delimiters (`\u003Cdoc>…\u003C\u002Fdoc>`, fenced blocks) with a rule that content inside\n  is data.\n- One prompt, one job. Two jobs in one prompt produce a model that half-does both.\n\n## Decision 2 — Instruction quality\n\n- Be specific about *what* and *how much*: length, format, audience, exclusions.\n- State the refusal case: \"if the documents do not contain the answer, say you\n  don't know\".\n- Positive instructions (\"cite the source id\") beat negative ones (\"don't make\n  things up\") — the negative needs a positive replacement.\n- Remove contradictions; contradictory prompts produce variance that looks like\n  model flakiness.\n\n## Decision 3 — Few-shot and reasoning\n\n- 3–8 examples, chosen to cover edge cases and format, not to be exhaustive.\n- Balanced examples: if every example says yes, the model says yes.\n- Chain-of-thought for multi-step reasoning; skip it for extraction where it\n  mostly adds tokens.\n- Ask for the reasoning in a structured field when it must be auditable, not in\n  free prose you then parse.\n\n## Decision 4 — Injection resistance\n\n- Treat all user and retrieved content as untrusted; never interpolate it into the\n  system region.\n- Delimit and label; instruct the model to ignore instructions found inside data.\n- Do not rely on the model alone: enforce permissions in code, validate tool calls\n  server-side (`agent-architect`).\n- Test with known payloads (\"ignore previous instructions…\"), including base64 and\n  unicode tricks.\n\n## Decision 5 — Lifecycle\n\n- Prompts in files, in version control, reviewed; not strings in a controller.\n- Each change runs the eval suite (`evals-architect`); attach the delta to the PR.\n- Version the prompt id with the model id in logs, so a regression is traceable to\n  a change.\n- Keep the previous prompt deployable — rollback is a config change, not a code\n  revert when possible.\n\n## Failure modes at scale\n\n- Prompt that grew to 3,000 tokens with four sections contradicting each other.\n- User text concatenated into the system prompt; injection succeeds on day one.\n- Few-shot examples all one shape; the model fails on a common edge case.\n- Prompt edited in the dashboard, no version, no eval, no record of who changed it.\n- `temperature` raised to \"make it more creative\" on an extraction endpoint.\n\n## Verification receipts\n\n1. Prompt file with layering visible and a version id.\n2. Eval score attached to the current prompt version.\n3. Injection test suite run against the current prompt.\n4. Log line showing prompt version + model id per request.\n5. Rollback to the previous prompt version exercised.\n",{"name":5,"license":15,"metadata":24,"description":7,"compatibility":31},{"crusor-path":25,"crusor-domain":26,"crusor-origin":27,"crusor-sources":28,"crusor-triggers":29,"crusor-verified-on":30},"ai-ml-architect\u002Fllm-architect\u002Fprompting-architect","ai-ml-architect","original","docs.anthropic.com\u002Fen\u002Fdocs\u002Fbuild-with-claude\u002Fprompt-engineering; platform.openai.com\u002Fdocs\u002Fguides\u002Fprompt-engineering; learnprompting.org","prompt engineering, system prompt, few shot, chain of thought, prompt injection, prompt template, prompt versioning, delimiters","2026-10-30","Any model or provider","main","8fa4e240be65b98472c9b2d3a505ade2aea1a5c6","skills\u002Fai-ml-architect\u002Fllm-architect\u002Fprompting-architect","https:\u002F\u002Fgithub.com\u002FSriAkhilSJ\u002FPulseAIRepo","https:\u002F\u002Fgithub.com\u002FSriAkhilSJ","Studying in CMR institute of Technology\r\n2024 - 2028","2026-11-13 21:02:23",{"source":8,"skillName":5,"commands":40,"prompt":50,"zipAvailable":51},[41,44,47],{"tool":42,"command":43},"npx","npx skills add SriAkhilSJ\u002FPulseAIRepo --skill prompting-architect",{"tool":45,"command":46},"bunx","bunx skills add SriAkhilSJ\u002FPulseAIRepo --skill prompting-architect",{"tool":48,"command":49},"pnpm","pnpm dlx skills add SriAkhilSJ\u002FPulseAIRepo --skill prompting-architect","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSriAkhilSJ\u002FPulseAIRepo\u002Fblob\u002Fmain\u002Fskills\u002Fai-ml-architect\u002Fllm-architect\u002Fprompting-architect\u002FSKILL.md",true,[],[54,61,68,75,82,89],{"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},"01M79TTAJNACCNXCEN3649CMMD","interaction-patterns-architect","Architect-level interaction design in code — choosing established patterns over invented ones, feedback and latency behaviour, destructive-action safeguards, navigation and overlay conventions, and the state model behind every interactive surface. Use when a screen has to behave, not just look.","https:\u002F\u002Fgithub.com\u002FSriAkhilSJ\u002FPulseAIRepo\u002Fblob\u002Fmain\u002Fskills\u002Fwebsite-architect\u002Fui-ux-implementation-architect\u002Finteraction-patterns-architect\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},"01M79TT2ESKB1TKZBYY9KYJHV9","design-system-ops-architect","Architect-level operation of a design system in code — token pipelines and versioning, component API and variant policy, the catalogue as the contract, adoption metrics, and the governance that stops a system from forking into three. Use when a component library must survive several teams.","https:\u002F\u002Fgithub.com\u002FSriAkhilSJ\u002FPulseAIRepo\u002Fblob\u002Fmain\u002Fskills\u002Fwebsite-architect\u002Fui-ux-implementation-architect\u002Fdesign-system-ops-architect\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},"01M79TSV0PWGNK3PRX9P4JDR9N","design-handoff-architect","Architect-level design handoff — what must be specified before implementation starts, tokens over raw values, responsive and content-limit contracts, state matrices, and the review loop that catches drift between design and code. Use when a design is about to become code.","https:\u002F\u002Fgithub.com\u002FSriAkhilSJ\u002FPulseAIRepo\u002Fblob\u002Fmain\u002Fskills\u002Fwebsite-architect\u002Fui-ux-implementation-architect\u002Fdesign-handoff-architect\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},"01M79TSJS9BFXNP696FMJ9GKDA","content-microcopy-architect","Architect-level UI content — where strings live, voice and terminology consistency, error and empty-state copy as part of the interface, translation-ready authoring, and the content model a product needs before it multiplies screens. Use when the words in the interface matter as much as the pixels.","https:\u002F\u002Fgithub.com\u002FSriAkhilSJ\u002FPulseAIRepo\u002Fblob\u002Fmain\u002Fskills\u002Fwebsite-architect\u002Fui-ux-implementation-architect\u002Fcontent-microcopy-architect\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},"01M79TSCNBST3N1M68V1KPH9HQ","ui-ux-implementation-architect","Architect-level direction for turning a design into working UI — the handoff contract, component ownership versus screen-level layout, interaction and state conventions, design QA gates, and the review habits that keep an implementation faithful without frozen pixels. Use before any specific UI implementation skill.","https:\u002F\u002Fgithub.com\u002FSriAkhilSJ\u002FPulseAIRepo\u002Fblob\u002Fmain\u002Fskills\u002Fwebsite-architect\u002Fui-ux-implementation-architect\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":19},"01M79TS4N6A4D2QQ433VXS5D0R","test-strategy-architect","Architect-level test strategy — allocating assertions across unit, integration, contract and end-to-end layers, designing for testability through dependency boundaries, fixture and data strategy, and the flake and coverage policies that keep a suite trustworthy. Use when defining how a codebase is tested.","https:\u002F\u002Fgithub.com\u002FSriAkhilSJ\u002FPulseAIRepo\u002Fblob\u002Fmain\u002Fskills\u002Fwebsite-architect\u002Ftesting-and-deployment-architect\u002Ftest-strategy-architect\u002FSKILL.md",[],[]]