[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77KN6WNSP9EPCSGVZNR6VDF":3,"skill-same:01M77KN6WNSP9EPCSGVZNR6VDF":61},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M77KN6WNSP9EPCSGVZNR6VDF","tflow-prompt",null,"Use when the user shares a raw, vague, or first-draft prompt and wants it clarified, tightened, strengthened, or made more reliable — or asks to improve, rewrite, or optimize a prompt, write a system prompt, or apply prompt-engineering techniques like few-shot examples, chain-of-thought, role framing, or XML structuring","terra0rg\u002Ftflow","terra0rg","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F107129622?v=4","01M77KMA9N87BG8SM8MCMH94VE","01M77KMAAB5HRM0VSQ3HRKHHK2",3,"MIT","https:\u002F\u002Fgithub.com\u002Fterra0rg\u002Ftflow\u002Fblob\u002Fmain\u002Fskills\u002Ftflow-prompt\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: tflow-prompt\ndescription: Use when the user shares a raw, vague, or first-draft prompt and wants it clarified, tightened, strengthened, or made more reliable — or asks to improve, rewrite, or optimize a prompt, write a system prompt, or apply prompt-engineering techniques like few-shot examples, chain-of-thought, role framing, or XML structuring\nlicense: MIT\ncompatibility: Portable Agent Skill source for Claude Code, OpenAI Codex, and runtimes that support SKILL.md; requires no scripts, tools, or network access.\n---\n\n# tflow Prompt\n\nUse this skill to turn a user's base prompt into a stronger one. The default is a\nsingle pass: read the prompt, apply the techniques that actually help it, and\nhand back the rewritten prompt **plus** a short change log. Always rewrite *and*\nexplain — never return a silently transformed prompt the user cannot audit.\n\nEnhance to earn it, not to decorate. Add a technique only when it makes the\nprompt measurably clearer for its goal; if the original is already tight, say so\nand change little. Match effort to the prompt's complexity — a one-liner usually\nneeds a clarity pass, not all seven techniques.\n\nPrompt-engineering specifics drift between model releases: token limits,\nprovider flags, and model names change. Treat the technique *principles* here as\ndurable, but tell the user to verify any concrete model name, token limit, or\nAPI field against the provider's current documentation rather than trusting a\nfixed value.\n\n## Locating the prompt\n\nTake the prompt to enhance from the user's latest message or from earlier in the\nconversation. If no candidate prompt is present, ask the user to paste the one\nthey want strengthened before going further.\n\n## Process\n\n1. **Infer the goal.** What outcome does the user want, for what audience, in\n   what shape? If the prompt is too thin to infer a goal, ask up to three\n   targeted questions (typically goal, audience, result shape), then proceed.\n2. **Run the completeness check.** A well-formed prompt covers up to four\n   components: an **instruction** (the task), **context** (background and\n   motivation), **input data** (the material to act on), and an **output\n   indicator** (the shape of the result). Note only the ones that are missing\n   *and matter* for this task — not every prompt needs all four.\n3. **Apply the techniques in order**, each only where it helps. The order in\n   [Techniques](#techniques-in-order) is deliberate: clarity first, structure\n   and examples next, role and reasoning last.\n4. **Scale to complexity.** Reserve examples, structure, role framing, and\n   step-by-step reasoning for prompts whose difficulty earns them. Name anything\n   you *remove* as noise, not just what you add.\n5. **Return the two-part result** below.\n\n## Techniques, in order\n\n1. **Clarity & directness** — state the task and its constraints explicitly;\n   replace vague language with concrete instructions.\n2. **Context & motivation** — explain *why*, so the model generalizes beyond the\n   literal words.\n3. **Examples** — show 2–5 diverse examples for format-sensitive or nuanced\n   tasks; demonstrate the desired output rather than only describing it.\n4. **Structure** — separate instruction, context, and input into labeled\n   sections (headers or tags) so they are not confused for one another.\n5. **Role** — give the model a role or expertise level when tone or domain rigor\n   matters.\n6. **Reasoning** — invite step-by-step thinking for analytical or multi-factor\n   tasks, before the final answer.\n7. **Decomposition** — split complex, multi-stage work into sequential prompts\n   where each output feeds the next.\n\nWorked before\u002Fafter rewrites are in [examples](references\u002Fexamples.md).\n\n## Result format\n\nReturn exactly two parts, in this order:\n\n1. **Enhanced prompt** — the rewritten prompt in a fenced code block, ready to\n   copy and use verbatim.\n2. **Change log** — a short bullet list, each line tagged by the technique that\n   motivated it and a one-line reason, ending with a **completeness note**: one\n   line naming which of the four components (instruction, context, input,\n   output indicator) are now present, and any the user must still supply — for\n   example real input data or domain facts. Use these tags:\n   - `clarity` — sharpened or disambiguated the instruction.\n   - `context` — added background or motivation.\n   - `example` — added or restructured examples.\n   - `structure` — introduced or tidied sectioning.\n   - `role` — set or adjusted a role.\n   - `reasoning` — invited step-by-step thinking.\n   - `decomposition` — split into stages or sequenced prompts.\n   - `cut` — removed noise, redundancy, or over-specification.\n\n## Boundaries\n\n- This skill improves prompts; it does not run, benchmark, or evaluate them.\n  Suggest the user test against their own success criteria, but keep execution\n  out of scope.\n- It assumes no specific provider or model. The techniques are general; defer\n  vendor-specific detail to the provider's live documentation.\n- It never fabricates the user's domain facts or input data. Missing material is\n  named in the completeness note, not guessed.\n\n## References\n\n- [examples](references\u002Fexamples.md) — worked before\u002Fafter enhancements showing\n  the two-part result and proportional technique use.\n","# tflow Prompt\n\nUse this skill to turn a user's base prompt into a stronger one. The default is a\nsingle pass: read the prompt, apply the techniques that actually help it, and\nhand back the rewritten prompt **plus** a short change log. Always rewrite *and*\nexplain — never return a silently transformed prompt the user cannot audit.\n\nEnhance to earn it, not to decorate. Add a technique only when it makes the\nprompt measurably clearer for its goal; if the original is already tight, say so\nand change little. Match effort to the prompt's complexity — a one-liner usually\nneeds a clarity pass, not all seven techniques.\n\nPrompt-engineering specifics drift between model releases: token limits,\nprovider flags, and model names change. Treat the technique *principles* here as\ndurable, but tell the user to verify any concrete model name, token limit, or\nAPI field against the provider's current documentation rather than trusting a\nfixed value.\n\n## Locating the prompt\n\nTake the prompt to enhance from the user's latest message or from earlier in the\nconversation. If no candidate prompt is present, ask the user to paste the one\nthey want strengthened before going further.\n\n## Process\n\n1. **Infer the goal.** What outcome does the user want, for what audience, in\n   what shape? If the prompt is too thin to infer a goal, ask up to three\n   targeted questions (typically goal, audience, result shape), then proceed.\n2. **Run the completeness check.** A well-formed prompt covers up to four\n   components: an **instruction** (the task), **context** (background and\n   motivation), **input data** (the material to act on), and an **output\n   indicator** (the shape of the result). Note only the ones that are missing\n   *and matter* for this task — not every prompt needs all four.\n3. **Apply the techniques in order**, each only where it helps. The order in\n   [Techniques](#techniques-in-order) is deliberate: clarity first, structure\n   and examples next, role and reasoning last.\n4. **Scale to complexity.** Reserve examples, structure, role framing, and\n   step-by-step reasoning for prompts whose difficulty earns them. Name anything\n   you *remove* as noise, not just what you add.\n5. **Return the two-part result** below.\n\n## Techniques, in order\n\n1. **Clarity & directness** — state the task and its constraints explicitly;\n   replace vague language with concrete instructions.\n2. **Context & motivation** — explain *why*, so the model generalizes beyond the\n   literal words.\n3. **Examples** — show 2–5 diverse examples for format-sensitive or nuanced\n   tasks; demonstrate the desired output rather than only describing it.\n4. **Structure** — separate instruction, context, and input into labeled\n   sections (headers or tags) so they are not confused for one another.\n5. **Role** — give the model a role or expertise level when tone or domain rigor\n   matters.\n6. **Reasoning** — invite step-by-step thinking for analytical or multi-factor\n   tasks, before the final answer.\n7. **Decomposition** — split complex, multi-stage work into sequential prompts\n   where each output feeds the next.\n\nWorked before\u002Fafter rewrites are in [examples](references\u002Fexamples.md).\n\n## Result format\n\nReturn exactly two parts, in this order:\n\n1. **Enhanced prompt** — the rewritten prompt in a fenced code block, ready to\n   copy and use verbatim.\n2. **Change log** — a short bullet list, each line tagged by the technique that\n   motivated it and a one-line reason, ending with a **completeness note**: one\n   line naming which of the four components (instruction, context, input,\n   output indicator) are now present, and any the user must still supply — for\n   example real input data or domain facts. Use these tags:\n   - `clarity` — sharpened or disambiguated the instruction.\n   - `context` — added background or motivation.\n   - `example` — added or restructured examples.\n   - `structure` — introduced or tidied sectioning.\n   - `role` — set or adjusted a role.\n   - `reasoning` — invited step-by-step thinking.\n   - `decomposition` — split into stages or sequenced prompts.\n   - `cut` — removed noise, redundancy, or over-specification.\n\n## Boundaries\n\n- This skill improves prompts; it does not run, benchmark, or evaluate them.\n  Suggest the user test against their own success criteria, but keep execution\n  out of scope.\n- It assumes no specific provider or model. The techniques are general; defer\n  vendor-specific detail to the provider's live documentation.\n- It never fabricates the user's domain facts or input data. Missing material is\n  named in the completeness note, not guessed.\n\n## References\n\n- [examples](references\u002Fexamples.md) — worked before\u002Fafter enhancements showing\n  the two-part result and proportional technique use.\n",{"name":5,"license":14,"description":7,"compatibility":23},"Portable Agent Skill source for Claude Code, OpenAI Codex, and runtimes that support SKILL.md; requires no scripts, tools, or network access.","main","52370138f4e23850775427e00c09b58c6b974517","skills\u002Ftflow-prompt",0,"https:\u002F\u002Fgithub.com\u002Fterra0rg\u002Ftflow","https:\u002F\u002Fgithub.com\u002Fterra0rg","2026-09-09 23:44:26",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add terra0rg\u002Ftflow --skill tflow-prompt",{"tool":37,"command":38},"bunx","bunx skills add terra0rg\u002Ftflow --skill tflow-prompt",{"tool":40,"command":41},"pnpm","pnpm dlx skills add terra0rg\u002Ftflow --skill tflow-prompt","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fterra0rg\u002Ftflow\u002Fblob\u002Fmain\u002Fskills\u002Ftflow-prompt\u002FSKILL.md",true,[45,51,55],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"evals\u002Fevals.json","REFERENCE","参考文档",2505,"https:\u002F\u002Fgithub.com\u002Fterra0rg\u002Ftflow\u002Fblob\u002Fmain\u002Fskills\u002Ftflow-prompt\u002Fevals\u002Fevals.json",{"path":52,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Fexamples.md",2742,"https:\u002F\u002Fgithub.com\u002Fterra0rg\u002Ftflow\u002Fblob\u002Fmain\u002Fskills\u002Ftflow-prompt\u002Freferences\u002Fexamples.md",{"path":56,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":59,"sourceHtmlUrl":60},"tests\u002Frun-tests.sh","SCRIPT","脚本",3896,"https:\u002F\u002Fgithub.com\u002Fterra0rg\u002Ftflow\u002Fblob\u002Fmain\u002Fskills\u002Ftflow-prompt\u002Ftests\u002Frun-tests.sh",[62,69,76,83,90,97],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":18},"01M77KQEX46XEMJBXZHQ51RBAK","tflow-skill-test","Use when an Agent Skill needs a TDD-style test plan before authoring, or a finished skill needs the three-layer test pass — structural gate, deterministic script checks, and judged eval scenarios","https:\u002F\u002Fgithub.com\u002Fterra0rg\u002Ftflow\u002Fblob\u002Fmain\u002Fskills\u002Ftflow-skill-test\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":18},"01M77KQAVFTNYRP9DQPZJ6N3QA","tflow-skill-idea","Use when a raw Agent Skill idea needs interactive shaping into a research-ready idea brief — surfacing the core purpose with Five Whys and a human-chosen direction before any research or authoring begins","https:\u002F\u002Fgithub.com\u002Fterra0rg\u002Ftflow\u002Fblob\u002Fmain\u002Fskills\u002Ftflow-skill-idea\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":18},"01M77KQ68X3CN1Q0CBD5WPX5XX","tflow-skill-factory","Use when a raw Agent Skill idea must become a tested, reviewed, and documented skill through the full eight-step pipeline; for a single phase alone, use the matching phase skill directly","https:\u002F\u002Fgithub.com\u002Fterra0rg\u002Ftflow\u002Fblob\u002Fmain\u002Fskills\u002Ftflow-skill-factory\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":18},"01M77KQ344Z2YK255DPG4Q5KPS","pass-well-formed","Use when you need a canonical example of a well-formed skill that passes all quality checks","https:\u002F\u002Fgithub.com\u002Fterra0rg\u002Ftflow\u002Fblob\u002Fmain\u002Fskills\u002Ftflow-skill-creator\u002Fscripts\u002Ffixtures\u002Fpass-well-formed\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":18},"01M77KQ0DVQHDG3N8T3VB8JYM1","pass-verb-substring","Use when you need information about typically uninstalled prior art","https:\u002F\u002Fgithub.com\u002Fterra0rg\u002Ftflow\u002Fblob\u002Fmain\u002Fskills\u002Ftflow-skill-creator\u002Fscripts\u002Ffixtures\u002Fpass-verb-substring\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":18},"01M77KPXFW3WAHSZMNFBPZTQ80","pass-trigger-condition","Use when an observable trigger condition applies to the current state","https:\u002F\u002Fgithub.com\u002Fterra0rg\u002Ftflow\u002Fblob\u002Fmain\u002Fskills\u002Ftflow-skill-creator\u002Fscripts\u002Ffixtures\u002Fpass-trigger-condition\u002FSKILL.md",[],[]]