[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6QMNWVJAHRKVXS2PDF7V23W":3,"skill-same:01M6QMNWVJAHRKVXS2PDF7V23W":85},{"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":31,"publishedAt":52,"linkOnly":53,"markdownContent":54,"markdownBody":55,"frontMatter":56,"refName":62,"commitSha":63,"skillDirectory":64,"forksCount":14,"repositoryHtmlUrl":65,"repositoryHomepageUrl":66,"ownerHtmlUrl":67,"ownerBlogUrl":68,"ownerDescription":69,"updatedAt":70,"install":71,"resources":84},"01M6QMNWVJAHRKVXS2PDF7V23W","prompt-engineer-toolkit",null,"Turns marketing prompts into tested, versioned production assets: A\u002FB prompt evaluation against structured test cases, immutable prompt version history with diffs, ready-to-use marketing prompt templates (ad copy, email campaigns, social posts, landing pages, SEO meta), and an LLM-governance playbook for marketing teams (claim discipline, disclosure rules, human-review gates). Use when a marketing team relies on AI-generated content and needs prompt quality to be measurable and safe — or when the user mentions 'prompt engineering,' 'improve my prompts,' 'prompt templates,' 'prompt versioning,' 'AI content workflow,' or 'AI governance for marketing.'","Tashima-Tarsh\u002FDisha6.6","Tashima-Tarsh","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F269906498?v=4","01M6PBH98X03XERH0HFT4PFB1P","NITISH KUMAR","01M6PBH9DA0M6KM3Z12P848F0K",0,"MIT","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fprompt-engineer-toolkit\u002FSKILL.md",[18,23,26],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000019","营销推广","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":27,"categoryName":28,"taxonomyType":29,"taxonomyTypeDesc":30},"01JBSEEDCAT000000000000035","市场营销","PROFESSION","适用职业",[32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51],"toolkit","prompt engineer","engineer","prompt engineer toolkit","prompt","versioning","test cases","posts","human","ai content workflow","ready","discipline","diffs","improve","team","playbook","Meta","Evaluation","email","safe","2026-11-10 10:12:30",false,"---\nname: \"prompt-engineer-toolkit\"\ndescription: \"Turns marketing prompts into tested, versioned production assets: A\u002FB prompt evaluation against structured test cases, immutable prompt version history with diffs, ready-to-use marketing prompt templates (ad copy, email campaigns, social posts, landing pages, SEO meta), and an LLM-governance playbook for marketing teams (claim discipline, disclosure rules, human-review gates). Use when a marketing team relies on AI-generated content and needs prompt quality to be measurable and safe — or when the user mentions 'prompt engineering,' 'improve my prompts,' 'prompt templates,' 'prompt versioning,' 'AI content workflow,' or 'AI governance for marketing.'\"\nlicense: MIT\nmetadata:\n  version: 1.0.0\n  author: Alireza Rezvani\n  category: marketing\n  updated: 2026-03-06\n---\n\n# Prompt Engineer Toolkit\n\n## Overview\n\nUse this skill to move prompts from ad-hoc drafts to production assets with repeatable testing, versioning, and regression safety. It emphasizes measurable quality over intuition. Apply it when launching a new LLM feature that needs reliable outputs, when prompt quality degrades after model or instruction changes, when multiple team members edit prompts and need history\u002Fdiffs, when you need evidence-based prompt choice for production rollout, or when you want consistent prompt governance across environments.\n\n## Core Capabilities\n\n- A\u002FB prompt evaluation against structured test cases\n- Quantitative scoring for adherence, relevance, and safety checks\n- Prompt version tracking with immutable history and changelog\n- Prompt diffs to review behavior-impacting edits\n- Reusable prompt templates and selection guidance\n- Regression-friendly workflows for model\u002Fprompt updates\n\n## Key Workflows\n\n### 1. Run Prompt A\u002FB Test\n\nPrepare JSON test cases and run:\n\n```bash\npython3 scripts\u002Fprompt_tester.py \\\n  --prompt-a-file prompts\u002Fa.txt \\\n  --prompt-b-file prompts\u002Fb.txt \\\n  --cases-file testcases.json \\\n  --runner-cmd 'my-llm-cli --prompt {prompt} --input {input}' \\\n  --format text\n```\n\nInput can also come from stdin\u002F`--input` JSON payload.\n\n### 2. Choose Winner With Evidence\n\nThe tester scores outputs per case and aggregates:\n\n- expected content coverage\n- forbidden content violations\n- regex\u002Fformat compliance\n- output length sanity\n\nUse the higher-scoring prompt as candidate baseline, then run regression suite.\n\n### 3. Version Prompts\n\n```bash\n# Add version\npython3 scripts\u002Fprompt_versioner.py add \\\n  --name support_classifier \\\n  --prompt-file prompts\u002Fsupport_v3.txt \\\n  --author alice\n\n# Diff versions\npython3 scripts\u002Fprompt_versioner.py diff --name support_classifier --from-version 2 --to-version 3\n\n# Changelog\npython3 scripts\u002Fprompt_versioner.py changelog --name support_classifier\n```\n\n### 4. Regression Loop\n\n1. Store baseline version.\n2. Propose prompt edits.\n3. Re-run A\u002FB test.\n4. Promote only if score and safety constraints improve.\n\n## Script Interfaces\n\n- `python3 scripts\u002Fprompt_tester.py --help`\n  - Reads prompts\u002Fcases from stdin or `--input`\n  - Optional external runner command\n  - Emits text or JSON metrics\n- `python3 scripts\u002Fprompt_versioner.py --help`\n  - Manages prompt history (`add`, `list`, `diff`, `changelog`)\n  - Stores metadata and content snapshots locally\n\n## Pitfalls, Best Practices & Review Checklist\n\n**Avoid these mistakes:**\n1. Picking prompts from single-case outputs — use a realistic, edge-case-rich test suite.\n2. Changing prompt and model simultaneously — always isolate variables.\n3. Missing `must_not_contain` (forbidden-content) checks in evaluation criteria.\n4. Editing prompts without version metadata, author, or change rationale.\n5. Skipping semantic diffs before deploying a new prompt version.\n6. Optimizing one benchmark while harming edge cases — track the full suite.\n7. Model swap without rerunning the baseline A\u002FB suite.\n\n**Before promoting any prompt, confirm:**\n- [ ] Task intent is explicit and unambiguous.\n- [ ] Output schema\u002Fformat is explicit.\n- [ ] Safety and exclusion constraints are explicit.\n- [ ] No contradictory instructions.\n- [ ] No unnecessary verbosity tokens.\n- [ ] A\u002FB score improves and violation count stays at zero.\n\n## References\n\n- [references\u002Fprompt-templates.md](references\u002Fprompt-templates.md) — 6 production marketing templates (ad copy, email sequence, social repurposing, landing sections, SEO meta, brand-voice rewrite) plus generic building blocks; each written to be graded by `prompt_tester.py`\n- [references\u002Ftechnique-guide.md](references\u002Ftechnique-guide.md) — technique-selection table for marketing tasks + the LLM-governance stack for marketing teams (claim discipline, disclosure rules, data boundaries, human-review gates)\n- [references\u002Fevaluation-rubric.md](references\u002Fevaluation-rubric.md) — mechanical scoring weights, acceptance gates, marketing quality dimensions, test-suite design, and eval anti-patterns\n- [README.md](README.md)\n\n## Evaluation Design\n\nEach test case should define:\n\n- `input`: realistic production-like input\n- `expected_contains`: required markers\u002Fcontent\n- `forbidden_contains`: disallowed phrases or unsafe content\n- `expected_regex`: required structural patterns\n\nThis enables deterministic grading across prompt variants.\n\n## Versioning Policy\n\n- Use semantic prompt identifiers per feature (`support_classifier`, `ad_copy_shortform`).\n- Record author + change note for every revision.\n- Never overwrite historical versions.\n- Diff before promoting a new prompt to production.\n\n## Rollout Strategy\n\n1. Create baseline prompt version.\n2. Propose candidate prompt.\n3. Run A\u002FB suite against same cases.\n4. Promote only if winner improves average and keeps violation count at zero.\n5. Track post-release feedback and feed new failure cases back into test suite.\n","# Prompt Engineer Toolkit\n\n## Overview\n\nUse this skill to move prompts from ad-hoc drafts to production assets with repeatable testing, versioning, and regression safety. It emphasizes measurable quality over intuition. Apply it when launching a new LLM feature that needs reliable outputs, when prompt quality degrades after model or instruction changes, when multiple team members edit prompts and need history\u002Fdiffs, when you need evidence-based prompt choice for production rollout, or when you want consistent prompt governance across environments.\n\n## Core Capabilities\n\n- A\u002FB prompt evaluation against structured test cases\n- Quantitative scoring for adherence, relevance, and safety checks\n- Prompt version tracking with immutable history and changelog\n- Prompt diffs to review behavior-impacting edits\n- Reusable prompt templates and selection guidance\n- Regression-friendly workflows for model\u002Fprompt updates\n\n## Key Workflows\n\n### 1. Run Prompt A\u002FB Test\n\nPrepare JSON test cases and run:\n\n```bash\npython3 scripts\u002Fprompt_tester.py \\\n  --prompt-a-file prompts\u002Fa.txt \\\n  --prompt-b-file prompts\u002Fb.txt \\\n  --cases-file testcases.json \\\n  --runner-cmd 'my-llm-cli --prompt {prompt} --input {input}' \\\n  --format text\n```\n\nInput can also come from stdin\u002F`--input` JSON payload.\n\n### 2. Choose Winner With Evidence\n\nThe tester scores outputs per case and aggregates:\n\n- expected content coverage\n- forbidden content violations\n- regex\u002Fformat compliance\n- output length sanity\n\nUse the higher-scoring prompt as candidate baseline, then run regression suite.\n\n### 3. Version Prompts\n\n```bash\n# Add version\npython3 scripts\u002Fprompt_versioner.py add \\\n  --name support_classifier \\\n  --prompt-file prompts\u002Fsupport_v3.txt \\\n  --author alice\n\n# Diff versions\npython3 scripts\u002Fprompt_versioner.py diff --name support_classifier --from-version 2 --to-version 3\n\n# Changelog\npython3 scripts\u002Fprompt_versioner.py changelog --name support_classifier\n```\n\n### 4. Regression Loop\n\n1. Store baseline version.\n2. Propose prompt edits.\n3. Re-run A\u002FB test.\n4. Promote only if score and safety constraints improve.\n\n## Script Interfaces\n\n- `python3 scripts\u002Fprompt_tester.py --help`\n  - Reads prompts\u002Fcases from stdin or `--input`\n  - Optional external runner command\n  - Emits text or JSON metrics\n- `python3 scripts\u002Fprompt_versioner.py --help`\n  - Manages prompt history (`add`, `list`, `diff`, `changelog`)\n  - Stores metadata and content snapshots locally\n\n## Pitfalls, Best Practices & Review Checklist\n\n**Avoid these mistakes:**\n1. Picking prompts from single-case outputs — use a realistic, edge-case-rich test suite.\n2. Changing prompt and model simultaneously — always isolate variables.\n3. Missing `must_not_contain` (forbidden-content) checks in evaluation criteria.\n4. Editing prompts without version metadata, author, or change rationale.\n5. Skipping semantic diffs before deploying a new prompt version.\n6. Optimizing one benchmark while harming edge cases — track the full suite.\n7. Model swap without rerunning the baseline A\u002FB suite.\n\n**Before promoting any prompt, confirm:**\n- [ ] Task intent is explicit and unambiguous.\n- [ ] Output schema\u002Fformat is explicit.\n- [ ] Safety and exclusion constraints are explicit.\n- [ ] No contradictory instructions.\n- [ ] No unnecessary verbosity tokens.\n- [ ] A\u002FB score improves and violation count stays at zero.\n\n## References\n\n- [references\u002Fprompt-templates.md](references\u002Fprompt-templates.md) — 6 production marketing templates (ad copy, email sequence, social repurposing, landing sections, SEO meta, brand-voice rewrite) plus generic building blocks; each written to be graded by `prompt_tester.py`\n- [references\u002Ftechnique-guide.md](references\u002Ftechnique-guide.md) — technique-selection table for marketing tasks + the LLM-governance stack for marketing teams (claim discipline, disclosure rules, data boundaries, human-review gates)\n- [references\u002Fevaluation-rubric.md](references\u002Fevaluation-rubric.md) — mechanical scoring weights, acceptance gates, marketing quality dimensions, test-suite design, and eval anti-patterns\n- [README.md](README.md)\n\n## Evaluation Design\n\nEach test case should define:\n\n- `input`: realistic production-like input\n- `expected_contains`: required markers\u002Fcontent\n- `forbidden_contains`: disallowed phrases or unsafe content\n- `expected_regex`: required structural patterns\n\nThis enables deterministic grading across prompt variants.\n\n## Versioning Policy\n\n- Use semantic prompt identifiers per feature (`support_classifier`, `ad_copy_shortform`).\n- Record author + change note for every revision.\n- Never overwrite historical versions.\n- Diff before promoting a new prompt to production.\n\n## Rollout Strategy\n\n1. Create baseline prompt version.\n2. Propose candidate prompt.\n3. Run A\u002FB suite against same cases.\n4. Promote only if winner improves average and keeps violation count at zero.\n5. Track post-release feedback and feed new failure cases back into test suite.\n",{"name":5,"license":15,"metadata":57,"description":7},{"author":58,"updated":59,"version":60,"category":61},"Alireza Rezvani",1772755200000,"1.0.0","marketing","main","0da4485785ee599388900be50db1635489d53056",".agents\u002Fskills\u002Fprompt-engineer-toolkit","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6","https:\u002F\u002Fdisha6.6.thenitishkr.in\u002F","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh","www.thenitishkr","thenitishkr | AI • Cyber-security • Research\r\n","2026-11-08 03:33:25",{"source":8,"skillName":5,"commands":72,"prompt":82,"zipAvailable":83},[73,76,79],{"tool":74,"command":75},"npx","npx skills add Tashima-Tarsh\u002FDisha6.6 --skill prompt-engineer-toolkit",{"tool":77,"command":78},"bunx","bunx skills add Tashima-Tarsh\u002FDisha6.6 --skill prompt-engineer-toolkit",{"tool":80,"command":81},"pnpm","pnpm dlx skills add Tashima-Tarsh\u002FDisha6.6 --skill prompt-engineer-toolkit","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fprompt-engineer-toolkit\u002FSKILL.md",true,[],[86,116,141,166,191,215],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":95,"publishedAt":52},"01M6QRD07D4TGNDK6VJ4EHF8BV","youtube-full","Use when the user needs YouTube transcripts, video search, channel browsing, playlist extraction, or content monitoring. Trigger phrases: 'get the transcript for', 'search YouTube for', 'what are the latest videos on', 'list this playlist', 'monitor this channel', or any request involving a YouTube URL, video ID, or @handle. Do NOT use for downloading video or audio files, YouTube engagement data (likes, comments), or private\u002Fage-restricted videos.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fyoutube-full\u002FSKILL.md",[92],{"categoryNo":93,"categoryName":94,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",[96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115],"youtube full","youtube","full","transcript","search","monitoring","data","Video","Audio","list","files","do","get","age","trigger","URL","for","browsing","request","youtube transcripts",{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":122,"publishedAt":52},"01M6QRCJ3112VYPA97YG7KGMC2","x-twitter-growth","X\u002FTwitter growth engine for building audience, crafting viral content, and analyzing engagement. Use when the user wants to grow on X\u002FTwitter, write tweets or threads, analyze their X profile, research competitors on X, plan a posting strategy, or optimize engagement. Complements social-content (generic multi-platform) with X-specific depth: algorithm mechanics, thread engineering, reply strategy, profile optimization, and competitive intelligence via web search.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fx-twitter-growth\u002FSKILL.md",[],[123,124,125,126,100,127,128,129,130,131,132,133,134,135,136,137,138,139,140,112],"twitter","x twitter growth","growth","research","content","engineering","plan","web search","competitors","analyze","engine","write","strategy","use","platform","grow","posting","competitive",{"skillNo":142,"name":143,"nameZh":6,"description":144,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":145,"categories":146,"keywords":148,"publishedAt":52},"01M6QRBN3EHQNJY42RERP7A149","write-a-skill","Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, build, or author a new skill.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwrite-a-skill\u002FSKILL.md",[147],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[149,134,150,151,152,153,154,155,136,156,157,62,158,159,160,161,162,163,164,165],"write a skill","github","create","https","productivity","matt pocock","direct","example","build","new skill","structure","new agent","resources","with","tree","progressive disclosure","author",{"skillNo":167,"name":168,"nameZh":6,"description":169,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":170,"categories":171,"keywords":172,"publishedAt":52},"01M6QRB6G8P33PNGAF9Y69EJ9T","wrap-up","Close out a launched Claude Managed Agent — recap every primitive the founder now owns, regenerate the single-file overview page, and suggest the next 1-2 upgrades. Use when the user says \"wrap up\", \"close this out\", \"what do I own now\", \"give me the summary\", \"recap the agent\", or when the orchestrator routes phase=wrap-up. primitives_inventory.py tables everything owned (agent, environment, session, memory, outcome, deployment); overview_page.py regenerates a self-contained .\u002Fmy-agent\u002Fagent-overview.html; upgrade_suggester.py ranks the next moves from recorded deferrals plus standing hardening steps. Companion to run-without-you; the last stop before phase=done.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwrap-up\u002FSKILL.md",[],[173,174,175,176,177,178,179,180,181,136,182,107,183,184,185,186,187,188,189,190],"wrap up","up","wrap","gemini","deployment","run","file","hardening","closeout","stop","upgrade","founder","close","companion","you","tables","directions","phase",{"skillNo":192,"name":193,"nameZh":6,"description":194,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":195,"categories":196,"keywords":198,"publishedAt":52},"01M6QRA5AYC1RBFZ39GTWGS3N8","workflow-builder","Design and write deterministic multi-agent workflow scripts (.js files in .claude\u002Fworkflows\u002F) for Claude Code's Workflow tool. Use when a user wants to build, create, author, scaffold, or run a custom Claude Code workflow, orchestrate sub-agents (fan-out, pipeline, loop, judge-panel), or automate a repeatable multi-step task across fresh-context agents.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fworkflow-builder\u002FSKILL.md",[197],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[199,200,201,202,203,151,178,204,205,206,207,208,134,209,106,210,211,212,213,214],"workflow","workflow builder","builder","design","workflows","code","orchestrate","pipeline","loop","multi-agent","context","across","fresh","scripts","judge","claude code workflow",{"skillNo":216,"name":217,"nameZh":6,"description":218,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":219,"categories":220,"keywords":221,"publishedAt":52},"01M6QR7QMCZESKQA0ERW1E657M","weekly-review","Use when someone wants to run a weekly review, close open loops, audit stalled projects and commitments, get their system back to trusted, restart a lapsed review habit, or says \"\u002Fcs:weekly-review\". Walks David Allen's three-phase loop — GET CLEAR, GET CURRENT, GET CREATIVE — with deterministic scripts that inventory open loops, gate the checklist with named gaps, and score commitment health 0-100.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fweekly-review\u002FSKILL.md",[],[222,223,224,225,226,227,228,229,46,207,230,231,232,233,234,235,108,236,237,190],"review","weekly review","weekly","deterministic scripts","reflect","feeds","inventory","open","projects","project-management","scanner","conversation","back","project","sprint","cadence"]