[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AMK0F56WN69C59P2MN6RQV":3,"skill-same:01M7AMK0F56WN69C59P2MN6RQV":75},{"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":30,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M7AMK0F56WN69C59P2MN6RQV","senior-prompt-engineer",null,"Use when the user asks to optimize prompts, design prompt templates, evaluate LLM outputs with an eval set, measure RAG retrieval quality, validate agent\u002Ftool configurations, analyze token usage, or design structured-output contracts. Covers eval-driven prompt iteration, RAG metrics (relevance, faithfulness, coverage), agent workflow validation, and token\u002Fcost budgeting — all model-agnostic, with three stdlib Python tools.","Cyrilthetecchieee\u002Fcyril-code-","Cyrilthetecchieee","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F219787998?v=4","01M7AF0MMMKRAA0H61XMJPV92H","Julian Cyril D ","01M7AF0MQ10AVG6QJQ1C2BC0F5",2,"MIT","https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Fengineering-team\u002Fskills\u002Fsenior-prompt-engineer\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: \"senior-prompt-engineer\"\ndescription: Use when the user asks to optimize prompts, design prompt templates, evaluate LLM outputs with an eval set, measure RAG retrieval quality, validate agent\u002Ftool configurations, analyze token usage, or design structured-output contracts. Covers eval-driven prompt iteration, RAG metrics (relevance, faithfulness, coverage), agent workflow validation, and token\u002Fcost budgeting — all model-agnostic, with three stdlib Python tools.\n---\n\n# Senior Prompt Engineer\n\nEval-driven prompt engineering, RAG quality measurement, and agent workflow validation. Everything here is **model-agnostic by design**: techniques are framed by what they do, not by which model generation they were observed on, and the tools never hardcode model IDs or pricing — you supply your provider's current rates when you want dollar figures.\n\n## Operating Rules\n\n1. **Never change a prompt without a baseline.** Capture metrics first (`--analyze --output baseline.json`), then compare every iteration against it.\n2. **Eval set before optimization.** 10–20 representative cases with expected outputs minimum. If the user has no eval set, build one with them before touching the prompt — optimizing against vibes is the #1 failure mode.\n3. **Prefer platform features over prompt hacks.** If the provider offers native structured outputs \u002F JSON schema enforcement, tool-use APIs, or prompt caching, use those instead of \"respond ONLY with JSON\" incantations. Prompt-level format enforcement is the fallback, not the default.\n4. **Current-generation models need less scaffolding.** Don't add chain-of-thought boilerplate, role framing, or few-shot examples reflexively — frontier models often do worse with redundant scaffolding. Add each element only when the eval set shows it helps.\n5. **Cost numbers are always user-supplied.** Look up the provider's current per-Mtok pricing and pass it via `--price-per-mtok` (never trust a cached price table — including any you remember).\n\n## Tools (exact CLIs, all stdlib)\n\n### 1. Prompt Optimizer — `scripts\u002Fprompt_optimizer.py`\n\nStatic analysis: token estimate, clarity\u002Fstructure scores (0–100), ambiguity + redundancy detection, few-shot example extraction.\n\n```bash\n# Full analysis (human-readable report)\npython3 scripts\u002Fprompt_optimizer.py prompt.txt --analyze\n\n# Save machine-readable baseline for later comparison\npython3 scripts\u002Fprompt_optimizer.py prompt.txt --analyze --json --output baseline.json\n\n# Token estimate; cost only if you supply your provider's current rate\npython3 scripts\u002Fprompt_optimizer.py prompt.txt --tokens --model claude --price-per-mtok 3.00\n\n# Whitespace\u002Fredundancy-trimmed version\npython3 scripts\u002Fprompt_optimizer.py prompt.txt --optimize --output optimized.txt\n\n# Extract Input\u002FOutput few-shot pairs to JSON\npython3 scripts\u002Fprompt_optimizer.py prompt.txt --extract-examples --output examples.json\n\n# Compare a revision against the saved baseline\npython3 scripts\u002Fprompt_optimizer.py optimized.txt --analyze --compare baseline.json\n```\n\n`--model` accepts any string; only the tokenizer family is inferred (names containing \"claude\" → 3.5 chars\u002Ftoken, otherwise 4.0). Exit 0 on success, 1 on missing file.\n\n### 2. RAG Evaluator — `scripts\u002Frag_evaluator.py`\n\nMeasures retrieval and grounding quality from two JSON files (formats printed in `--help`).\n\n```bash\npython3 scripts\u002Frag_evaluator.py --contexts retrieved.json --questions eval_set.json\npython3 scripts\u002Frag_evaluator.py --contexts ctx.json --questions q.json --k 10 --json\npython3 scripts\u002Frag_evaluator.py --contexts ctx.json --questions q.json --output report.json --verbose\npython3 scripts\u002Frag_evaluator.py --contexts ctx.json --questions q.json --compare baseline_report.json\n```\n\nReports context relevance, precision@k, coverage, answer faithfulness, groundedness. Treat relevance \u003C 0.80 as a retrieval problem (chunking\u002Fembedding\u002Ffiltering), not a prompt problem — fix retrieval before rewriting the generation prompt.\n\n### 3. Agent Orchestrator — `scripts\u002Fagent_orchestrator.py`\n\nValidates agent configs (YAML\u002FJSON): tool wiring, missing required config, loop risk, token estimates.\n\n```bash\npython3 scripts\u002Fagent_orchestrator.py agent.yaml --validate\npython3 scripts\u002Fagent_orchestrator.py agent.yaml --visualize --format mermaid\npython3 scripts\u002Fagent_orchestrator.py agent.yaml --estimate-cost --runs 100 \\\n    --input-price-per-mtok 3.00 --output-price-per-mtok 15.00\n```\n\nWithout the two price flags, `--estimate-cost` reports token estimates only. The `model:` field in the config is informational — any model name is accepted.\n\n## Workflows\n\n### Prompt Optimization (eval-gated)\n\n1. **Baseline:** `python3 scripts\u002Fprompt_optimizer.py current_prompt.txt --analyze --json --output baseline.json`\n2. **Diagnose** from the report: ambiguous verbs (\"analyze\", \"handle\"), redundant blocks, missing output contract, token waste.\n3. **Apply one change at a time**, in this order of leverage:\n   | Symptom | Fix |\n   |---------|-----|\n   | Malformed\u002Funparseable output | Native structured outputs \u002F JSON schema if the API supports it; explicit schema-in-prompt otherwise |\n   | Inconsistent answers across runs | Tighten instructions + add 2–3 contrastive examples (one near-miss showing what NOT to do) |\n   | Misses edge cases | Enumerate the edge cases explicitly; add a \"when uncertain, do X\" rule |\n   | Token bloat on repeated calls | Move stable prefix (system rules, examples) first so prompt caching applies; trim redundancy |\n   | Wrong reasoning on hard cases | Ask for stepwise reasoning *in a scratch field the consumer ignores*, or use the provider's extended-thinking mode |\n4. **Re-analyze and compare:** `python3 scripts\u002Fprompt_optimizer.py revised.txt --analyze --compare baseline.json`\n5. **Eval gate (must pass before shipping):** run the revised prompt over the eval set, write per-case pass\u002Ffail to `eval_results.json`, then assert:\n   ```bash\n   python3 scripts\u002Fprompt_optimizer.py revised.txt --analyze --json --output revised.json \\\n     && python3 -c \"\n   import json, sys\n   r = json.load(open('revised.json')); b = json.load(open('baseline.json'))\n   ok = r['clarity_score'] >= b['clarity_score'] and r['token_count'] \u003C= b['token_count'] * 1.10\n   sys.exit(0 if ok else 1)\"\n   echo \"gate exit=$?\"   # 0 = ship; 1 = regression, iterate again\n   ```\n   Pair this structural gate with your task-level eval: the revision must not lose any previously-passing eval case (no-regression rule).\n\n### Few-Shot Example Design\n\n1. Define the task contract first (input shape, output shape, edge-case policy).\n2. Start with **zero examples** and measure — current models often need none. Add examples only for failure clusters the eval reveals.\n3. When adding: 3–5 max, ordered simple → edge → negative (what NOT to extract), formatted identically to the real output contract.\n4. Validate consistency: `python3 scripts\u002Fprompt_optimizer.py prompt_with_examples.txt --extract-examples --output examples.json` and inspect that every extracted pair parses against your schema.\n5. Re-run the eval set; if a case passes only because it resembles an example, add a held-out variant to the eval set.\n\n### Structured Output Design\n\n1. Write the JSON Schema first (types, enums, required, maxLength).\n2. **Prefer API-native enforcement**: structured-outputs \u002F response-schema \u002F tool-call parameters guarantee shape; prompt text cannot.\n3. Fallback (API without schema support): include the schema rendered as field-by-field rules + one valid example, and instruct \"output only the JSON object\".\n4. Gate: pipe 10 eval outputs through a schema validator (`python3 -c \"import json,sys; [json.loads(l) for l in sys.stdin]\"` at minimum); 10\u002F10 must parse, else return to step 2.\n\n### RAG Tuning Loop\n\n1. Build `questions.json` (id, question, reference answer) and capture current retrievals to `contexts.json`.\n2. `python3 scripts\u002Frag_evaluator.py --contexts contexts.json --questions questions.json --output rag_baseline.json`\n3. Fix the **lowest metric first**: relevance → chunking\u002Fembeddings\u002Fmetadata filters; faithfulness → grounding instructions + \"answer only from context\" + citation requirement; coverage → retrieval k \u002F query expansion.\n4. Gate: `python3 scripts\u002Frag_evaluator.py --contexts new_contexts.json --questions questions.json --compare rag_baseline.json` — every metric must be ≥ baseline; any regression blocks the change.\n\n### Agent Config Review\n\n1. `python3 scripts\u002Fagent_orchestrator.py agent.yaml --validate` — must exit with VALIDATION PASSED; fix every error and warning (missing tool config, unbounded iterations, loop risk).\n2. Check context discipline: each tool description ≤ 1–2 sentences, tool count minimal for the job, stable system prompt placed first (cache-friendly), iteration cap + early-exit condition present.\n3. Budget: `--estimate-cost --runs N` with your current prices; if cost\u002Frun exceeds budget, cut tools or context before downgrading the model.\n\n## References\n\n| File | Contains | Load when user asks about |\n|------|----------|---------------------------|\n| `references\u002Fprompt_engineering_patterns.md` | 10 prompt patterns with input\u002Foutput examples | \"which pattern?\", few-shot design, decomposition, meta-prompting |\n| `references\u002Fllm_evaluation_frameworks.md` | Eval metrics, scoring methods, A\u002FB testing | \"how to evaluate?\", \"measure quality\", \"compare prompts\" |\n| `references\u002Fagentic_system_design.md` | Agent architectures (ReAct, Plan-Execute, Tool Use) | \"build agent\", \"tool calling\", \"multi-agent\" |\n\n## Related Skills\n\n- `engineering-team\u002Fskills\u002Fsenior-ml-engineer` — model deployment and serving (this skill stops at the prompt\u002Feval layer)\n- `engineering\u002Frag-architect` — RAG system architecture (this skill measures RAG quality; that one designs the pipeline)\n- `engineering\u002Fagent-designer` — full agent system design (this skill validates configs; that one designs the architecture)\n","# Senior Prompt Engineer\n\nEval-driven prompt engineering, RAG quality measurement, and agent workflow validation. Everything here is **model-agnostic by design**: techniques are framed by what they do, not by which model generation they were observed on, and the tools never hardcode model IDs or pricing — you supply your provider's current rates when you want dollar figures.\n\n## Operating Rules\n\n1. **Never change a prompt without a baseline.** Capture metrics first (`--analyze --output baseline.json`), then compare every iteration against it.\n2. **Eval set before optimization.** 10–20 representative cases with expected outputs minimum. If the user has no eval set, build one with them before touching the prompt — optimizing against vibes is the #1 failure mode.\n3. **Prefer platform features over prompt hacks.** If the provider offers native structured outputs \u002F JSON schema enforcement, tool-use APIs, or prompt caching, use those instead of \"respond ONLY with JSON\" incantations. Prompt-level format enforcement is the fallback, not the default.\n4. **Current-generation models need less scaffolding.** Don't add chain-of-thought boilerplate, role framing, or few-shot examples reflexively — frontier models often do worse with redundant scaffolding. Add each element only when the eval set shows it helps.\n5. **Cost numbers are always user-supplied.** Look up the provider's current per-Mtok pricing and pass it via `--price-per-mtok` (never trust a cached price table — including any you remember).\n\n## Tools (exact CLIs, all stdlib)\n\n### 1. Prompt Optimizer — `scripts\u002Fprompt_optimizer.py`\n\nStatic analysis: token estimate, clarity\u002Fstructure scores (0–100), ambiguity + redundancy detection, few-shot example extraction.\n\n```bash\n# Full analysis (human-readable report)\npython3 scripts\u002Fprompt_optimizer.py prompt.txt --analyze\n\n# Save machine-readable baseline for later comparison\npython3 scripts\u002Fprompt_optimizer.py prompt.txt --analyze --json --output baseline.json\n\n# Token estimate; cost only if you supply your provider's current rate\npython3 scripts\u002Fprompt_optimizer.py prompt.txt --tokens --model claude --price-per-mtok 3.00\n\n# Whitespace\u002Fredundancy-trimmed version\npython3 scripts\u002Fprompt_optimizer.py prompt.txt --optimize --output optimized.txt\n\n# Extract Input\u002FOutput few-shot pairs to JSON\npython3 scripts\u002Fprompt_optimizer.py prompt.txt --extract-examples --output examples.json\n\n# Compare a revision against the saved baseline\npython3 scripts\u002Fprompt_optimizer.py optimized.txt --analyze --compare baseline.json\n```\n\n`--model` accepts any string; only the tokenizer family is inferred (names containing \"claude\" → 3.5 chars\u002Ftoken, otherwise 4.0). Exit 0 on success, 1 on missing file.\n\n### 2. RAG Evaluator — `scripts\u002Frag_evaluator.py`\n\nMeasures retrieval and grounding quality from two JSON files (formats printed in `--help`).\n\n```bash\npython3 scripts\u002Frag_evaluator.py --contexts retrieved.json --questions eval_set.json\npython3 scripts\u002Frag_evaluator.py --contexts ctx.json --questions q.json --k 10 --json\npython3 scripts\u002Frag_evaluator.py --contexts ctx.json --questions q.json --output report.json --verbose\npython3 scripts\u002Frag_evaluator.py --contexts ctx.json --questions q.json --compare baseline_report.json\n```\n\nReports context relevance, precision@k, coverage, answer faithfulness, groundedness. Treat relevance \u003C 0.80 as a retrieval problem (chunking\u002Fembedding\u002Ffiltering), not a prompt problem — fix retrieval before rewriting the generation prompt.\n\n### 3. Agent Orchestrator — `scripts\u002Fagent_orchestrator.py`\n\nValidates agent configs (YAML\u002FJSON): tool wiring, missing required config, loop risk, token estimates.\n\n```bash\npython3 scripts\u002Fagent_orchestrator.py agent.yaml --validate\npython3 scripts\u002Fagent_orchestrator.py agent.yaml --visualize --format mermaid\npython3 scripts\u002Fagent_orchestrator.py agent.yaml --estimate-cost --runs 100 \\\n    --input-price-per-mtok 3.00 --output-price-per-mtok 15.00\n```\n\nWithout the two price flags, `--estimate-cost` reports token estimates only. The `model:` field in the config is informational — any model name is accepted.\n\n## Workflows\n\n### Prompt Optimization (eval-gated)\n\n1. **Baseline:** `python3 scripts\u002Fprompt_optimizer.py current_prompt.txt --analyze --json --output baseline.json`\n2. **Diagnose** from the report: ambiguous verbs (\"analyze\", \"handle\"), redundant blocks, missing output contract, token waste.\n3. **Apply one change at a time**, in this order of leverage:\n   | Symptom | Fix |\n   |---------|-----|\n   | Malformed\u002Funparseable output | Native structured outputs \u002F JSON schema if the API supports it; explicit schema-in-prompt otherwise |\n   | Inconsistent answers across runs | Tighten instructions + add 2–3 contrastive examples (one near-miss showing what NOT to do) |\n   | Misses edge cases | Enumerate the edge cases explicitly; add a \"when uncertain, do X\" rule |\n   | Token bloat on repeated calls | Move stable prefix (system rules, examples) first so prompt caching applies; trim redundancy |\n   | Wrong reasoning on hard cases | Ask for stepwise reasoning *in a scratch field the consumer ignores*, or use the provider's extended-thinking mode |\n4. **Re-analyze and compare:** `python3 scripts\u002Fprompt_optimizer.py revised.txt --analyze --compare baseline.json`\n5. **Eval gate (must pass before shipping):** run the revised prompt over the eval set, write per-case pass\u002Ffail to `eval_results.json`, then assert:\n   ```bash\n   python3 scripts\u002Fprompt_optimizer.py revised.txt --analyze --json --output revised.json \\\n     && python3 -c \"\n   import json, sys\n   r = json.load(open('revised.json')); b = json.load(open('baseline.json'))\n   ok = r['clarity_score'] >= b['clarity_score'] and r['token_count'] \u003C= b['token_count'] * 1.10\n   sys.exit(0 if ok else 1)\"\n   echo \"gate exit=$?\"   # 0 = ship; 1 = regression, iterate again\n   ```\n   Pair this structural gate with your task-level eval: the revision must not lose any previously-passing eval case (no-regression rule).\n\n### Few-Shot Example Design\n\n1. Define the task contract first (input shape, output shape, edge-case policy).\n2. Start with **zero examples** and measure — current models often need none. Add examples only for failure clusters the eval reveals.\n3. When adding: 3–5 max, ordered simple → edge → negative (what NOT to extract), formatted identically to the real output contract.\n4. Validate consistency: `python3 scripts\u002Fprompt_optimizer.py prompt_with_examples.txt --extract-examples --output examples.json` and inspect that every extracted pair parses against your schema.\n5. Re-run the eval set; if a case passes only because it resembles an example, add a held-out variant to the eval set.\n\n### Structured Output Design\n\n1. Write the JSON Schema first (types, enums, required, maxLength).\n2. **Prefer API-native enforcement**: structured-outputs \u002F response-schema \u002F tool-call parameters guarantee shape; prompt text cannot.\n3. Fallback (API without schema support): include the schema rendered as field-by-field rules + one valid example, and instruct \"output only the JSON object\".\n4. Gate: pipe 10 eval outputs through a schema validator (`python3 -c \"import json,sys; [json.loads(l) for l in sys.stdin]\"` at minimum); 10\u002F10 must parse, else return to step 2.\n\n### RAG Tuning Loop\n\n1. Build `questions.json` (id, question, reference answer) and capture current retrievals to `contexts.json`.\n2. `python3 scripts\u002Frag_evaluator.py --contexts contexts.json --questions questions.json --output rag_baseline.json`\n3. Fix the **lowest metric first**: relevance → chunking\u002Fembeddings\u002Fmetadata filters; faithfulness → grounding instructions + \"answer only from context\" + citation requirement; coverage → retrieval k \u002F query expansion.\n4. Gate: `python3 scripts\u002Frag_evaluator.py --contexts new_contexts.json --questions questions.json --compare rag_baseline.json` — every metric must be ≥ baseline; any regression blocks the change.\n\n### Agent Config Review\n\n1. `python3 scripts\u002Fagent_orchestrator.py agent.yaml --validate` — must exit with VALIDATION PASSED; fix every error and warning (missing tool config, unbounded iterations, loop risk).\n2. Check context discipline: each tool description ≤ 1–2 sentences, tool count minimal for the job, stable system prompt placed first (cache-friendly), iteration cap + early-exit condition present.\n3. Budget: `--estimate-cost --runs N` with your current prices; if cost\u002Frun exceeds budget, cut tools or context before downgrading the model.\n\n## References\n\n| File | Contains | Load when user asks about |\n|------|----------|---------------------------|\n| `references\u002Fprompt_engineering_patterns.md` | 10 prompt patterns with input\u002Foutput examples | \"which pattern?\", few-shot design, decomposition, meta-prompting |\n| `references\u002Fllm_evaluation_frameworks.md` | Eval metrics, scoring methods, A\u002FB testing | \"how to evaluate?\", \"measure quality\", \"compare prompts\" |\n| `references\u002Fagentic_system_design.md` | Agent architectures (ReAct, Plan-Execute, Tool Use) | \"build agent\", \"tool calling\", \"multi-agent\" |\n\n## Related Skills\n\n- `engineering-team\u002Fskills\u002Fsenior-ml-engineer` — model deployment and serving (this skill stops at the prompt\u002Feval layer)\n- `engineering\u002Frag-architect` — RAG system architecture (this skill measures RAG quality; that one designs the pipeline)\n- `engineering\u002Fagent-designer` — full agent system design (this skill validates configs; that one designs the architecture)\n",{"name":5,"description":7},"main","57e7aa6b6e03bce1a7d7862ba9c2ec312f7f19b5","src\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Fengineering-team\u002Fskills\u002Fsenior-prompt-engineer",0,"https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-","https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee","https:\u002F\u002Fwithcyril.me\u002F","Hi, I’m Julian Cyril D, a Computer Science and Business Systems student at PSNACET.\r\nI’m passionate about full-stack development, UI\u002FUX design, and building sma","2026-11-04 23:28:50",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add Cyrilthetecchieee\u002Fcyril-code- --skill senior-prompt-engineer",{"tool":39,"command":40},"bunx","bunx skills add Cyrilthetecchieee\u002Fcyril-code- --skill senior-prompt-engineer",{"tool":42,"command":43},"pnpm","pnpm dlx skills add Cyrilthetecchieee\u002Fcyril-code- --skill senior-prompt-engineer","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Fengineering-team\u002Fskills\u002Fsenior-prompt-engineer\u002FSKILL.md",true,[47,53,57,61,67,71],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fagentic_system_design.md","REFERENCE","参考文档",21700,"https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Fengineering-team\u002Fskills\u002Fsenior-prompt-engineer\u002Freferences\u002Fagentic_system_design.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fllm_evaluation_frameworks.md",13303,"https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Fengineering-team\u002Fskills\u002Fsenior-prompt-engineer\u002Freferences\u002Fllm_evaluation_frameworks.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fprompt_engineering_patterns.md",13675,"https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Fengineering-team\u002Fskills\u002Fsenior-prompt-engineer\u002Freferences\u002Fprompt_engineering_patterns.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fagent_orchestrator.py.txt","SCRIPT","脚本",21450,"https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Fengineering-team\u002Fskills\u002Fsenior-prompt-engineer\u002Fscripts\u002Fagent_orchestrator.py.txt",{"path":68,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Fprompt_optimizer.py.txt",19039,"https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Fengineering-team\u002Fskills\u002Fsenior-prompt-engineer\u002Fscripts\u002Fprompt_optimizer.py.txt",{"path":72,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":73,"sourceHtmlUrl":74},"scripts\u002Frag_evaluator.py.txt",20362,"https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Fengineering-team\u002Fskills\u002Fsenior-prompt-engineer\u002Fscripts\u002Frag_evaluator.py.txt",[76,85,92,100,107,114],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":80,"licenseFileUrl":81,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M7AQV6CYX8RMC78420V9WZ62","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Fwebapp-testing\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},"01M7AQV2895N3S1MEX6K76G6G2","youtube-downloader","Download YouTube videos with customizable quality and format options. Use this skill when the user asks to download, save, or grab YouTube videos. Supports various quality settings (best, 1080p, 720p, 480p, 360p), multiple formats (mp4, webm, mkv), and audio-only downloads as MP3.","https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Fvideo-downloader\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":80,"licenseFileUrl":96,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M7AQTRNX62DNKVZ5GXEHRBKB","theme-factory","Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors\u002Ffonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.","https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Ftheme-factory\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Ftheme-factory\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":19},"01M7AQTNNVHAAN9H6DA8T6ZVE0","template-skill","Replace with description of the skill and when Claude should use it.","https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Ftemplate-skill\u002FSKILL.md",[],[],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":19},"01M7AQTJ3MQ6AKX152MEX2MYCC","tailored-resume-generator","Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances","https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Ftailored-resume-generator\u002FSKILL.md",[],[],{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":80,"licenseFileUrl":118,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":19},"01M7AQTD7D5MYET2YWG7HG9WM3","slack-gif-creator","Toolkit for creating animated GIFs optimized for Slack, with validators for size constraints and composable animation primitives. This skill applies when users request animated GIFs or emoji animations for Slack from descriptions like \"make me a GIF for Slack of X doing Y\".","https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Fslack-gif-creator\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Fslack-gif-creator\u002FSKILL.md",[],[]]