[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DJCC1GEDQM14V87P7W0AFK":3,"skill-same:01M6DJCC1GEDQM14V87P7W0AFK":98},{"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":23,"publishedAt":41,"linkOnly":42,"markdownContent":43,"markdownBody":44,"frontMatter":45,"refName":50,"commitSha":51,"skillDirectory":52,"forksCount":14,"repositoryHtmlUrl":53,"repositoryHomepageUrl":6,"ownerHtmlUrl":54,"ownerBlogUrl":55,"ownerDescription":56,"updatedAt":57,"install":58,"resources":71},"01M6DJCC1GEDQM14V87P7W0AFK","agent-ste",null,"Use when rewriting user or planner instructions before planning or execution; when prompts contain vague verbs (optimize, improve, better, appropriate, reasonable, quickly, carefully, as needed, if necessary); when multiple agents or LLMs must interpret the same task reproducibly; when an instruction lacks explicit actor, inputs, outputs, success criteria, failure conditions, ordering, or scope; or when preparing handoffs between orchestrators and workers.","dasobral\u002Fskills","dasobral","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F108470360?v=4","01M6DJBRR588S4TSNFT0ZYY6BV","Daniel SB","01M6DJBRWBDEBPCQ874SWDZWZR",0,"MIT","https:\u002F\u002Fgithub.com\u002Fdasobral\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fagent-ste\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40],"agent ste","ste","use","scope","as","optimize","task","workers","prompts","export","llms","user","instructions","planner","improve","execution","planning","2026-11-10 10:12:30",false,"---\nname: agent-ste\ndescription: 'Use when rewriting user or planner instructions before planning or execution;\n  when prompts contain vague verbs (optimize, improve, better, appropriate, reasonable,\n  quickly, carefully, as needed, if necessary); when multiple agents or LLMs must\n  interpret the same task reproducibly; when an instruction lacks explicit actor,\n  inputs, outputs, success criteria, failure conditions, ordering, or scope; or when\n  preparing handoffs between orchestrators and workers.\n\n  '\nlicense: MIT\nmetadata:\n  source_platform: portable\n  ingested_by: skills-export\n---\n\n# Agent STE (Agent Simplified Technical English)\n\nRewrite instructions into a controlled natural language optimized for LLM\nexecution: explicit, measurable, ordered, and reproducible across models.\n\n**Core principle:** Prefer deterministic execution over natural prose.\nExplicitness beats brevity. Unambiguous wording beats elegant wording.\n\n**Inspiration:** Principles behind ASD-STE100 (controlled language for clarity).\nThis skill is **not** ASD-STE100 and does not claim compliance. See\n`references\u002Fprinciples.md`.\n\n## When to Use\n\n- Before planning or executing non-trivial work\n- Before dispatching subagents or cross-model handoffs\n- When the prompt contains forbidden vague language (see below)\n- When success would be judged differently by two competent agents\n\n**When NOT to use**\n\n- Pure chitchat or one-line factual Q&A with no side effects\n- Already-formal specs (OpenAPI, JSON Schema, RFC text) that need no rewrite\n- Emergency stop \u002F safety refusal wording that must stay short and human\n\n## Transformation Algorithm\n\nExecute these steps in order. Do not skip steps under time pressure.\n\n1. **Objective** — State exactly one primary deliverable in one sentence. Do not\n   join independent goals with “and” inside `OBJECTIVE`.\n2. **Entities** — List every actor, system, file, service, and artifact. Assign\n   a stable identifier (`SVC-API`, `FILE-auth.ts`, `AGENT-worker`).\n3. **Glossary** — For each critical term, fix one meaning. Ban synonyms for\n   those terms inside the instruction.\n4. **Demote vagueness** — Replace every forbidden pattern with a measurable or\n   observable statement (`references\u002Frules.md`).\n5. **Split actions** — One action per sentence. One objective per instruction\n   block. Use a numbered list for ordering.\n6. **Fill slots** — Complete the template in `templates\u002Finstruction-block.md`\n   (actor, object, inputs, outputs, assumptions, constraints, preconditions,\n   postconditions, invariants, success, failure, rollback, idempotency,\n   side effects, permissions, dependencies, artifacts, validation, checklist).\n7. **Scope fence** — State what is in scope and what is out of scope.\n8. **Self-check** — Answer every item in `references\u002Fchecklist.md` with YES\u002FNO.\n   If any required item is NO, revise before planning or execution.\n\n## Mandatory Rules (summary)\n\nFull normative list: `references\u002Frules.md`.\n\n| Rule | Why |\n|------|-----|\n| One action per sentence | Prevents partial execution and skipped conjuncts |\n| One objective per instruction block | Stops silent scope expansion |\n| One meaning per critical word | Removes synonym drift across LLMs |\n| Explicit actor + object | No orphan imperatives |\n| Explicit inputs + outputs | Makes dataflow checkable |\n| Explicit success + failure | Defines done vs retry vs abort |\n| Explicit ordering | `1 → 2 → 3` or mark `PARALLEL` |\n| Explicit units + identifiers | No “soon”, “large”, “the file” |\n| No pronouns when ≥2 entities | “It\u002Fthey\u002Fthis” is an entity bug |\n| No forbidden vague lexicon | Forces observables |\n\n## Forbidden Patterns (detect and rewrite)\n\n`optimize` · `improve` · `better` · `appropriate` · `reasonable` · `quickly` ·\n`carefully` · `if necessary` · `as needed` · `etc.` · `and so on` · `normally` ·\n`probably` · `maybe` · `somehow` · `tidy` · `harden` · `fix up` ·\n`make sure` (without a checkable predicate) · `satisfied` · `obvious`\n\nRewrite table and agent-oriented slots: `references\u002Frules.md`.\n\n## Output Contract\n\nEmit an Agent STE block using `templates\u002Finstruction-block.md`. Then either:\n\n- execute that block, or\n- hand it to the next agent unchanged\n\nDo not plan from the original vague prompt once an Agent STE rewrite exists.\n\n## Examples and Spec\n\n- Worked rewrites (coding, DevOps, docs, Git, research, debug, infra, security):\n  `references\u002Fexamples.md`\n- Objective compliance checklist: `references\u002Fchecklist.md`\n- Future machine-checkable spec (MUST\u002FSHOULD\u002FMAY, JSON\u002FYAML, linting, MCP):\n  `references\u002Fspec-v1.md`\n\n## Limitations\n\n- Does not replace domain expertise or formal verification\n- Cannot invent missing requirements; mark `UNKNOWN` and halt or ask\n- Numeric targets require a source (user, SLO, benchmark); else state\n  `METRIC-SOURCE: UNKNOWN` and do not fabricate thresholds\n- Over-application to trivial chat wastes tokens — respect When NOT to use\n- Not a license to ignore higher-priority safety or repository rules\n\n## Rationalizations — Do Not Skip\n\n| Excuse | Reality |\n|--------|---------|\n| \"Too simple to rewrite\" | Simple vague prompts still fork across models |\n| \"No time for slots\" | Missing success criteria causes expensive rework |\n| \"Context implies the metric\" | Another LLM does not share your implied context |\n| \"I'll keep optimize but add detail\" | Forbidden lexicon remains non-deterministic |\n| \"Pronouns are fine; there are only two things\" | Two things is exactly when pronouns collide |\n| \"Rollback is overkill for a docs tweak\" | State `ROLLBACK: none — read-only` explicitly |\n| \"One OBJECTIVE can list three goals with and\" | That is three blocks or gated phases — split them |\n\n**Red flags — STOP and rewrite:** residual `etc.`; success = “looks good”;\nactor missing; two actions joined by “and”; synonym pairs for the same concept;\n`if necessary` without a boolean predicate.\n","# Agent STE (Agent Simplified Technical English)\n\nRewrite instructions into a controlled natural language optimized for LLM\nexecution: explicit, measurable, ordered, and reproducible across models.\n\n**Core principle:** Prefer deterministic execution over natural prose.\nExplicitness beats brevity. Unambiguous wording beats elegant wording.\n\n**Inspiration:** Principles behind ASD-STE100 (controlled language for clarity).\nThis skill is **not** ASD-STE100 and does not claim compliance. See\n`references\u002Fprinciples.md`.\n\n## When to Use\n\n- Before planning or executing non-trivial work\n- Before dispatching subagents or cross-model handoffs\n- When the prompt contains forbidden vague language (see below)\n- When success would be judged differently by two competent agents\n\n**When NOT to use**\n\n- Pure chitchat or one-line factual Q&A with no side effects\n- Already-formal specs (OpenAPI, JSON Schema, RFC text) that need no rewrite\n- Emergency stop \u002F safety refusal wording that must stay short and human\n\n## Transformation Algorithm\n\nExecute these steps in order. Do not skip steps under time pressure.\n\n1. **Objective** — State exactly one primary deliverable in one sentence. Do not\n   join independent goals with “and” inside `OBJECTIVE`.\n2. **Entities** — List every actor, system, file, service, and artifact. Assign\n   a stable identifier (`SVC-API`, `FILE-auth.ts`, `AGENT-worker`).\n3. **Glossary** — For each critical term, fix one meaning. Ban synonyms for\n   those terms inside the instruction.\n4. **Demote vagueness** — Replace every forbidden pattern with a measurable or\n   observable statement (`references\u002Frules.md`).\n5. **Split actions** — One action per sentence. One objective per instruction\n   block. Use a numbered list for ordering.\n6. **Fill slots** — Complete the template in `templates\u002Finstruction-block.md`\n   (actor, object, inputs, outputs, assumptions, constraints, preconditions,\n   postconditions, invariants, success, failure, rollback, idempotency,\n   side effects, permissions, dependencies, artifacts, validation, checklist).\n7. **Scope fence** — State what is in scope and what is out of scope.\n8. **Self-check** — Answer every item in `references\u002Fchecklist.md` with YES\u002FNO.\n   If any required item is NO, revise before planning or execution.\n\n## Mandatory Rules (summary)\n\nFull normative list: `references\u002Frules.md`.\n\n| Rule | Why |\n|------|-----|\n| One action per sentence | Prevents partial execution and skipped conjuncts |\n| One objective per instruction block | Stops silent scope expansion |\n| One meaning per critical word | Removes synonym drift across LLMs |\n| Explicit actor + object | No orphan imperatives |\n| Explicit inputs + outputs | Makes dataflow checkable |\n| Explicit success + failure | Defines done vs retry vs abort |\n| Explicit ordering | `1 → 2 → 3` or mark `PARALLEL` |\n| Explicit units + identifiers | No “soon”, “large”, “the file” |\n| No pronouns when ≥2 entities | “It\u002Fthey\u002Fthis” is an entity bug |\n| No forbidden vague lexicon | Forces observables |\n\n## Forbidden Patterns (detect and rewrite)\n\n`optimize` · `improve` · `better` · `appropriate` · `reasonable` · `quickly` ·\n`carefully` · `if necessary` · `as needed` · `etc.` · `and so on` · `normally` ·\n`probably` · `maybe` · `somehow` · `tidy` · `harden` · `fix up` ·\n`make sure` (without a checkable predicate) · `satisfied` · `obvious`\n\nRewrite table and agent-oriented slots: `references\u002Frules.md`.\n\n## Output Contract\n\nEmit an Agent STE block using `templates\u002Finstruction-block.md`. Then either:\n\n- execute that block, or\n- hand it to the next agent unchanged\n\nDo not plan from the original vague prompt once an Agent STE rewrite exists.\n\n## Examples and Spec\n\n- Worked rewrites (coding, DevOps, docs, Git, research, debug, infra, security):\n  `references\u002Fexamples.md`\n- Objective compliance checklist: `references\u002Fchecklist.md`\n- Future machine-checkable spec (MUST\u002FSHOULD\u002FMAY, JSON\u002FYAML, linting, MCP):\n  `references\u002Fspec-v1.md`\n\n## Limitations\n\n- Does not replace domain expertise or formal verification\n- Cannot invent missing requirements; mark `UNKNOWN` and halt or ask\n- Numeric targets require a source (user, SLO, benchmark); else state\n  `METRIC-SOURCE: UNKNOWN` and do not fabricate thresholds\n- Over-application to trivial chat wastes tokens — respect When NOT to use\n- Not a license to ignore higher-priority safety or repository rules\n\n## Rationalizations — Do Not Skip\n\n| Excuse | Reality |\n|--------|---------|\n| \"Too simple to rewrite\" | Simple vague prompts still fork across models |\n| \"No time for slots\" | Missing success criteria causes expensive rework |\n| \"Context implies the metric\" | Another LLM does not share your implied context |\n| \"I'll keep optimize but add detail\" | Forbidden lexicon remains non-deterministic |\n| \"Pronouns are fine; there are only two things\" | Two things is exactly when pronouns collide |\n| \"Rollback is overkill for a docs tweak\" | State `ROLLBACK: none — read-only` explicitly |\n| \"One OBJECTIVE can list three goals with and\" | That is three blocks or gated phases — split them |\n\n**Red flags — STOP and rewrite:** residual `etc.`; success = “looks good”;\nactor missing; two actions joined by “and”; synonym pairs for the same concept;\n`if necessary` without a boolean predicate.\n",{"name":5,"license":15,"metadata":46,"description":49},{"ingested_by":47,"source_platform":48},"skills-export","portable","Use when rewriting user or planner instructions before planning or execution; when prompts contain vague verbs (optimize, improve, better, appropriate, reasonable, quickly, carefully, as needed, if necessary); when multiple agents or LLMs must interpret the same task reproducibly; when an instruction lacks explicit actor, inputs, outputs, success criteria, failure conditions, ordering, or scope; or when preparing handoffs between orchestrators and workers.\n","main","1e047a4b00be0c07efa464cd97f36fa39d4b1718","skills\u002Fagent-ste","https:\u002F\u002Fgithub.com\u002Fdasobral\u002Fskills","https:\u002F\u002Fgithub.com\u002Fdasobral","https:\u002F\u002Forcid.org\u002Fmy-orcid?orcid=0000-0001-9559-3651","Software Engineer with a Ph. D. in Physics","2026-08-15 21:49:02",{"source":8,"skillName":5,"commands":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add dasobral\u002Fskills --skill agent-ste",{"tool":64,"command":65},"bunx","bunx skills add dasobral\u002Fskills --skill agent-ste",{"tool":67,"command":68},"pnpm","pnpm dlx skills add dasobral\u002Fskills --skill agent-ste","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdasobral\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fagent-ste\u002FSKILL.md",true,[72,78,82,86,90,94],{"path":73,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002Fchecklist.md","REFERENCE","参考文档",3941,"https:\u002F\u002Fgithub.com\u002Fdasobral\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fagent-ste\u002Freferences\u002Fchecklist.md",{"path":79,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Fexamples.md",10702,"https:\u002F\u002Fgithub.com\u002Fdasobral\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fagent-ste\u002Freferences\u002Fexamples.md",{"path":83,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002Fprinciples.md",4594,"https:\u002F\u002Fgithub.com\u002Fdasobral\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fagent-ste\u002Freferences\u002Fprinciples.md",{"path":87,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":88,"sourceHtmlUrl":89},"references\u002Frules.md",6323,"https:\u002F\u002Fgithub.com\u002Fdasobral\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fagent-ste\u002Freferences\u002Frules.md",{"path":91,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":92,"sourceHtmlUrl":93},"references\u002Fspec-v1.md",9137,"https:\u002F\u002Fgithub.com\u002Fdasobral\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fagent-ste\u002Freferences\u002Fspec-v1.md",{"path":95,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":96,"sourceHtmlUrl":97},"templates\u002Finstruction-block.md",2054,"https:\u002F\u002Fgithub.com\u002Fdasobral\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fagent-ste\u002Ftemplates\u002Finstruction-block.md",[99,112,146,166,199,223],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":106,"publishedAt":41},"01M6DJFKJASZX8BMFGRQBEKFY9","fixture-skill","Fixture skill used to prove trust inventory coverage.","https:\u002F\u002Fgithub.com\u002Fdasobral\u002Fskills\u002Fblob\u002Fmain\u002Ftools\u002Fskills-export\u002Ftests\u002Ffixtures\u002Fworkflows\u002Fagent-security\u002Frepository\u002F.cursor\u002Fskills\u002Ffixture-skill\u002FSKILL.md",[105],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[107,108,109,110,111],"fixture","fixture skill","trust","coverage","inventory",{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":129,"publishedAt":41},"01M6DJFG24D9X2WAP411JJP71W","write-conformant-code","Write code in any language that matches project conventions exactly. Reads CODING_REQUIREMENTS.md, prior review output, or built-in defaults before writing. Part of Codecraft pipeline: analyze → write → review → audit. Use when implementing features, functions, or any code that should fit seamlessly into an existing codebase.","https:\u002F\u002Fgithub.com\u002Fdasobral\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fwrite-conformant-code\u002FSKILL.md",[118,121,126],{"categoryNo":119,"categoryName":120,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":122,"categoryName":123,"taxonomyType":124,"taxonomyTypeDesc":125},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",{"categoryNo":127,"categoryName":128,"taxonomyType":124,"taxonomyTypeDesc":125},"01JBSEEDCAT000000000000036","内容创作者",[130,131,132,133,134,135,136,137,138,139,140,141,142,143,26,144,145],"code","write","write conformant code","conventions","writing","review","fit","project conventions","requirements","audit","pipeline","analyze","coding","project","functions","language",{"skillNo":147,"name":148,"nameZh":6,"description":149,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":150,"categories":151,"keywords":155,"publishedAt":41},"01M6DJFDDCWB5VMAYE79YTZB40","test-crypto-interoperability","Record reproducible cryptographic interoperability cases, including negotiation, fallback, sizes, latency, fragmentation, and negative tests.","https:\u002F\u002Fgithub.com\u002Fdasobral\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftest-crypto-interoperability\u002FSKILL.md",[152],{"categoryNo":153,"categoryName":154,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[156,157,158,159,160,161,162,163,164,165],"test","interoperability","crypto","test crypto interoperability","negotiation","Reproducible","fallback","record","latency","tests",{"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":181,"publishedAt":41},"01M6DJF68YHCTQA473PSH24HSK","scientific-platform-architect","Design scientific computing platforms combining HPC kernels with modern infrastructure. Enforces compute-layer separation (Rust\u002FPyTorch\u002FPython), emulator-first thinking, and right-sized infrastructure. Use for MCMC pipelines, neural emulators, platform design, or scientific code review.","https:\u002F\u002Fgithub.com\u002Fdasobral\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fscientific-platform-architect\u002FSKILL.md",[172,175,178],{"categoryNo":173,"categoryName":174,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000007","代码审查",{"categoryNo":176,"categoryName":177,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":179,"categoryName":180,"taxonomyType":124,"taxonomyTypeDesc":125},"01JBSEEDCAT000000000000032","设计师",[182,183,184,185,186,187,188,189,190,26,191,192,130,193,194,195,196,135,197,198],"platform","scientific platform architect","architect","emulators","scientific computing","pytorch","thinking","Neural","pipelines","platform design","first","infrastructure","compute","rust","python","design","code review",{"skillNo":200,"name":201,"nameZh":6,"description":202,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":203,"categories":204,"keywords":206,"publishedAt":41},"01M6DJF2D8ZNG4439WQ21CQ75D","rust-systems","Rust systems engineering for daemons, HTTP APIs, and AOS components. Enforces Tokio\u002FAxum async-first, LiteLLM-compatible OpenAI APIs, workspace layouts, tracing, and systemd-compatible daemon design. Part of AOS Stack plugin. Use for .rs files, Cargo.toml, daemons, or Rust orchestrator services.","https:\u002F\u002Fgithub.com\u002Fdasobral\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Frust-systems\u002FSKILL.md",[205],{"categoryNo":176,"categoryName":177,"taxonomyType":21,"taxonomyTypeDesc":22},[207,208,195,209,26,210,211,212,213,192,214,215,216,217,218,219,197,220,221,222],"rust systems","systems","openai","orchestrator","litellm","workspace","stack","services","tracing","async","plugin","http","components","cargo","toml","files",{"skillNo":224,"name":225,"nameZh":6,"description":226,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":227,"categories":228,"keywords":230,"publishedAt":41},"01M6DJEYP0JJX0XJPJYR36VRTW","run-agent-attack-replay","Aggregate isolated agent attack trials with deterministic side-effect assertions, Wilson intervals, and preserved trace evidence.","https:\u002F\u002Fgithub.com\u002Fdasobral\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Frun-agent-attack-replay\u002FSKILL.md",[229],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[231,232,233,234,235,236,237],"run","replay","run agent attack replay","deterministic","evidence","effect","trace"]