[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"creator:01M6MYYWF28C4KBQHHWB9SC6TS":3,"creator-list:01M6MYYWF28C4KBQHHWB9SC6TS:stars:1:":21},{"accountNo":4,"login":5,"displayName":6,"avatarUrl":7,"accountType":8,"accountTypeDesc":9,"profileDescription":10,"skillCount":11,"repoCount":12,"professionCount":13,"scenarioCount":13,"totalStars":14,"updatedAt":15,"htmlUrl":16,"blogUrl":17,"company":17,"location":18,"followersCount":19,"publicReposCount":20},"01M6MYYWF28C4KBQHHWB9SC6TS","snewhouse","Stephen J Newhouse","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6317143?v=4","USER","个人作者","Data Scientist, Bioinformatician, Dad, Husband, MS warrior",41,1,5,6,"2026-11-11 21:34:39","https:\u002F\u002Fgithub.com\u002Fsnewhouse",null,"Earth",83,215,{"records":22,"total":11,"current":12,"size":424},[23,52,80,101,126,156,180,202,228,254,273,295,315,339,355,367,384,401],{"skillNo":24,"name":25,"nameZh":17,"description":26,"descriptionZh":17,"repositoryFullName":27,"ownerLogin":5,"ownerAvatarUrl":7,"ownerAccountNo":4,"ownerDisplayName":6,"repositoryNo":28,"starsCount":14,"licenseSpdxId":29,"licenseFileUrl":17,"sourceHtmlUrl":30,"categories":31,"keywords":37,"publishedAt":51},"01M6MZ588SD5DDH59H18PRNWEV","deploy-helper","You can use this to help with deploy stuff, deploying, deployments, releases, shipping, pushing to prod, going live, rollouts.","snewhouse\u002Faa-ma-forge","01M6MYYWJWQMDN2ZPFMJ584SSM","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fsnewhouse\u002Faa-ma-forge\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fevals\u002Fskill-draft\u002Fdraft\u002FSKILL.md",[32],{"categoryNo":33,"categoryName":34,"taxonomyType":35,"taxonomyTypeDesc":36},"01JBSEEDCAT000000000000011","运维与部署","SCENARIO","使用场景",[38,39,40,41,42,43,44,45,46,47,48,49,50],"deploy","deploy helper","helper","help","shipping","use","deployments","rollouts","releases","live","with","you","can","2026-11-10 10:12:30",{"skillNo":53,"name":54,"nameZh":17,"description":55,"descriptionZh":17,"repositoryFullName":27,"ownerLogin":5,"ownerAvatarUrl":7,"ownerAccountNo":4,"ownerDisplayName":6,"repositoryNo":28,"starsCount":14,"licenseSpdxId":56,"licenseFileUrl":57,"sourceHtmlUrl":58,"categories":59,"keywords":71,"publishedAt":51},"01M6MZ54NEKRYXGMJ1KJWYMKM7","writing-for-agents","Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","MIT","https:\u002F\u002Fgithub.com\u002Fsnewhouse\u002Faa-ma-forge\u002Fblob\u002Fmain\u002Fclaude-code\u002Fskills\u002Fwriting-for-agents\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fsnewhouse\u002Faa-ma-forge\u002Fblob\u002Fmain\u002Fclaude-code\u002Fskills\u002Fwriting-for-agents\u002FSKILL.md",[60,63,66],{"categoryNo":61,"categoryName":62,"taxonomyType":35,"taxonomyTypeDesc":36},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":64,"categoryName":65,"taxonomyType":35,"taxonomyTypeDesc":36},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":67,"categoryName":68,"taxonomyType":69,"taxonomyTypeDesc":70},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[72,73,74,75,76,77,78,43,79],"writing","writing for agents","for","documents","editing","read","instructions","line",{"skillNo":81,"name":82,"nameZh":17,"description":83,"descriptionZh":17,"repositoryFullName":27,"ownerLogin":5,"ownerAvatarUrl":7,"ownerAccountNo":4,"ownerDisplayName":6,"repositoryNo":28,"starsCount":14,"licenseSpdxId":29,"licenseFileUrl":17,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":51},"01M6MZ500T0FH1G8TBSQV7G5G2","verify-plan","Slash entry for plan verification: runs plan-verification on an existing AA-MA plan, writes [task]-verification.md, and with --iterate loops until the plan converges. Use when the user types \u002Fverify-plan or wants the verification report saved.","https:\u002F\u002Fgithub.com\u002Fsnewhouse\u002Faa-ma-forge\u002Fblob\u002Fmain\u002Fclaude-code\u002Fskills\u002Fverify-plan\u002FSKILL.md",[],[87,88,89,90,91,92,43,93,94,95,48,96,74,97,98,99,100],"verify","plan","verify plan","report","verification","user","task","loops","types","saved","Existing","iterate","entry","plan verification",{"skillNo":102,"name":103,"nameZh":17,"description":104,"descriptionZh":17,"repositoryFullName":27,"ownerLogin":5,"ownerAvatarUrl":7,"ownerAccountNo":4,"ownerDisplayName":6,"repositoryNo":28,"starsCount":14,"licenseSpdxId":29,"licenseFileUrl":17,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":51},"01M6MZ4V9ST4K54NT1SRBGCE7P","verify-impl","Post-impl adversarial review symmetric to \u002Fverify-plan. Dispatches up to 5 parallel audit agents (code-reviewer, security-auditor, tdd-sequence-auditor, context7-evidence-auditor, future-proofing-auditor) based on the milestone's plan-declared Audit-Profile. CRITICAL findings surface via AskUserQuestion accept\u002Fdispute\u002Fdefer panel before §7.3 user authorization. Introduced in v0.8.0 per ADR-0005. Invoked by Phase 6.8 of \u002Fexecute-aa-ma-milestone.","https:\u002F\u002Fgithub.com\u002Fsnewhouse\u002Faa-ma-forge\u002Fblob\u002Fmain\u002Fclaude-code\u002Fskills\u002Fverify-impl\u002FSKILL.md",[],[87,108,109,110,111,112,113,88,114,115,116,117,118,119,120,121,122,123,124,125],"impl","verify impl","review","tdd","code","audit","adr","parallel","reviewer","evidence","up","context7","milestone","critical","via","panel","post","adversarial",{"skillNo":127,"name":128,"nameZh":17,"description":129,"descriptionZh":17,"repositoryFullName":27,"ownerLogin":5,"ownerAvatarUrl":7,"ownerAccountNo":4,"ownerDisplayName":6,"repositoryNo":28,"starsCount":14,"licenseSpdxId":29,"licenseFileUrl":17,"sourceHtmlUrl":130,"categories":131,"keywords":136,"publishedAt":51},"01M6MZ4K7CC9PMJ1KEY3F53RS1","understand-codebase","Onboard to a new, inherited, or shared codebase. Read it, understand it, map it, and learn its conventions, versioning, tests, tech stack, rules (AGENTS.md \u002F CLAUDE.md \u002F .cursorrules \u002F etc.), build\u002Frun\u002FCI, integrations, security posture, and repo health — then produce an honest pros\u002Fcons verdict, a \"contribute safely\" playbook, and an \"add a feature\" playbook, written to ONBOARDING.md at the repo root plus a .claude\u002Fonboarding\u002F set of deep-dives — and optionally author an AGENTS.md if one is missing, or review and propose improvements to an existing one. Tiered (Quick \u002F Standard \u002F Deep). Reuses codemem (index + diagrams), gsd-map-codebase, system-mapping, code-intelligence, impact-analysis rather than re-implementing them; Deep tier runs a TeamCreate agent-team. Keywords: new codebase, shared codebase, inherited code, onboard, understand this repo, how do I contribute, how do I add a feature, ramp up, get oriented, ONBOARDING.md, AGENTS.md, codebase walkthrough, joining a project.","https:\u002F\u002Fgithub.com\u002Fsnewhouse\u002Faa-ma-forge\u002Fblob\u002Fmain\u002Fclaude-code\u002Fskills\u002Funderstand-codebase\u002FSKILL.md",[132,133],{"categoryNo":64,"categoryName":65,"taxonomyType":35,"taxonomyTypeDesc":36},{"categoryNo":134,"categoryName":135,"taxonomyType":69,"taxonomyTypeDesc":70},"01JBSEEDCAT000000000000038","人力资源",[137,138,139,140,141,142,143,144,118,145,146,147,148,149,150,151,152,153,154,155],"understand","codebase","understand codebase","learn","ci","SET","analysis","walkthrough","diagrams","map","shared","deep","project","get","impact","quick","re","implementing","repo health",{"skillNo":157,"name":158,"nameZh":17,"description":159,"descriptionZh":17,"repositoryFullName":27,"ownerLogin":5,"ownerAvatarUrl":7,"ownerAccountNo":4,"ownerDisplayName":6,"repositoryNo":28,"starsCount":14,"licenseSpdxId":29,"licenseFileUrl":17,"sourceHtmlUrl":160,"categories":161,"keywords":162,"publishedAt":51},"01M6MZ4D1ZC8MTW064QXY6WC76","token-compression","Output token compression for AA-MA workflows. Reduces response tokens by 40-75% while preserving full technical accuracy. Three intensity levels mapped to execution modes: lite (HITL), full (general), ultra (AFK). Auto-activates during AA-MA execution based on task Mode field. Manual activation via \u002Fcompress lite|full|ultra.","https:\u002F\u002Fgithub.com\u002Fsnewhouse\u002Faa-ma-forge\u002Fblob\u002Fmain\u002Fclaude-code\u002Fskills\u002Ftoken-compression\u002FSKILL.md",[],[163,164,165,166,167,168,169,170,93,171,172,173,174,122,175,176,177,74,178,179],"compression","token","token compression","workflows","execution","technical","auto","general","three","hitl","tokens","intensity","output","manual","mode","accuracy","modes",{"skillNo":181,"name":182,"nameZh":17,"description":183,"descriptionZh":17,"repositoryFullName":27,"ownerLogin":5,"ownerAvatarUrl":7,"ownerAccountNo":4,"ownerDisplayName":6,"repositoryNo":28,"starsCount":14,"licenseSpdxId":29,"licenseFileUrl":17,"sourceHtmlUrl":184,"categories":185,"keywords":186,"publishedAt":51},"01M6MZ493XAJBXC35CHW4MV066","system-mapping","Lightweight pre-flight checklist for understanding system context before code changes. Perform 5-point analysis of architecture, execution flows, logging, dependencies, and environment. Use before modifying unfamiliar code or multi-file changes.","https:\u002F\u002Fgithub.com\u002Fsnewhouse\u002Faa-ma-forge\u002Fblob\u002Fmain\u002Fclaude-code\u002Fskills\u002Fsystem-mapping\u002FSKILL.md",[],[187,188,189,190,191,112,192,193,167,143,194,195,196,43,197,198,199,200,74,201],"system","mapping","system mapping","change","architecture","logging","file","check","context","environment","checklist","dependencies","multi","flows","changes",{"skillNo":203,"name":204,"nameZh":17,"description":205,"descriptionZh":17,"repositoryFullName":27,"ownerLogin":5,"ownerAvatarUrl":7,"ownerAccountNo":4,"ownerDisplayName":6,"repositoryNo":28,"starsCount":14,"licenseSpdxId":29,"licenseFileUrl":17,"sourceHtmlUrl":206,"categories":207,"keywords":211,"publishedAt":51},"01M6MZ45KQ5SFKDEGY37WEX358","sole-dev-merge","GitHub PR merge for a sole developer — local fixes and checks, code and security review, push and PR, CI watch, merge and cleanup, through one tested script (sdm.sh). Run only when the user asks to merge a branch or PR.","https:\u002F\u002Fgithub.com\u002Fsnewhouse\u002Faa-ma-forge\u002Fblob\u002Fmain\u002Fclaude-code\u002Fskills\u002Fsole-dev-merge\u002FSKILL.md",[208],{"categoryNo":209,"categoryName":210,"taxonomyType":69,"taxonomyTypeDesc":70},"01JBSEEDCAT000000000000030","开发工程师",[212,213,214,110,215,216,217,112,218,141,219,220,221,222,223,224,225,226,74,227],"merge","dev","sole dev merge","github","pr","cleanup","push","branch","only","github pr","local","github pr merge","pr merge","ci watch","true","fixes",{"skillNo":229,"name":230,"nameZh":17,"description":231,"descriptionZh":17,"repositoryFullName":27,"ownerLogin":5,"ownerAvatarUrl":7,"ownerAccountNo":4,"ownerDisplayName":6,"repositoryNo":28,"starsCount":14,"licenseSpdxId":56,"licenseFileUrl":232,"sourceHtmlUrl":233,"categories":234,"keywords":236,"publishedAt":51},"01M6MZ41EV8Q5QYEVFPH9FX5TZ","secrets-management","Implement secure secrets management for CI\u002FCD pipelines using Vault, AWS Secrets Manager, or native platform solutions. Use when handling sensitive credentials, rotating secrets, or securing CI\u002FCD environments.","https:\u002F\u002Fgithub.com\u002Fsnewhouse\u002Faa-ma-forge\u002Fblob\u002Fmain\u002Fclaude-code\u002Fskills\u002Fsecrets-management\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fsnewhouse\u002Faa-ma-forge\u002Fblob\u002Fmain\u002Fclaude-code\u002Fskills\u002Fsecrets-management\u002FSKILL.md",[235],{"categoryNo":33,"categoryName":34,"taxonomyType":35,"taxonomyTypeDesc":36},[237,238,239,240,241,141,242,243,244,43,245,246,247,248,249,250,251,252,253,74],"secrets management","secrets","management","implement","secure","aws","vault","credentials","pipelines","aws secrets manager","platform","cd","native","CI\u002FCD","secrets manager","environments","manager",{"skillNo":255,"name":256,"nameZh":17,"description":257,"descriptionZh":17,"repositoryFullName":27,"ownerLogin":5,"ownerAvatarUrl":7,"ownerAccountNo":4,"ownerDisplayName":6,"repositoryNo":28,"starsCount":14,"licenseSpdxId":29,"licenseFileUrl":17,"sourceHtmlUrl":258,"categories":259,"keywords":260,"publishedAt":51},"01M6MZ3XFB30Q27TH7H3S0KA70","secops","Security review, dependency audit and scanner choice: routes each artifact to its scanner (Ruff S for Python, gitleaks for secrets, pip-audit for the Python lock, osv-scanner for JS, R and other lockfiles, ShellCheck for shell), names each finding's rule and CWE, and sets the layer each check runs at (edit, commit, CI). Use when reviewing code or a file for security problems (load it before reading the code), auditing dependencies for known vulnerabilities, or choosing a repo's security checks.","https:\u002F\u002Fgithub.com\u002Fsnewhouse\u002Faa-ma-forge\u002Fblob\u002Fmain\u002Fclaude-code\u002Fskills\u002Fsecops\u002FSKILL.md",[],[256,110,261,262,112,193,141,263,264,265,194,43,266,267,268,269,270,271,272,74],"python","commit","pip-audit","choice","repo","ruff","scanner","reviewing code","ShellCheck","lock","pip","load",{"skillNo":274,"name":275,"nameZh":17,"description":276,"descriptionZh":17,"repositoryFullName":27,"ownerLogin":5,"ownerAvatarUrl":7,"ownerAccountNo":4,"ownerDisplayName":6,"repositoryNo":28,"starsCount":14,"licenseSpdxId":29,"licenseFileUrl":17,"sourceHtmlUrl":277,"categories":278,"keywords":279,"publishedAt":51},"01M6MZ3RABHQCH7P54QJF4NZTF","retro","Weekly engineering retrospective. Analyzes commit history, work patterns,\nand code quality metrics with persistent history and trend tracking.\nTeam-aware: breaks down per-person contributions with praise and growth areas.","https:\u002F\u002Fgithub.com\u002Fsnewhouse\u002Faa-ma-forge\u002Fblob\u002Fmain\u002Fclaude-code\u002Fskills\u002Fretro\u002FSKILL.md",[],[275,262,280,281,112,282,283,284,285,286,77,287,288,289,290,291,292,48,293,294],"code quality","retrospective","metrics","team","Bash","history","work","write","growth","patterns","code quality metrics","trend","quality metrics","weekly","down",{"skillNo":296,"name":297,"nameZh":17,"description":298,"descriptionZh":17,"repositoryFullName":27,"ownerLogin":5,"ownerAvatarUrl":7,"ownerAccountNo":4,"ownerDisplayName":6,"repositoryNo":28,"starsCount":14,"licenseSpdxId":29,"licenseFileUrl":17,"sourceHtmlUrl":299,"categories":300,"keywords":301,"publishedAt":51},"01M6MZ3MKGBY7QV398608CXB61","python-quality-gates","Python quality gates: zero tolerance for failing tests (no \"pre-existing failure\" excuse), and the pre-commit documentation-maintenance checklist. Use when finishing Python work, running a test suite, or preparing a Python commit.","https:\u002F\u002Fgithub.com\u002Fsnewhouse\u002Faa-ma-forge\u002Fblob\u002Fmain\u002Fclaude-code\u002Fskills\u002Fpython-quality-gates\u002FSKILL.md",[],[261,302,303,304,305,306,262,307,308,309,286,43,310,311,197,312,313,74,97,314],"quality gates","quality","gates","python quality gates","test","documentation","ZeRO","pre-commit","test suite","maintenance","tests","tolerance","suite",{"skillNo":316,"name":317,"nameZh":17,"description":318,"descriptionZh":17,"repositoryFullName":27,"ownerLogin":5,"ownerAvatarUrl":7,"ownerAccountNo":4,"ownerDisplayName":6,"repositoryNo":28,"starsCount":14,"licenseSpdxId":56,"licenseFileUrl":319,"sourceHtmlUrl":320,"categories":321,"keywords":325,"publishedAt":51},"01M6MZ3H3174HFRKG5Q5JFGV5Q","prototype","Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.","https:\u002F\u002Fgithub.com\u002Fsnewhouse\u002Faa-ma-forge\u002Fblob\u002Fmain\u002Fclaude-code\u002Fskills\u002Fprototype\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fsnewhouse\u002Faa-ma-forge\u002Fblob\u002Fmain\u002Fclaude-code\u002Fskills\u002Fprototype\u002FSKILL.md",[322],{"categoryNo":323,"categoryName":324,"taxonomyType":69,"taxonomyTypeDesc":70},"01JBSEEDCAT000000000000032","设计师",[317,326,327,328,329,330,194,331,92,43,332,333,334,335,336,337,338],"design","state","ui","explore","model","question","look","build","logic","sanity","answer","state model","throwaway",{"skillNo":340,"name":341,"nameZh":17,"description":342,"descriptionZh":17,"repositoryFullName":27,"ownerLogin":5,"ownerAvatarUrl":7,"ownerAccountNo":4,"ownerDisplayName":6,"repositoryNo":28,"starsCount":14,"licenseSpdxId":29,"licenseFileUrl":17,"sourceHtmlUrl":343,"categories":344,"keywords":345,"publishedAt":51},"01M6MZ3AX01FYWXV1531551HER","plan-verification","Verifies an AA-MA plan from 6 adversarial angles (facts, assumptions, impact, acceptance criteria, implementation barriers, domain risk) and lists its defects. Use when asked to verify, check or review an AA-MA plan, and at aa-ma-plan Phase 4.5.","https:\u002F\u002Fgithub.com\u002Fsnewhouse\u002Faa-ma-forge\u002Fblob\u002Fmain\u002Fclaude-code\u002Fskills\u002Fplan-verification\u002FSKILL.md",[],[91,88,100,110,346,347,87,194,43,348,349,350,351,151,352,353,354,125],"acceptance","risk","implementation","acceptance criteria","domain","plan phase","at","facts","defects",{"skillNo":356,"name":357,"nameZh":17,"description":358,"descriptionZh":17,"repositoryFullName":27,"ownerLogin":5,"ownerAvatarUrl":7,"ownerAccountNo":4,"ownerDisplayName":6,"repositoryNo":28,"starsCount":14,"licenseSpdxId":29,"licenseFileUrl":17,"sourceHtmlUrl":359,"categories":360,"keywords":361,"publishedAt":51},"01M6MZ3719CHVMNH1QMKMSFEAN","ops-mode","Activate full operational constraints mode for disciplined, efficient execution. Use when the user asks for ops mode.","https:\u002F\u002Fgithub.com\u002Fsnewhouse\u002Faa-ma-forge\u002Fblob\u002Fmain\u002Fclaude-code\u002Fskills\u002Fops-mode\u002FSKILL.md",[],[362,177,363,167,364,92,43,365,366,74],"ops","ops mode","constraints","activate","full",{"skillNo":368,"name":369,"nameZh":17,"description":370,"descriptionZh":17,"repositoryFullName":27,"ownerLogin":5,"ownerAvatarUrl":7,"ownerAccountNo":4,"ownerDisplayName":6,"repositoryNo":28,"starsCount":14,"licenseSpdxId":29,"licenseFileUrl":17,"sourceHtmlUrl":371,"categories":372,"keywords":373,"publishedAt":51},"01M6MZ31F7M5EP8TD7QNWJB7WK","operational-constraints","Activate comprehensive operational constraints for disciplined execution. Use at session start, before complex tasks, during planning phases, or when encountering friction. Enforces token efficiency, tool protocols, parallel execution, TDD, and system mapping.","https:\u002F\u002Fgithub.com\u002Fsnewhouse\u002Faa-ma-forge\u002Fblob\u002Fmain\u002Fclaude-code\u002Fskills\u002Foperational-constraints\u002FSKILL.md",[],[364,374,375,376,377,167,378,187,379,115,380,362,43,365,93,381,382,177,74,383],"operational constraints","tasks","planning","protocols","ultrathink","tool","session","efficiency","session start","token efficiency",{"skillNo":385,"name":386,"nameZh":17,"description":387,"descriptionZh":17,"repositoryFullName":27,"ownerLogin":5,"ownerAvatarUrl":7,"ownerAccountNo":4,"ownerDisplayName":6,"repositoryNo":28,"starsCount":14,"licenseSpdxId":29,"licenseFileUrl":17,"sourceHtmlUrl":388,"categories":389,"keywords":390,"publishedAt":51},"01M6MZ2WHT9CJ90QJX0K79Z61C","logging-and-comments","Logging and code-comment standard for Python and Bash: library vs app logging, stderr vs stdout, no silent failures, run-level context for pipelines, why-comments, docstrings, constant rationale, TODO format, and the Ruff rules that enforce it. Use when writing or reviewing any script, CLI, hook, pipeline, or library code, or when adding try\u002Fexcept, || true, or 2>\u002Fdev\u002Fnull.","https:\u002F\u002Fgithub.com\u002Fsnewhouse\u002Faa-ma-forge\u002Fblob\u002Fmain\u002Fclaude-code\u002Fskills\u002Flogging-and-comments\u002FSKILL.md",[],[192,391,392,72,393,261,394,112,213,395,284,396,43,266,397,398,399,226,74,400],"comments","logging and comments","cli","run","pipeline","Rules","todo","enforce","app","docstrings",{"skillNo":402,"name":403,"nameZh":17,"description":404,"descriptionZh":17,"repositoryFullName":27,"ownerLogin":5,"ownerAvatarUrl":7,"ownerAccountNo":4,"ownerDisplayName":6,"repositoryNo":28,"starsCount":14,"licenseSpdxId":29,"licenseFileUrl":17,"sourceHtmlUrl":405,"categories":406,"keywords":407,"publishedAt":51},"01M6MZ2RDZZ888PPNSNSE64AVX","llm-output-safety","Production safety requirements for pipelines that put LLM-generated text into client-facing outputs: non-Latin character sanitization, programmatic citation integrity, and treating recurring issues as architectural deficiencies. Use when generating reports, exports, or any client-facing document from LLM output.","https:\u002F\u002Fgithub.com\u002Fsnewhouse\u002Faa-ma-forge\u002Fblob\u002Fmain\u002Fclaude-code\u002Fskills\u002Fllm-output-safety\u002FSKILL.md",[],[408,175,409,410,411,412,413,414,415,43,245,416,417,418,419,420,421,422,423,74],"Safety","llm output safety","issues","Production","integrity","text","generated","recurring","reports","document","character","requirements","as","client","programmatic","sanitization",18]