[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6HYYHT3JKGGKS1SAXRW51HX":3,"skill-same:01M6HYYHT3JKGGKS1SAXRW51HX":73},{"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":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":52,"commitSha":53,"skillDirectory":54,"forksCount":55,"repositoryHtmlUrl":56,"repositoryHomepageUrl":6,"ownerHtmlUrl":57,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":58,"install":59,"resources":72},"01M6HYYHT3JKGGKS1SAXRW51HX","hforge-recursive-investigate",null,"Auto-discoverable wrapper for the Harness Forge recursive-investigate workflow. Use when a task is ambiguous, cross-module, investigation-heavy, or likely to benefit from Typed RLM, bounded subcalls, and durable recursive artifacts.","ldilov\u002Fharness-forge","ldilov","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F25016670?v=4","01M6HYXAEJP0KYT2DF86WYN8QK","Lazar Dilov","01M6HYXAJETHAW5DD5TAAFEQ7D",6,"GPL-3.0","https:\u002F\u002Fgithub.com\u002Fldilov\u002Fharness-forge\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fhforge-recursive-investigate\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"hforge recursive investigate","recursive","investigate","Wrapper","for","with","about","targets","module","rlm","task","workflow","auto","use","investigation","forge","harness","artifacts","support","2026-11-10 10:12:30",false,"---\nname: \"hforge-recursive-investigate\"\ndescription: \"Auto-discoverable wrapper for the Harness Forge recursive-investigate workflow. Use when a task is ambiguous, cross-module, investigation-heavy, or likely to benefit from Typed RLM, bounded subcalls, and durable recursive artifacts.\"\ncompatibility: \"Works best in repositories already initialized with Harness Forge and should remain honest about translated support on partial targets.\"\nmetadata:\n  author: \"harness-forge\"\n  source: \"skills\u002Fhforge-recursive-investigate\u002FSKILL.md\"\n---\n\n## User Input\n\n```text\n$ARGUMENTS\n```\n\nYou must consider the user input before proceeding.\n\n## Goal\n\nUse Harness Forge recursive mode as an explicit investigation operating layer\nfor hard tasks, preferring Typed RLM first and only falling back to bounded\nstructured analysis when necessary.\n\n## Execution\n\n1. Treat the text after `\u002Fhforge-recursive-investigate` as the investigation objective or task focus.\n2. Inspect `.hforge\u002Fagent-manifest.json`, `.hforge\u002Fruntime\u002Findex.json`, `.hforge\u002Fruntime\u002Frecursive\u002Flanguage-capabilities.json`, `.hforge\u002Fruntime\u002Frecursive\u002Fruntime-inventory.json`, and `.hforge\u002Fruntime\u002Frecursive\u002Fescalation-heuristics.json` first when present.\n3. Run `hforge recursive capabilities --root . --json` before claiming recursive support for the active language or target.\n4. Run `hforge recursive runtimes --root . --json` before assuming Python or PowerShell code-cell availability.\n5. Use `hforge recursive provision-runtime \u003Cpython|powershell> --root . --json` only when a workspace-managed runtime alias is genuinely useful.\n6. Create or inspect a session with `hforge recursive plan \"\u003Cobjective>\" --task-id \u003CtaskId> --root . --json` or `hforge recursive inspect \u003CsessionId> --root . --json`.\n7. Prefer Typed RLM through `hforge recursive execute \u003CsessionId> --file \u003Cbundle.json> --root . --json` or `--stdin`.\n8. Use `hforge recursive run \u003CsessionId> --file \u003Csnippet>` or `--stdin` only when one bounded structured-analysis step is the right tool.\n9. Inspect durable artifacts with `hforge recursive iterations`, `subcalls`, `cells`, `promotions`, `meta-ops`, `score`, and `replay`.\n10. Reuse the recursive artifacts in your summary instead of re-scanning the whole repo.\n11. Keep product code unchanged unless the user explicitly asks for edits.\n","## User Input\n\n```text\n$ARGUMENTS\n```\n\nYou must consider the user input before proceeding.\n\n## Goal\n\nUse Harness Forge recursive mode as an explicit investigation operating layer\nfor hard tasks, preferring Typed RLM first and only falling back to bounded\nstructured analysis when necessary.\n\n## Execution\n\n1. Treat the text after `\u002Fhforge-recursive-investigate` as the investigation objective or task focus.\n2. Inspect `.hforge\u002Fagent-manifest.json`, `.hforge\u002Fruntime\u002Findex.json`, `.hforge\u002Fruntime\u002Frecursive\u002Flanguage-capabilities.json`, `.hforge\u002Fruntime\u002Frecursive\u002Fruntime-inventory.json`, and `.hforge\u002Fruntime\u002Frecursive\u002Fescalation-heuristics.json` first when present.\n3. Run `hforge recursive capabilities --root . --json` before claiming recursive support for the active language or target.\n4. Run `hforge recursive runtimes --root . --json` before assuming Python or PowerShell code-cell availability.\n5. Use `hforge recursive provision-runtime \u003Cpython|powershell> --root . --json` only when a workspace-managed runtime alias is genuinely useful.\n6. Create or inspect a session with `hforge recursive plan \"\u003Cobjective>\" --task-id \u003CtaskId> --root . --json` or `hforge recursive inspect \u003CsessionId> --root . --json`.\n7. Prefer Typed RLM through `hforge recursive execute \u003CsessionId> --file \u003Cbundle.json> --root . --json` or `--stdin`.\n8. Use `hforge recursive run \u003CsessionId> --file \u003Csnippet>` or `--stdin` only when one bounded structured-analysis step is the right tool.\n9. Inspect durable artifacts with `hforge recursive iterations`, `subcalls`, `cells`, `promotions`, `meta-ops`, `score`, and `replay`.\n10. Reuse the recursive artifacts in your summary instead of re-scanning the whole repo.\n11. Keep product code unchanged unless the user explicitly asks for edits.\n",{"name":5,"metadata":48,"description":7,"compatibility":51},{"author":49,"source":50},"harness-forge","skills\u002Fhforge-recursive-investigate\u002FSKILL.md","Works best in repositories already initialized with Harness Forge and should remain honest about translated support on partial targets.","main","27337828f396bcf279d7c4353a4a4f0cdc97659f",".agents\u002Fskills\u002Fhforge-recursive-investigate",1,"https:\u002F\u002Fgithub.com\u002Fldilov\u002Fharness-forge","https:\u002F\u002Fgithub.com\u002Fldilov","2026-05-19 21:48:38",{"source":8,"skillName":5,"commands":60,"prompt":70,"zipAvailable":71},[61,64,67],{"tool":62,"command":63},"npx","npx skills add ldilov\u002Fharness-forge --skill hforge-recursive-investigate",{"tool":65,"command":66},"bunx","bunx skills add ldilov\u002Fharness-forge --skill hforge-recursive-investigate",{"tool":68,"command":69},"pnpm","pnpm dlx skills add ldilov\u002Fharness-forge --skill hforge-recursive-investigate","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fldilov\u002Fharness-forge\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fhforge-recursive-investigate\u002FSKILL.md",true,[],[74,100,129,148,172,183],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":83,"publishedAt":43},"01M6HZ7WE4DSYWPX0W2JX9BD8K","typescript-engineering","typescript and javascript engineering guidance seeded from the harness forge knowledge base. use when the repo or task is dominated by .ts, .tsx, package.json, tsconfig, node.js services, react, next.js, frontend tooling, or multi-package workspaces where type boundaries matter.","https:\u002F\u002Fgithub.com\u002Fldilov\u002Fharness-forge\u002Fblob\u002Fmain\u002Fskills\u002Ftypescript-engineering\u002FSKILL.md",[80],{"categoryNo":81,"categoryName":82,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",[84,85,86,87,88,89,40,90,39,91,92,93,94,37,95,96,34,97,98,99],"typescript","engineering","typescript engineering","frontend","javascript","react","package","Next.js","knowledge","node","repo","workspaces","tsx","next","knowledge base","type",{"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":112,"publishedAt":43},"01M6HZ7QRWHQP72E7DPB6W5S6C","token-budget-optimizer","compact context, reuse existing runtime artifacts, and choose the smallest authoritative surface before expanding prompt history. use when the task is growing large, when earlier repo intelligence already exists, or when repeated rescans would waste tokens without adding new evidence.","https:\u002F\u002Fgithub.com\u002Fldilov\u002Fharness-forge\u002Fblob\u002Fmain\u002Fskills\u002Ftoken-budget-optimizer\u002FSKILL.md",[106,107],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":108,"categoryName":109,"taxonomyType":110,"taxonomyTypeDesc":111},"01JBSEEDCAT000000000000040","财务","PROFESSION","适用职业",[113,114,115,116,117,41,118,119,94,120,121,37,122,34,123,124,125,126,127,128],"Budget","optimizer","token","token budget","token budget optimizer","choose","history","prompt","context","evidence","intelligence","compact","tokens","runtime","reuse","Existing",{"skillNo":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":138,"publishedAt":43},"01M6HZ7MMX3ZZP4KF2FVC2EHP0","test-strategy-and-coverage","Define right-sized test layers and coverage priorities for a change.","https:\u002F\u002Fgithub.com\u002Fldilov\u002Fharness-forge\u002Fblob\u002Fmain\u002Fskills\u002Ftest-strategy-and-coverage\u002FSKILL.md",[135],{"categoryNo":136,"categoryName":137,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[139,140,141,142,143,144,145,146,147,28],"test","strategy","coverage","test strategy","test strategy and coverage","change","priorities","define","layers",{"skillNo":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":154,"publishedAt":43},"01M6HZ7HE9C6MGWT9JG17Z3Y3M","speckit-taskstoissues","Convert existing tasks into actionable, dependency-ordered GitHub issues for the feature based on available design artifacts.","https:\u002F\u002Fgithub.com\u002Fldilov\u002Fharness-forge\u002Fblob\u002Fmain\u002Fskills\u002Fspeckit-taskstoissues\u002FSKILL.md",[],[155,156,157,158,159,160,161,41,162,163,164,165,166,167,168,169,170,171,28,128],"speckit taskstoissues","speckit","design","directory","project structure","tasks","github issues","issues","specify","convert","dependency","structure","project","commands","feature","actionable","kit",{"skillNo":173,"name":174,"nameZh":6,"description":175,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":176,"categories":177,"keywords":178,"publishedAt":43},"01M6HZ7E2NMYB9N2GKYVRF09AK","speckit-tasks","Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.","https:\u002F\u002Fgithub.com\u002Fldilov\u002Fharness-forge\u002Fblob\u002Fmain\u002Fskills\u002Fspeckit-tasks\u002FSKILL.md",[],[160,179,156,157,158,180,159,181,41,163,165,166,167,168,169,170,182,29,171,28],"speckit tasks","github","generate","spec-kit",{"skillNo":184,"name":185,"nameZh":6,"description":186,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":187,"categories":188,"keywords":189,"publishedAt":43},"01M6HZ7AS0E880YSZN4FEFF6QF","speckit-specify","Create or update the feature specification from a natural language feature description.","https:\u002F\u002Fgithub.com\u002Fldilov\u002Fharness-forge\u002Fblob\u002Fmain\u002Fskills\u002Fspeckit-specify\u002FSKILL.md",[],[163,190,156,158,191,180,159,192,193,194,195,196,166,167,168,169,182,29,197,171],"speckit specify","spec","create","update","templates","specification","natural language","feature specification"]