[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AZ5W47GAAWC0BA182WBHCP":3,"skill-same:01M7AZ5W47GAAWC0BA182WBHCP":47},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":14,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":6,"updatedAt":32,"install":33,"resources":46},"01M7AZ5W47GAAWC0BA182WBHCP","agent-experience",null,"Use when writing or changing a model-facing tool definition (name, description, parameter schema, or its system-prompt section), and when designing skills, context loading, or multi-step workflows, to make information discoverable and use context efficiently.","Darthph0enix7\u002FEnpoi-harness","Darthph0enix7","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F131202811?v=4","01M7AZ5R47P734DG5HWJ4CHYN5","Eren Kalinsazlioglu","01M7AZ5R54MGXEKD09HT2692HC",0,"MIT","https:\u002F\u002Fgithub.com\u002FDarthph0enix7\u002FEnpoi-harness\u002Fblob\u002Fstable\u002F.agents\u002Fskills\u002Fagent-experience\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: agent-experience\ndescription: Use when writing or changing a model-facing tool definition (name, description, parameter schema, or its system-prompt section), and when designing skills, context loading, or multi-step workflows, to make information discoverable and use context efficiently.\nmetadata:\n  date: \"2026-09-11\"\n---\n\n- **Start with minimal context:** expose purpose, available actions, and constraints first; load detailed instructions when needed.\n- **Make discovery explicit:** every deferred resource needs a clear description and a reliable way to retrieve it.\n- **Keep critical constraints visible:** permissions, destructive effects, and required validation should appear before the relevant action.\n- **Prefer bounded outputs:** return concise results with identifiers or paths for retrieving details; avoid dumping entire logs or documents.\n- **Use locality:** include a bounded amount of likely needed adjacent context with an operation’s result. For example, deliver a thread reply with a few preceding messages. Mark omissions and truncation explicitly, and provide a way to retrieve more.\n- **Evaluate total work:** saving context is useful only if it does not cause more searches, repeated reads, or mistakes.\n\n## Tool definitions\n\n- **Delete obvious constraints.** Omit rules the model learns from the call result, such as a missing file failing to read or a failed send not being delivered.\n- **Describe behavior, not implementation.** State what the tool does and returns; omit internal mechanisms, output markers the model sees in results, and enforcement details.\n- **Put parameter rules on the parameter.** Defaults, ranges, pairing, and when-to-set rules belong in that parameter's description or schema; a description that varies with configuration usually means the varying part belongs to a parameter.\n- **Say each fact once.** Do not repeat the tool definition in its system-prompt section, a parameter description in the tool description, or one tool's rules in another tool.\n- **Measure the change.** Compare first-turn prompt tokens before and after a tool-definition change.\n","- **Start with minimal context:** expose purpose, available actions, and constraints first; load detailed instructions when needed.\n- **Make discovery explicit:** every deferred resource needs a clear description and a reliable way to retrieve it.\n- **Keep critical constraints visible:** permissions, destructive effects, and required validation should appear before the relevant action.\n- **Prefer bounded outputs:** return concise results with identifiers or paths for retrieving details; avoid dumping entire logs or documents.\n- **Use locality:** include a bounded amount of likely needed adjacent context with an operation’s result. For example, deliver a thread reply with a few preceding messages. Mark omissions and truncation explicitly, and provide a way to retrieve more.\n- **Evaluate total work:** saving context is useful only if it does not cause more searches, repeated reads, or mistakes.\n\n## Tool definitions\n\n- **Delete obvious constraints.** Omit rules the model learns from the call result, such as a missing file failing to read or a failed send not being delivered.\n- **Describe behavior, not implementation.** State what the tool does and returns; omit internal mechanisms, output markers the model sees in results, and enforcement details.\n- **Put parameter rules on the parameter.** Defaults, ranges, pairing, and when-to-set rules belong in that parameter's description or schema; a description that varies with configuration usually means the varying part belongs to a parameter.\n- **Say each fact once.** Do not repeat the tool definition in its system-prompt section, a parameter description in the tool description, or one tool's rules in another tool.\n- **Measure the change.** Compare first-turn prompt tokens before and after a tool-definition change.\n",{"name":5,"metadata":24,"description":7},{"date":25},"2026-09-11","stable","e1afeb6cb36b3d087b063999192dc27167bb9221",".agents\u002Fskills\u002Fagent-experience","https:\u002F\u002Fgithub.com\u002FDarthph0enix7\u002FEnpoi-harness","https:\u002F\u002Fgithub.com\u002FDarthph0enix7","https:\u002F\u002Feren.enpoi.com","2026-11-14 07:20:03",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add Darthph0enix7\u002FEnpoi-harness --skill agent-experience",{"tool":39,"command":40},"bunx","bunx skills add Darthph0enix7\u002FEnpoi-harness --skill agent-experience",{"tool":42,"command":43},"pnpm","pnpm dlx skills add Darthph0enix7\u002FEnpoi-harness --skill agent-experience","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FDarthph0enix7\u002FEnpoi-harness\u002Fblob\u002Fstable\u002F.agents\u002Fskills\u002Fagent-experience\u002FSKILL.md",true,[],[48,55,62,69,76,83],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M7AZ9FBAME46EHHX8WZY0NMJ","user-only-skill","Prove model-disabled skills stay outside the model catalog.","https:\u002F\u002Fgithub.com\u002FDarthph0enix7\u002FEnpoi-harness\u002Fblob\u002Fstable\u002Fsnapshots\u002Fsession\u002Fskill-load\u002Fworkspace\u002F.dsh\u002Fskills\u002Fuser-only-skill\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M7AZ9DMBD63P0N69APH8JX2Q","snapshot-skill","Exercise project skill discovery and loading in snapshot tests.","https:\u002F\u002Fgithub.com\u002FDarthph0enix7\u002FEnpoi-harness\u002Fblob\u002Fstable\u002Fsnapshots\u002Fsession\u002Fskill-load\u002Fworkspace\u002F.dsh\u002Fskills\u002Fsnapshot-skill\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M7AZ9B7ETHFP8DB1HPMTNMZA","model-only-skill","Prove user-disabled skills remain available to the model.","https:\u002F\u002Fgithub.com\u002FDarthph0enix7\u002FEnpoi-harness\u002Fblob\u002Fstable\u002Fsnapshots\u002Fsession\u002Fskill-load\u002Fworkspace\u002F.dsh\u002Fskills\u002Fmodel-only-skill\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M7AZ97FV84XFGRT59MYM976A","tier3-workflow","The \"All Out\" Tier. Complex implementation with continuous Oracle supervision and Roundtable ambiguity resolution.","https:\u002F\u002Fgithub.com\u002FDarthph0enix7\u002FEnpoi-harness\u002Fblob\u002Fstable\u002Fprofile\u002Fweb\u002Fskills\u002Ftier3-workflow\u002FSKILL.md",[],[],{"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":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M7AZ93373GE2QZ43NER37DYT","tier2-workflow","Sophisticated ideation and planning. Mandatory roundtable tool usage for vision expansion before technical implementation.","https:\u002F\u002Fgithub.com\u002FDarthph0enix7\u002FEnpoi-harness\u002Fblob\u002Fstable\u002Fprofile\u002Fweb\u002Fskills\u002Ftier2-workflow\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M7AZ90RHMJTBVS8DXYHSYQ8V","tier1-workflow","Guided and supervised workflow. Mandatory Oracle reviews for planning and final implementation.","https:\u002F\u002Fgithub.com\u002FDarthph0enix7\u002FEnpoi-harness\u002Fblob\u002Fstable\u002Fprofile\u002Fweb\u002Fskills\u002Ftier1-workflow\u002FSKILL.md",[],[]]