[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78F5YTY32F9QPV8QCM6601Y":3,"skill-same:01M78F5YTY32F9QPV8QCM6601Y":44},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M78F5YTY32F9QPV8QCM6601Y","condensing-instructions",null,"Refine an instruction document for Claude 5 generation models: cut rules the model's judgment already covers, move detail behind progressive disclosure, and route each remaining piece to the system prompt, CLAUDE.md, a skill, or a reference. Use for system prompts, CLAUDE.md files, skills, tool descriptions, agent instructions, context engineering, prompt slimming, and token reduction.","jl-cmd-projects\u002Fclaude-dev-env","jl-cmd-projects","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F338158757?v=4","01M78F4M55P4QY5YPN27XBQA9N","01M78F4M65AGEYC88NV6PW4715",7,"MIT","https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fpackages\u002Fclaude-dev-env\u002F.agents\u002Fskills-archived\u002Fcondensing-instructions\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: condensing-instructions\ndescription: >-\n  Refine an instruction document for Claude 5 generation models: cut rules the\n  model's judgment already covers, move detail behind progressive disclosure,\n  and route each remaining piece to the system prompt, CLAUDE.md, a skill, or a\n  reference. Use for system prompts, CLAUDE.md files, skills, tool\n  descriptions, agent instructions, context engineering, prompt slimming, and\n  token reduction.\n---\n\n# Condensing Instructions\n\nCut an instruction document to what a Claude 5 generation model needs, and move the rest to the surface that loads it on demand. Over 80% of Claude Code's system prompt came out for Claude Opus 5 and Claude Fable 5 with no measurable drop in performance, so treat a long instruction document as a place with room to cut.\n\n## Clear the conflicts first\n\nRead the system prompt, the CLAUDE.md, and the skills as one body of text and find the lines that pull against each other — \"leave documentation as appropriate\" sitting beside \"DO NOT add comments\". A conflict makes the model deliberate at length before it acts. Resolve each pair into one statement, or delete both when neither changes what the model does.\n\n## Trade rules for judgment\n\nDelete a rule written to block a worst case, such as file deletion. Claude 5 generation models read the surrounding context and decide well without it, and a rigid rule blocks the user who has a real reason to want the behavior it forbids.\n\nState the outcome and the signal the model should read:\n\n- Cut: \"Default to writing no comments. Never write multi-paragraph docstrings or multi-line comment blocks — one short line max. Don't create planning, decision, or analysis documents unless the user asks for them.\"\n- Keep: \"Write code that reads like the surrounding code: match its comment density, naming, and idiom.\"\n\n## Design the interface in place of examples\n\nExamples constrain exploration. Carry usage in the tool's own shape: expressive names, expressive parameters, and types that signal intent. A status parameter enumerated as `pending`, `in_progress`, `completed` shows correct use with no example attached.\n\n## Load detail at the point of use\n\nMove detail out of always-on text and into a surface the model reaches for:\n\n- A skill the model calls when the task calls for it. Code review and verification detail belongs here.\n- A linked file the model opens on demand.\n- A tool with deferred loading, where the model searches for the definition before it uses the tool.\n\nKeep the always-on context lean and let the model pull the rest.\n\n## Say each thing once\n\nPut tool usage guidance in the tool description alone. Delete the copy that repeats it in the system prompt.\n\n## Let memory carry session facts\n\nClaude's automatic memory captures relevant context and carries it across sessions. Delete hand-written memory notes from CLAUDE.md when memory already holds them.\n\n## Point at rich references\n\nInclude files as references with @mentions. Prefer a reference the model can read with no ambiguity, in this order:\n\n1. Code from this or another codebase — the highest fidelity specification available.\n2. A test suite that pins the behavior.\n3. An HTML artifact or a mockup.\n4. A rubric, which lets a verification agent score work against a quality standard.\n5. Prose description or a screenshot.\n\n## Route what remains\n\n| Surface | What belongs there |\n|---|---|\n| System prompt | The product Claude works within and the role it plays. For a custom agent, spend real effort here. |\n| CLAUDE.md | A short line on what the repository is, then the gotchas found inside the codebase. Drop anything the model can read off the file structure. Link to skills for the detail. |\n| Skills | Opinions, knowledge, and practices particular to your team or product, written as a guide the model consults. Split a long skill into several files. Constrain only where it matters. |\n| References | Specs, mockups, and codebases pulled in by @mention. |\n\n## Deliver\n\nRewrite the document in place and report what moved to which surface. Offer `claude doctor` as a follow-up pass — it rightsizes skills and CLAUDE.md files against these same rules.\n","# Condensing Instructions\n\nCut an instruction document to what a Claude 5 generation model needs, and move the rest to the surface that loads it on demand. Over 80% of Claude Code's system prompt came out for Claude Opus 5 and Claude Fable 5 with no measurable drop in performance, so treat a long instruction document as a place with room to cut.\n\n## Clear the conflicts first\n\nRead the system prompt, the CLAUDE.md, and the skills as one body of text and find the lines that pull against each other — \"leave documentation as appropriate\" sitting beside \"DO NOT add comments\". A conflict makes the model deliberate at length before it acts. Resolve each pair into one statement, or delete both when neither changes what the model does.\n\n## Trade rules for judgment\n\nDelete a rule written to block a worst case, such as file deletion. Claude 5 generation models read the surrounding context and decide well without it, and a rigid rule blocks the user who has a real reason to want the behavior it forbids.\n\nState the outcome and the signal the model should read:\n\n- Cut: \"Default to writing no comments. Never write multi-paragraph docstrings or multi-line comment blocks — one short line max. Don't create planning, decision, or analysis documents unless the user asks for them.\"\n- Keep: \"Write code that reads like the surrounding code: match its comment density, naming, and idiom.\"\n\n## Design the interface in place of examples\n\nExamples constrain exploration. Carry usage in the tool's own shape: expressive names, expressive parameters, and types that signal intent. A status parameter enumerated as `pending`, `in_progress`, `completed` shows correct use with no example attached.\n\n## Load detail at the point of use\n\nMove detail out of always-on text and into a surface the model reaches for:\n\n- A skill the model calls when the task calls for it. Code review and verification detail belongs here.\n- A linked file the model opens on demand.\n- A tool with deferred loading, where the model searches for the definition before it uses the tool.\n\nKeep the always-on context lean and let the model pull the rest.\n\n## Say each thing once\n\nPut tool usage guidance in the tool description alone. Delete the copy that repeats it in the system prompt.\n\n## Let memory carry session facts\n\nClaude's automatic memory captures relevant context and carries it across sessions. Delete hand-written memory notes from CLAUDE.md when memory already holds them.\n\n## Point at rich references\n\nInclude files as references with @mentions. Prefer a reference the model can read with no ambiguity, in this order:\n\n1. Code from this or another codebase — the highest fidelity specification available.\n2. A test suite that pins the behavior.\n3. An HTML artifact or a mockup.\n4. A rubric, which lets a verification agent score work against a quality standard.\n5. Prose description or a screenshot.\n\n## Route what remains\n\n| Surface | What belongs there |\n|---|---|\n| System prompt | The product Claude works within and the role it plays. For a custom agent, spend real effort here. |\n| CLAUDE.md | A short line on what the repository is, then the gotchas found inside the codebase. Drop anything the model can read off the file structure. Link to skills for the detail. |\n| Skills | Opinions, knowledge, and practices particular to your team or product, written as a guide the model consults. Split a long skill into several files. Constrain only where it matters. |\n| References | Specs, mockups, and codebases pulled in by @mention. |\n\n## Deliver\n\nRewrite the document in place and report what moved to which surface. Offer `claude doctor` as a follow-up pass — it rightsizes skills and CLAUDE.md files against these same rules.\n",{"name":5,"description":7},"main","974284b42eeb4609e94d4ebc1f6e36df400d54ca","packages\u002Fclaude-dev-env\u002F.agents\u002Fskills-archived\u002Fcondensing-instructions",1,"https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env","https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects","2026-11-15 05:02:47",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add jl-cmd-projects\u002Fclaude-dev-env --skill condensing-instructions",{"tool":36,"command":37},"bunx","bunx skills add jl-cmd-projects\u002Fclaude-dev-env --skill condensing-instructions",{"tool":39,"command":40},"pnpm","pnpm dlx skills add jl-cmd-projects\u002Fclaude-dev-env --skill condensing-instructions","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fpackages\u002Fclaude-dev-env\u002F.agents\u002Fskills-archived\u002Fcondensing-instructions\u002FSKILL.md",true,[],[45,52,59,66,73,80],{"skillNo":46,"name":47,"nameZh":6,"description":48,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":49,"categories":50,"keywords":51,"publishedAt":18},"01M78FER7S09AE87MMJFT1E87E","update","Fast-forwards a local repository's main branch to a remote's main after confirming the repo path and source remote through AskUserQuestion. Use when the user says '\u002Fupdate', 'update main', 'fast-forward main', 'sync main from origin', 'pull latest main into \u003Cpath>', or 'bring main up to date'.","https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fskill-archive\u002Fupdate\u002FSKILL.md",[],[],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":18},"01M78FENWZS01MB4PMGX6801X6","source-command-sr-loop","Converging cleanup loop: repeat \u002Fsimplify until clean, then repeat \u002Fcode-review --fix until clean","https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fskill-archive\u002Fsource-command-sr-loop\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":18},"01M78FEGZ7JDWEG3RM78M9Y8F8","skill-builder","Skill lifecycle: classify, scaffold, write via the skill-writer-agent, self-audit, compose sub-skills, polish description triggers, enforce deterministic scripts. Triggers: build a skill, new skill workflow, improve this skill, optimize skill description, skill development lifecycle, skill modularity, skill composition, description trigger catalog, deterministic skill scripts.","https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fskill-archive\u002Fskill-builder\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":18},"01M78FEDEYHJYKTER9S566DMEZ","session-tidy","Audit, clean, and consolidate session logs in the Obsidian vault. Fixes format drift, resolves orphaned next-steps, updates stale statuses, and generates project rollup summaries. Use when session logs feel cluttered or before starting a new project milestone. Triggers on '\u002Fsession-tidy', 'tidy sessions', 'clean up session logs', 'session audit'.","https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fskill-archive\u002Fsession-tidy\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":18},"01M78FE8QR789SKBF3A78N2T13","session-log","Logs a session report as an HTML page, tracks vault context, extracts decisions, and outputs a \u002Frename command. Use for \u002Fsession-log, 'journal this session', 'log this work', 'session report', 'summarize\u002Flog\u002Frecord this session', 'save session', 'capture session', or 'document what we did'.","https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fskill-archive\u002Fsession-log\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":18},"01M78FE4JDJHKTJPWRWNQEX2HT","run-claude-dev-env","Build, install, run, and test the claude-dev-env installer. Use when asked to run claude-dev-env, install the Claude Code config into ~\u002F.claude, drive the installer, smoke-test it against a sandbox, or run its test suite.","https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fskill-archive\u002Frun-claude-dev-env\u002FSKILL.md",[],[]]