[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7ASMRB5H5EYTWJ2R9JSG5SN":3,"skill-same:01M7ASMRB5H5EYTWJ2R9JSG5SN":57},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"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":29,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M7ASMRB5H5EYTWJ2R9JSG5SN","headroom",null,"Evaluate or integrate Headroom for large repetitive tool outputs, JSON, logs, or retrieved context. Use when the user names Headroom or asks to measure context compression in an application they control. Start with a local library trial; not a default proxy, provider switch, prose-shortening mode, or solution for an ordinary small command result.","saski\u002Farnesto","saski","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F140356?v=4","01M7ASBDSNXTRYDYB4K1PEA1RV","01M7ASBDTAKBDAAV99S1GE7HK6",6,"Unlicense","https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fheadroom\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: headroom\ndescription: >\n  Evaluate or integrate Headroom for large repetitive tool outputs, JSON, logs,\n  or retrieved context. Use when the user names Headroom or asks to measure\n  context compression in an application they control. Start with a local\n  library trial; not a default proxy, provider switch, prose-shortening mode,\n  or solution for an ordinary small command result.\n---\n\n# Headroom\n\nTreat compression as a transformation that must preserve task-critical\nevidence. Start with a synthetic local example, then compare representative\npayloads before changing any running agent's request path.\n\n## Choose the integration\n\n- Prefer upstream query filtering, bounded reads, or RTK for simple shell\n  output. Avoid stacking compressors without measuring the combined result.\n- Use the Python library when the application owns the request payload. The\n  reviewed package is `headroom-ai==0.39.1`, requiring Python 3.10 or newer.\n- A proxy, `headroom wrap`, or MCP installation is a separate integration:\n  those paths can change provider routing, credentials handling, configuration,\n  and stored context. Inspect those changes before applying them; this skill\n  does not authorize a client migration or imply desktop-client compatibility.\n\n## Start locally\n\nUse the project's dependency manager, or an isolated environment for a trial.\nInstall the pinned base package, not `[all]`, for the example in\n[local trial](references\u002Flocal-trial.md). Disable telemetry and update checks\nbefore running it. The example uses no API key and makes no LLM request.\n\n```python\nfrom headroom import CompressConfig, compress\n\nresult = compress(\n    messages,\n    model=\"gpt-4o\",  # Tokenizer selection for this example; no model request.\n    config=CompressConfig(\n        kompress_model=\"disabled\",\n        compress_system_messages=False,\n        compress_user_messages=False,\n        protect_recent=4,\n    ),\n)\n```\n\nUse the actual target model's supported tokenizer for a real evaluation. A\nfirst tokenizer load can require a vocabulary download. Do not report estimated\ncounts as measured tokens. Disabling Kompress avoids its ML-model download;\nit does not make initial package\u002Ftokenizer installation offline.\n\n## Check evidence preservation\n\n1. Retain the original payload separately. Library compression is lossy; full\n   retrieval requires a working retained store and retrieval integration.\n2. Verify system instructions, current user intent, and recent messages remain\n   intact. Protect tool-call IDs, relevant errors, rare outliers, and exact data\n   needed by the task. Do not truncate away permission or policy information.\n3. Compare downstream answers and required assertions with and without\n   compression. Token reduction alone is not success.\n4. If data is missing, counts are estimates, the store is unavailable, or\n   correctness regresses, use the original payload and report the limitation.\n\n## Report and contain the trial\n\nReport package version, configuration, original and compressed token counts,\npreservation checks, and whether a provider was actually tested. Keep cache,\nlogs, retained payloads, and databases outside Git. In-memory retrieval ends\nwith the process; do not promise reversible recovery after it exits.\n\nArnesto supplies this optional runbook. It does not enable a proxy, install an\nMCP server, change OmniRoute, or claim end-to-end savings from a local fixture.\n","# Headroom\n\nTreat compression as a transformation that must preserve task-critical\nevidence. Start with a synthetic local example, then compare representative\npayloads before changing any running agent's request path.\n\n## Choose the integration\n\n- Prefer upstream query filtering, bounded reads, or RTK for simple shell\n  output. Avoid stacking compressors without measuring the combined result.\n- Use the Python library when the application owns the request payload. The\n  reviewed package is `headroom-ai==0.39.1`, requiring Python 3.10 or newer.\n- A proxy, `headroom wrap`, or MCP installation is a separate integration:\n  those paths can change provider routing, credentials handling, configuration,\n  and stored context. Inspect those changes before applying them; this skill\n  does not authorize a client migration or imply desktop-client compatibility.\n\n## Start locally\n\nUse the project's dependency manager, or an isolated environment for a trial.\nInstall the pinned base package, not `[all]`, for the example in\n[local trial](references\u002Flocal-trial.md). Disable telemetry and update checks\nbefore running it. The example uses no API key and makes no LLM request.\n\n```python\nfrom headroom import CompressConfig, compress\n\nresult = compress(\n    messages,\n    model=\"gpt-4o\",  # Tokenizer selection for this example; no model request.\n    config=CompressConfig(\n        kompress_model=\"disabled\",\n        compress_system_messages=False,\n        compress_user_messages=False,\n        protect_recent=4,\n    ),\n)\n```\n\nUse the actual target model's supported tokenizer for a real evaluation. A\nfirst tokenizer load can require a vocabulary download. Do not report estimated\ncounts as measured tokens. Disabling Kompress avoids its ML-model download;\nit does not make initial package\u002Ftokenizer installation offline.\n\n## Check evidence preservation\n\n1. Retain the original payload separately. Library compression is lossy; full\n   retrieval requires a working retained store and retrieval integration.\n2. Verify system instructions, current user intent, and recent messages remain\n   intact. Protect tool-call IDs, relevant errors, rare outliers, and exact data\n   needed by the task. Do not truncate away permission or policy information.\n3. Compare downstream answers and required assertions with and without\n   compression. Token reduction alone is not success.\n4. If data is missing, counts are estimates, the store is unavailable, or\n   correctness regresses, use the original payload and report the limitation.\n\n## Report and contain the trial\n\nReport package version, configuration, original and compressed token counts,\npreservation checks, and whether a provider was actually tested. Keep cache,\nlogs, retained payloads, and databases outside Git. In-memory retrieval ends\nwith the process; do not promise reversible recovery after it exits.\n\nArnesto supplies this optional runbook. It does not enable a proxy, install an\nMCP server, change OmniRoute, or claim end-to-end savings from a local fixture.\n",{"name":5,"description":7},"main","3c24fc2c035029b08c7326774bee3fef8fb95566",".agents\u002Fskills\u002Fheadroom",0,"https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto","https:\u002F\u002Fgithub.com\u002Fsaski","http:\u002F\u002Fsaski.com","2026-11-12 20:09:16",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add saski\u002Farnesto --skill headroom",{"tool":37,"command":38},"bunx","bunx skills add saski\u002Farnesto --skill headroom",{"tool":40,"command":41},"pnpm","pnpm dlx skills add saski\u002Farnesto --skill headroom","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fheadroom\u002FSKILL.md",true,[45,51],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"references\u002Flocal-smoke.py","SCRIPT","脚本",2765,"https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fheadroom\u002Freferences\u002Flocal-smoke.py",{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Flocal-trial.md","REFERENCE","参考文档",3436,"https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fheadroom\u002Freferences\u002Flocal-trial.md",[58,65,72,79,86,93],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":18},"01M7AT7F5FSHNAMFMF01N0QA1X","visualize","Use \u002Fvisualize for creating compact charts, diagrams, or other visuals inline as part of the conversation itself. It chooses among Markdown tables, Mermaid, inline HTML, and other supported in-transcript forms. Use Canvas for durable artifacts outside the transcript that users may revisit, refine, or share.","https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.cursor\u002Fskills-cursor\u002Fvisualize\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":18},"01M7AT79MHSAR3JDDMP7DGERM9","update-cursor-settings","Modify Cursor\u002FVSCode user settings in settings.json. Use when you want to change editor settings, preferences, configuration, themes, font size, tab size, format on save, auto save, keybindings, or any settings.json values.","https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.cursor\u002Fskills-cursor\u002Fupdate-cursor-settings\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":18},"01M7AT73WF3Y22E0FKYAMCCJES","update-cli-config","View and modify Cursor CLI configuration settings in ~\u002F.cursor\u002Fcli-config.json. Use when the user wants to change CLI settings, configure permissions, switch approval mode, enable vim mode, toggle display options, configure sandbox, or manage any CLI preferences.","https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.cursor\u002Fskills-cursor\u002Fupdate-cli-config\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":18},"01M7AT6F3FBP85AJJ5BJNR8B5W","statusline","Configure a custom status line in the CLI. Use when the user mentions status line, statusline, statusLine, CLI status bar, prompt footer customization, or wants to add session context above the prompt.","https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.cursor\u002Fskills-cursor\u002Fstatusline\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":18},"01M7AT6D24QFS5XRAFN8S5XJ7W","split-to-prs","Split current work into small reviewable PRs. Use when the user asks to split a chat, set of changes, branch, or PR.","https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.cursor\u002Fskills-cursor\u002Fsplit-to-prs\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":18},"01M7AT69FYFN84XZKW452JV5DF","shell","Runs the rest of a \u002Fshell request as a literal shell command. Use only when the user explicitly invokes \u002Fshell and wants the following text executed directly in the terminal.","https:\u002F\u002Fgithub.com\u002Fsaski\u002Farnesto\u002Fblob\u002Fmain\u002F.cursor\u002Fskills-cursor\u002Fshell\u002FSKILL.md",[],[]]