[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M74WVC0DPD810Y3WXRPEDZPN":3,"skill-same:01M74WVC0DPD810Y3WXRPEDZPN":45},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M74WVC0DPD810Y3WXRPEDZPN","writing-style",null,"Apply consistent writing style to commits, PR descriptions, issue bodies, and inline code comments. Invoke before writing any user-facing text to ensure it matches the project's established voice.","phaedrus1992\u002Fllmenv","phaedrus1992","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F22475972?v=4","01M74WTJB2Y3041TQR80DYKMAR","Phaedrus","01M74WTJBSJTG3HBYX6WSS3E0M",4,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fphaedrus1992\u002Fllmenv\u002Fblob\u002Fmain\u002Fexamples\u002Fconfig-llmenv-dir\u002Fbundles\u002Fbase\u002Fskills\u002Fwriting-style\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: writing-style\ndescription: >\n  Apply consistent writing style to commits, PR descriptions, issue bodies,\n  and inline code comments. Invoke before writing any user-facing text to\n  ensure it matches the project's established voice.\n---\n\n\u003C!--\n  This skill lives in bundles\u002Fbase\u002Fskills\u002Fwriting-style\u002F so it's available\n  in every session (base bundle fires for user-alice always).\n\n  SKILL.md files are injected as agent context when the skill is invoked.\n  The frontmatter `name` and `description` fields control how llmenv\n  materializes the skill as a plugin slash-command.\n\n  This particular skill encodes a personal writing voice so that Claude\n  produces commits and PR descriptions that sound like the author wrote them,\n  not like a language model summarizing a diff. Adapt the sections below to\n  your own style.\n\n  HOW IT CONNECTS TO THE REST OF THE SYSTEM:\n    - Invoked explicitly: user types `\u002Fwriting-style` or Claude invokes it\n      when writing commit messages or PR descriptions.\n    - The skill is loaded from this SKILL.md into the agent's context.\n    - It doesn't require any special hooks or MCP servers — it's pure\n      context injection.\n-->\n\n# Writing Style Guide\n\nUse this guide whenever writing commits, PR titles\u002Fbodies, issue descriptions,\nor inline comments. The goal is prose that reads as if a senior engineer wrote\nit in a Slack message: direct, specific, no ceremony.\n\n## Core Principles\n\n- **Direct**: lead with the fact, not a preamble.\n- **Specific**: name the thing, not \"the functionality\" or \"the component\".\n- **Brief**: one sentence is better than three when one works.\n- **Technical but not jargon-heavy**: write for a peer who knows the system,\n  not for a documentation audience.\n\n## Commit messages\n\nFormat: imperative mood, ≤72 characters, present tense.\n\n```text\nAdd rate limiting to the ingest endpoint\nFix off-by-one in page cursor calculation\nDrop unused `legacy_auth` middleware\n```\n\nWhat NOT to do:\n\n```text\n# Too long, passive voice, vague\nAdded some changes to fix the issue with the rate limiting that was\ncausing problems in the endpoint\n\n# Marketing speak\nImplement robust, enterprise-grade rate limiting solution\n```\n\nThe subject line is a command to the codebase: \"Do X.\" If the subject needs\nmore than ~72 chars, the change is probably too big for one commit.\n\n## PR descriptions\n\nLead with what the code does *now*, not what you changed or why you changed it.\n\n**Good:**\n> The ingest endpoint now rejects requests above 100 req\u002Fs per API key with\n> a 429. Burst headroom is 20 extra requests; the window is a sliding 60s.\n\n**Bad:**\n> This PR adds rate limiting. I decided to use a sliding window because token\n> bucket was too complex. I also considered leaky bucket but rejected it.\n\nSkip: \"In this PR\", \"This change\", \"As part of this work\". Start with the\nsystem behavior.\n\n## Issue descriptions\n\nState the problem, not the investigation. Assume the reader is a peer who\nwill act on it.\n\n**Good:**\n> `cargo test` on a fresh checkout fails with `error[E0432]: unresolved import`\n> on `crate::auth::Token`. Introduced in #314. Bisect points to the rename in\n> `src\u002Fauth\u002Fmod.rs:47`.\n\n**Bad:**\n> I was trying to run the tests and encountered an error. After some\n> investigation I believe there might be an issue with the imports.\n\n## Inline code comments\n\nOnly write a comment when the WHY is non-obvious. Never explain WHAT.\n\n```rust\n\u002F\u002F ponytail: global lock; per-account locks if throughput matters\nlet _guard = GLOBAL_LOCK.lock().await;\n```\n\nNot:\n\n```rust\n\u002F\u002F Lock the global lock to ensure thread safety\nlet _guard = GLOBAL_LOCK.lock().await;\n```\n\n## Tone markers\n\n- OK: \"This breaks X\", \"Avoids the O(n²) scan\", \"Skipped Y — only matters if Z\"\n- Not OK: \"This enhancement improves\", \"Leverages\", \"Robust\", \"Seamless\"\n- Hedging: only when genuine uncertainty exists. \"Probably\" and \"might\" are fine\n  when you mean them; drop them when you're certain.\n","\u003C!--\n  This skill lives in bundles\u002Fbase\u002Fskills\u002Fwriting-style\u002F so it's available\n  in every session (base bundle fires for user-alice always).\n\n  SKILL.md files are injected as agent context when the skill is invoked.\n  The frontmatter `name` and `description` fields control how llmenv\n  materializes the skill as a plugin slash-command.\n\n  This particular skill encodes a personal writing voice so that Claude\n  produces commits and PR descriptions that sound like the author wrote them,\n  not like a language model summarizing a diff. Adapt the sections below to\n  your own style.\n\n  HOW IT CONNECTS TO THE REST OF THE SYSTEM:\n    - Invoked explicitly: user types `\u002Fwriting-style` or Claude invokes it\n      when writing commit messages or PR descriptions.\n    - The skill is loaded from this SKILL.md into the agent's context.\n    - It doesn't require any special hooks or MCP servers — it's pure\n      context injection.\n-->\n\n# Writing Style Guide\n\nUse this guide whenever writing commits, PR titles\u002Fbodies, issue descriptions,\nor inline comments. The goal is prose that reads as if a senior engineer wrote\nit in a Slack message: direct, specific, no ceremony.\n\n## Core Principles\n\n- **Direct**: lead with the fact, not a preamble.\n- **Specific**: name the thing, not \"the functionality\" or \"the component\".\n- **Brief**: one sentence is better than three when one works.\n- **Technical but not jargon-heavy**: write for a peer who knows the system,\n  not for a documentation audience.\n\n## Commit messages\n\nFormat: imperative mood, ≤72 characters, present tense.\n\n```text\nAdd rate limiting to the ingest endpoint\nFix off-by-one in page cursor calculation\nDrop unused `legacy_auth` middleware\n```\n\nWhat NOT to do:\n\n```text\n# Too long, passive voice, vague\nAdded some changes to fix the issue with the rate limiting that was\ncausing problems in the endpoint\n\n# Marketing speak\nImplement robust, enterprise-grade rate limiting solution\n```\n\nThe subject line is a command to the codebase: \"Do X.\" If the subject needs\nmore than ~72 chars, the change is probably too big for one commit.\n\n## PR descriptions\n\nLead with what the code does *now*, not what you changed or why you changed it.\n\n**Good:**\n> The ingest endpoint now rejects requests above 100 req\u002Fs per API key with\n> a 429. Burst headroom is 20 extra requests; the window is a sliding 60s.\n\n**Bad:**\n> This PR adds rate limiting. I decided to use a sliding window because token\n> bucket was too complex. I also considered leaky bucket but rejected it.\n\nSkip: \"In this PR\", \"This change\", \"As part of this work\". Start with the\nsystem behavior.\n\n## Issue descriptions\n\nState the problem, not the investigation. Assume the reader is a peer who\nwill act on it.\n\n**Good:**\n> `cargo test` on a fresh checkout fails with `error[E0432]: unresolved import`\n> on `crate::auth::Token`. Introduced in #314. Bisect points to the rename in\n> `src\u002Fauth\u002Fmod.rs:47`.\n\n**Bad:**\n> I was trying to run the tests and encountered an error. After some\n> investigation I believe there might be an issue with the imports.\n\n## Inline code comments\n\nOnly write a comment when the WHY is non-obvious. Never explain WHAT.\n\n```rust\n\u002F\u002F ponytail: global lock; per-account locks if throughput matters\nlet _guard = GLOBAL_LOCK.lock().await;\n```\n\nNot:\n\n```rust\n\u002F\u002F Lock the global lock to ensure thread safety\nlet _guard = GLOBAL_LOCK.lock().await;\n```\n\n## Tone markers\n\n- OK: \"This breaks X\", \"Avoids the O(n²) scan\", \"Skipped Y — only matters if Z\"\n- Not OK: \"This enhancement improves\", \"Leverages\", \"Robust\", \"Seamless\"\n- Hedging: only when genuine uncertainty exists. \"Probably\" and \"might\" are fine\n  when you mean them; drop them when you're certain.\n",{"name":5,"description":7},"main","2ccf515b8e8251dfd0392546073a1baaf42e79cf","examples\u002Fconfig-llmenv-dir\u002Fbundles\u002Fbase\u002Fskills\u002Fwriting-style",1,"https:\u002F\u002Fgithub.com\u002Fphaedrus1992\u002Fllmenv","https:\u002F\u002Fgithub.com\u002Fphaedrus1992","2026-11-15 01:43:22",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add phaedrus1992\u002Fllmenv --skill writing-style",{"tool":37,"command":38},"bunx","bunx skills add phaedrus1992\u002Fllmenv --skill writing-style",{"tool":40,"command":41},"pnpm","pnpm dlx skills add phaedrus1992\u002Fllmenv --skill writing-style","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fphaedrus1992\u002Fllmenv\u002Fblob\u002Fmain\u002Fexamples\u002Fconfig-llmenv-dir\u002Fbundles\u002Fbase\u002Fskills\u002Fwriting-style\u002FSKILL.md",true,[],[46,53,60,67,74,81],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":19},"01M74WW2BKBJSM8QS9BAEYMC24","clippy","Rust clippy linter skill","https:\u002F\u002Fgithub.com\u002Fphaedrus1992\u002Fllmenv\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fbundles\u002Frust-defaults\u002Fskills\u002Fclippy\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M74WW0P1A8YWDVYM864T6J5X","hello","Hello world skill","https:\u002F\u002Fgithub.com\u002Fphaedrus1992\u002Fllmenv\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fbundles\u002Fbase\u002Fskills\u002Fhello\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M74WVXR7Y3XMRDXXVGTZD9HT","setup-llmenv","Interactive setup wizard for new llmenv users. Evaluates existing Claude Code configuration, helps sort into bundles, and writes llmenv-native equivalents.","https:\u002F\u002Fgithub.com\u002Fphaedrus1992\u002Fllmenv\u002Fblob\u002Fmain\u002Fskills\u002Fsetup-llmenv\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M74WVVKQPW6TKJHCTB5WHQKG","llmenv","How to use llmenv's built-in features (task tracker, memory, context-mode, codebase-memory) effectively. Load this first; it points to a reference file per enabled feature rather than dumping all of them into context.","https:\u002F\u002Fgithub.com\u002Fphaedrus1992\u002Fllmenv\u002Fblob\u002Fmain\u002Fskills\u002Fllmenv\u002FSKILL.md",[],[],{"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":80,"publishedAt":19},"01M74WVQEJ1S6T2M3DEF3JJF66","fyi","Use when the user asks for an \"fyi\", \"morning todo\", \"morning briefing\", \"what's on my plate\", \"what do I have open\", \"what's in flight\", \"where did I leave off\", \"what needs my attention today\", or \"my open work across projects\". Surveys the user's currently-open, in-flight, and pending work across GitHub, Linear, Slack, Pylon, and Notion, then produces a ranked, GitHub-markdown briefing for the day. Forward-looking sibling of daily-update (which reports what already happened).","https:\u002F\u002Fgithub.com\u002Fphaedrus1992\u002Fllmenv\u002Fblob\u002Fmain\u002Fexamples\u002Fconfig-llmenv-dir\u002Fbundles\u002Fwork\u002Fskills\u002Ffyi\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M74WVMF20C830E3NT7GSJH2P","daily-update","Use when the user asks for a \"standup\", \"scrum update\", \"daily update\", \"status update\", \"what did I work on\", or \"what did I do yesterday\". Scans llmenv session logs, Linear, Slack, and GitHub for the user's own activity on a given day and produces a short scrum-style update, copied to the clipboard as Slack markdown.","https:\u002F\u002Fgithub.com\u002Fphaedrus1992\u002Fllmenv\u002Fblob\u002Fmain\u002Fexamples\u002Fconfig-llmenv-dir\u002Fbundles\u002Fwork\u002Fskills\u002Fdaily-update\u002FSKILL.md",[],[]]