[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M74WVMF20C830E3NT7GSJH2P":3,"skill-same:01M74WVMF20C830E3NT7GSJH2P":56},{"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":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":47},"01M74WVMF20C830E3NT7GSJH2P","daily-update",null,"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.","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\u002Fwork\u002Fskills\u002Fdaily-update\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: daily-update\ndescription: 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.\nresources:\n  - scripts\u002Fscan-sessions.mjs\n  - scripts\u002Fgh-activity.sh\n---\n\n# Daily Update\n\nProduce a short, paste-ready scrum\u002Fstandup update from the user's real activity\nacross four sources. Default day is **yesterday** (local time); honor any date or\nrange the user gives. End by copying the update to the clipboard.\n\nThis is a reporting task — **read-only everywhere**. Never post to Slack, edit\nLinear, or touch GitHub. The only side effect is the clipboard.\n\n## Required tools — no silent fallback\n\nEvery source and tool below is **required**, not best-effort. If any tool, MCP, or\nscript the skill depends on is unavailable or unauthenticated — the slack plugin not\nlogged in, the grid MCP disconnected, a script missing, Linear unreachable — **STOP\nand tell the user to fix or authenticate it.** Do NOT quietly fall back to a degraded\nsubset and produce a partial report: a standup that silently drops a whole source\nreads as \"that's all that happened\" when it isn't, and Slack in particular carries\nwork that never shows up in GitHub or Linear. The slack plugin needs an interactive\nOAuth login; if its search tools aren't registered, trigger its `authenticate` tool\nand wait for the user to complete the flow before continuing.\n\n## Sources (gather all four, in parallel)\n\n1. **llmenv session logs** — what the user actually did at the keyboard.\n\n   ```bash\n   \"${CLAUDE_CONFIG_DIR}\u002Fskills\u002Fdaily-update\u002Fscripts\u002Fscan-sessions.mjs\" --date \u003CYYYY-MM-DD>\n   ```\n\n   Emits a per-project digest: human prompts (noise-filtered) + the intent of any\n   compacted sessions. It scans **all** llmenv profile hashes plus user global claude\n   -- a single day routinely spans several projects and profiles, so trust the script\n   over any single transcript.\n\n2. **GitHub** — what shipped. Scope to the work org to cut noise.\n\n   ```bash\n   \"${CLAUDE_CONFIG_DIR}\u002Fskills\u002Fdaily-update\u002Fscripts\u002Fgh-activity.sh\" \u003CYYYY-MM-DD> \u003Cowner>\n   ```\n\n   Returns PRs updated\u002Fmerged, commits authored, and issues touched. Merged PRs and\n   commit subjects are the strongest \"done\" signal — prefer them over log chatter.\n\n3. **Linear** — issue status movement. List the user's issues and keep the ones\n   whose `updated_at` falls on the target day:\n   `mcp__grid__linear_list_issues(assignee=\"\u003Cuser work email>\")`. Use\n   `linear_read_issue` \u002F `linear_search_issues` only to clarify a specific ticket.\n   A status move is itself the work signal — an issue that went to **In Review** or\n   **In Progress** that day belongs in the update even when there's no merged PR,\n   commit, session log, or Slack mention for it. Don't require corroboration to\n   include a Linear item; missing these is the most common gap. Map state to section:\n   `Done`\u002F`Merged` → *Yesterday*, `In Review`\u002F`In Progress` → *Today* (or wherever\n   the day's framing puts it).\n\n4. **Slack** — discussions, decisions, handoffs. Two different tools, by intent —\n   use both:\n   - **The user's OWN messages** → the authenticated **slack plugin** MCP\n     (`mcp__plugin_slack_slack__*`), which searches *as the user*. Resolve their\n     Slack id first (`slack_search_users` on their work email, or read it straight\n     from the `slack_search_public_and_private` tool description, which states the\n     logged-in user's id), then:\n     `slack_search_public_and_private(query=\"from:\u003C@USER_ID> on:\u003CYYYY-MM-DD>\", sort=\"timestamp\")`.\n     **Page through all results** — a busy day exceeds the 20-result cap, so follow\n     the cursor until exhausted. This is the *only* tool that finds what the user\n     said; its `from:`\u002F`on:` operators work because it runs under the user's identity.\n   - **General team chatter about the user's issues** → the **grid** Slack tools\n     (`mcp__grid__slack_search_messages`). This is a bot-authenticated, full-text\n     content index: it **ignores `from:`\u002F`on:` operators** (so `from:@me` returns\n     nothing) and can't be scoped to the user — but it's useful for what *others*\n     said about a ticket or PR. Never use it as a substitute for the user's own\n     messages; it cannot surface them.\n   Long handoff\u002Fsummary messages the user posted are high-signal; one-word replies\n   and DM banter are not.\n\nRun the two scripts and the MCP queries concurrently. Process large script output\nwith `ctx_execute`\u002F`ctx_execute_file` rather than reading raw logs into context.\n\n## Synthesis\n\nCross-reference before writing — the sources correct each other:\n\n- **GitHub is ground truth for code.** If a log session guessed a PR's purpose, the\n  PR title\u002Fnumber wins. (E.g. a PR titled \"leader election\" is leader election,\n  even if a chat called it something else.)\n- **Map work to identifiers, and link them.** Tie each line to its PR (`#1234`),\n  Linear key (`ABC-1234` \u002F `DEF-1234`), or Slack thread where one exists. Every\n  identifier you mention must be a link, never bare text:\n  - Linear keys → `[ABC-1234](https:\u002F\u002Flinear.app\u002Fphaedrus1992\u002Fissue\u002FABC-1234)` (any\n    team prefix: ABC, DEF, JKL, etc. — same URL shape).\n  - GitHub PRs → `[#1234](https:\u002F\u002Fgithub.com\u002Fphaedrus1992\u002F\u003Crepo>\u002Fpull\u002F1234)`.\n  This applies to *every* mention, not just the headline item on a line.\n- **Linked follow-ups.** If the day's work created issues (you'll see \"create an ABC\n  issue…\" in the session logs), find each one in Linear and link it by key — don't\n  write \"filed follow-ups\" without saying which. Resolve the actual key via\n  `linear_search_issues`; the same prompt often spawns a mistaken duplicate on another\n  team that gets cancelled, so prefer the live ABC issue.\n- **Mind the timezone and the day boundary.** GitHub\u002F`gh` timestamps are UTC; the\n  user's day — and Slack timestamps — are local. A PR merged near midnight local time\n  can land on the adjacent UTC day in the `gh` results, so cross-check against the\n  Slack local-time activity before attributing it to the target day. And a standup the\n  user posted on the *morning* of the target day reports the *previous* day's work, not\n  the target day's — diff against it, but don't re-report its contents as the target\n  day's. Lean on the user's own Slack messages (local time) to anchor what actually\n  happened on the day in question.\n- **Collapse duplicates.** The same task usually appears in all four sources; report\n  it once.\n- **Don't drop a source that only one source knows about.** GitHub PRs are the spine,\n  but a Linear issue that moved with no PR, or a decision that lives only in Slack, is\n  still real work. Each source can contribute items the others miss — sweep all four,\n  don't let the PR list become the whole report.\n- **Drop non-work.** Banter, reactions, and off-topic DMs do not belong in a standup.\n\nBefore finalizing, sanity-check the draft against each source one more time: every\nLinear issue that moved on the day, every merged PR, and every substantive Slack\nhandoff should map to a bullet or be a deliberate drop — not an oversight. If an\nasync-standup bot or teammate posted a draft for the same day (often a DM), diff\nagainst it; anything it caught that you didn't is a gap to fold in.\n\n## Output format\n\nKeep it to a basic standup. Default shape:\n\n```text\n*Yesterday:*\n• \u003Cthing done> (\u003Cref>)\n• ...\n\n*Today:*\n• \u003Cnext step>\n\n*Blockers:* \u003Cblocker, or \"none\">\n```\n\n- Slack-flavored: `*bold*` (single asterisks), `•` bullets. No `#` headings, no tables.\n- Links use **markdown** form `[label](url)`, not Slack's `\u003Curl|label>` — the user's\n  Slack does not render the angle-bracket form.\n- No emoji. ASCII only — don't carry over Unicode arrows or symbols from source titles\n  (e.g. a PR titled \"vcluster↔EC\" becomes \"vcluster\u002FEC\", `->` instead of `→`).\n- Short. A handful of bullets per section — the user can ask for the long version.\n- **Write it in the user's voice: invoke the `bens-voice` skill** before drafting.\n  Plain and factual — a bug fix is a bug fix, not a \"critical stability improvement.\"\n\n## Deliver\n\nCopy the final update to the clipboard (macOS), then show it back in the reply:\n\n```bash\npbcopy \u003C\u003C'EOF'\n\u003Cthe update>\nEOF\n```\n\nConfirm it's on the clipboard and ready to paste into Slack.\n\n## Date handling\n\n- No date given → yesterday (the script default).\n- \"today\", \"this week\", a specific date, or a range → pass the matching `--date`\n  to the script and the same `on:`\u002F`after:`\u002F`before:` filters to Slack\u002FGitHub. For a\n  range, run the scan once per day or widen the GitHub\u002FSlack date filters and group\n  the result by day.\n","# Daily Update\n\nProduce a short, paste-ready scrum\u002Fstandup update from the user's real activity\nacross four sources. Default day is **yesterday** (local time); honor any date or\nrange the user gives. End by copying the update to the clipboard.\n\nThis is a reporting task — **read-only everywhere**. Never post to Slack, edit\nLinear, or touch GitHub. The only side effect is the clipboard.\n\n## Required tools — no silent fallback\n\nEvery source and tool below is **required**, not best-effort. If any tool, MCP, or\nscript the skill depends on is unavailable or unauthenticated — the slack plugin not\nlogged in, the grid MCP disconnected, a script missing, Linear unreachable — **STOP\nand tell the user to fix or authenticate it.** Do NOT quietly fall back to a degraded\nsubset and produce a partial report: a standup that silently drops a whole source\nreads as \"that's all that happened\" when it isn't, and Slack in particular carries\nwork that never shows up in GitHub or Linear. The slack plugin needs an interactive\nOAuth login; if its search tools aren't registered, trigger its `authenticate` tool\nand wait for the user to complete the flow before continuing.\n\n## Sources (gather all four, in parallel)\n\n1. **llmenv session logs** — what the user actually did at the keyboard.\n\n   ```bash\n   \"${CLAUDE_CONFIG_DIR}\u002Fskills\u002Fdaily-update\u002Fscripts\u002Fscan-sessions.mjs\" --date \u003CYYYY-MM-DD>\n   ```\n\n   Emits a per-project digest: human prompts (noise-filtered) + the intent of any\n   compacted sessions. It scans **all** llmenv profile hashes plus user global claude\n   -- a single day routinely spans several projects and profiles, so trust the script\n   over any single transcript.\n\n2. **GitHub** — what shipped. Scope to the work org to cut noise.\n\n   ```bash\n   \"${CLAUDE_CONFIG_DIR}\u002Fskills\u002Fdaily-update\u002Fscripts\u002Fgh-activity.sh\" \u003CYYYY-MM-DD> \u003Cowner>\n   ```\n\n   Returns PRs updated\u002Fmerged, commits authored, and issues touched. Merged PRs and\n   commit subjects are the strongest \"done\" signal — prefer them over log chatter.\n\n3. **Linear** — issue status movement. List the user's issues and keep the ones\n   whose `updated_at` falls on the target day:\n   `mcp__grid__linear_list_issues(assignee=\"\u003Cuser work email>\")`. Use\n   `linear_read_issue` \u002F `linear_search_issues` only to clarify a specific ticket.\n   A status move is itself the work signal — an issue that went to **In Review** or\n   **In Progress** that day belongs in the update even when there's no merged PR,\n   commit, session log, or Slack mention for it. Don't require corroboration to\n   include a Linear item; missing these is the most common gap. Map state to section:\n   `Done`\u002F`Merged` → *Yesterday*, `In Review`\u002F`In Progress` → *Today* (or wherever\n   the day's framing puts it).\n\n4. **Slack** — discussions, decisions, handoffs. Two different tools, by intent —\n   use both:\n   - **The user's OWN messages** → the authenticated **slack plugin** MCP\n     (`mcp__plugin_slack_slack__*`), which searches *as the user*. Resolve their\n     Slack id first (`slack_search_users` on their work email, or read it straight\n     from the `slack_search_public_and_private` tool description, which states the\n     logged-in user's id), then:\n     `slack_search_public_and_private(query=\"from:\u003C@USER_ID> on:\u003CYYYY-MM-DD>\", sort=\"timestamp\")`.\n     **Page through all results** — a busy day exceeds the 20-result cap, so follow\n     the cursor until exhausted. This is the *only* tool that finds what the user\n     said; its `from:`\u002F`on:` operators work because it runs under the user's identity.\n   - **General team chatter about the user's issues** → the **grid** Slack tools\n     (`mcp__grid__slack_search_messages`). This is a bot-authenticated, full-text\n     content index: it **ignores `from:`\u002F`on:` operators** (so `from:@me` returns\n     nothing) and can't be scoped to the user — but it's useful for what *others*\n     said about a ticket or PR. Never use it as a substitute for the user's own\n     messages; it cannot surface them.\n   Long handoff\u002Fsummary messages the user posted are high-signal; one-word replies\n   and DM banter are not.\n\nRun the two scripts and the MCP queries concurrently. Process large script output\nwith `ctx_execute`\u002F`ctx_execute_file` rather than reading raw logs into context.\n\n## Synthesis\n\nCross-reference before writing — the sources correct each other:\n\n- **GitHub is ground truth for code.** If a log session guessed a PR's purpose, the\n  PR title\u002Fnumber wins. (E.g. a PR titled \"leader election\" is leader election,\n  even if a chat called it something else.)\n- **Map work to identifiers, and link them.** Tie each line to its PR (`#1234`),\n  Linear key (`ABC-1234` \u002F `DEF-1234`), or Slack thread where one exists. Every\n  identifier you mention must be a link, never bare text:\n  - Linear keys → `[ABC-1234](https:\u002F\u002Flinear.app\u002Fphaedrus1992\u002Fissue\u002FABC-1234)` (any\n    team prefix: ABC, DEF, JKL, etc. — same URL shape).\n  - GitHub PRs → `[#1234](https:\u002F\u002Fgithub.com\u002Fphaedrus1992\u002F\u003Crepo>\u002Fpull\u002F1234)`.\n  This applies to *every* mention, not just the headline item on a line.\n- **Linked follow-ups.** If the day's work created issues (you'll see \"create an ABC\n  issue…\" in the session logs), find each one in Linear and link it by key — don't\n  write \"filed follow-ups\" without saying which. Resolve the actual key via\n  `linear_search_issues`; the same prompt often spawns a mistaken duplicate on another\n  team that gets cancelled, so prefer the live ABC issue.\n- **Mind the timezone and the day boundary.** GitHub\u002F`gh` timestamps are UTC; the\n  user's day — and Slack timestamps — are local. A PR merged near midnight local time\n  can land on the adjacent UTC day in the `gh` results, so cross-check against the\n  Slack local-time activity before attributing it to the target day. And a standup the\n  user posted on the *morning* of the target day reports the *previous* day's work, not\n  the target day's — diff against it, but don't re-report its contents as the target\n  day's. Lean on the user's own Slack messages (local time) to anchor what actually\n  happened on the day in question.\n- **Collapse duplicates.** The same task usually appears in all four sources; report\n  it once.\n- **Don't drop a source that only one source knows about.** GitHub PRs are the spine,\n  but a Linear issue that moved with no PR, or a decision that lives only in Slack, is\n  still real work. Each source can contribute items the others miss — sweep all four,\n  don't let the PR list become the whole report.\n- **Drop non-work.** Banter, reactions, and off-topic DMs do not belong in a standup.\n\nBefore finalizing, sanity-check the draft against each source one more time: every\nLinear issue that moved on the day, every merged PR, and every substantive Slack\nhandoff should map to a bullet or be a deliberate drop — not an oversight. If an\nasync-standup bot or teammate posted a draft for the same day (often a DM), diff\nagainst it; anything it caught that you didn't is a gap to fold in.\n\n## Output format\n\nKeep it to a basic standup. Default shape:\n\n```text\n*Yesterday:*\n• \u003Cthing done> (\u003Cref>)\n• ...\n\n*Today:*\n• \u003Cnext step>\n\n*Blockers:* \u003Cblocker, or \"none\">\n```\n\n- Slack-flavored: `*bold*` (single asterisks), `•` bullets. No `#` headings, no tables.\n- Links use **markdown** form `[label](url)`, not Slack's `\u003Curl|label>` — the user's\n  Slack does not render the angle-bracket form.\n- No emoji. ASCII only — don't carry over Unicode arrows or symbols from source titles\n  (e.g. a PR titled \"vcluster↔EC\" becomes \"vcluster\u002FEC\", `->` instead of `→`).\n- Short. A handful of bullets per section — the user can ask for the long version.\n- **Write it in the user's voice: invoke the `bens-voice` skill** before drafting.\n  Plain and factual — a bug fix is a bug fix, not a \"critical stability improvement.\"\n\n## Deliver\n\nCopy the final update to the clipboard (macOS), then show it back in the reply:\n\n```bash\npbcopy \u003C\u003C'EOF'\n\u003Cthe update>\nEOF\n```\n\nConfirm it's on the clipboard and ready to paste into Slack.\n\n## Date handling\n\n- No date given → yesterday (the script default).\n- \"today\", \"this week\", a specific date, or a range → pass the matching `--date`\n  to the script and the same `on:`\u002F`after:`\u002F`before:` filters to Slack\u002FGitHub. For a\n  range, run the scan once per day or widen the GitHub\u002FSlack date filters and group\n  the result by day.\n",{"name":5,"resources":24,"description":7},[25,26],"scripts\u002Fscan-sessions.mjs","scripts\u002Fgh-activity.sh","main","2ccf515b8e8251dfd0392546073a1baaf42e79cf","examples\u002Fconfig-llmenv-dir\u002Fbundles\u002Fwork\u002Fskills\u002Fdaily-update",1,"https:\u002F\u002Fgithub.com\u002Fphaedrus1992\u002Fllmenv","https:\u002F\u002Fgithub.com\u002Fphaedrus1992","2026-11-15 01:43:22",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add phaedrus1992\u002Fllmenv --skill daily-update",{"tool":40,"command":41},"bunx","bunx skills add phaedrus1992\u002Fllmenv --skill daily-update",{"tool":43,"command":44},"pnpm","pnpm dlx skills add phaedrus1992\u002Fllmenv --skill daily-update","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fphaedrus1992\u002Fllmenv\u002Fblob\u002Fmain\u002Fexamples\u002Fconfig-llmenv-dir\u002Fbundles\u002Fwork\u002Fskills\u002Fdaily-update\u002FSKILL.md",true,[48,53],{"path":26,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"SCRIPT","脚本",1300,"https:\u002F\u002Fgithub.com\u002Fphaedrus1992\u002Fllmenv\u002Fblob\u002Fmain\u002Fexamples\u002Fconfig-llmenv-dir\u002Fbundles\u002Fwork\u002Fskills\u002Fdaily-update\u002Fscripts\u002Fgh-activity.sh",{"path":25,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":54,"sourceHtmlUrl":55},5351,"https:\u002F\u002Fgithub.com\u002Fphaedrus1992\u002Fllmenv\u002Fblob\u002Fmain\u002Fexamples\u002Fconfig-llmenv-dir\u002Fbundles\u002Fwork\u002Fskills\u002Fdaily-update\u002Fscripts\u002Fscan-sessions.mjs",[57,64,71,78,85,92],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"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":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":19},"01M74WW0P1A8YWDVYM864T6J5X","hello","Hello world skill","https:\u002F\u002Fgithub.com\u002Fphaedrus1992\u002Fllmenv\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fbundles\u002Fbase\u002Fskills\u002Fhello\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"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":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"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":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"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":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":19},"01M74WVK2TFMW4MSQAKM4EZ8GR","build-check","Run cargo build + clippy + test before claiming done in the llmenv repo.","https:\u002F\u002Fgithub.com\u002Fphaedrus1992\u002Fllmenv\u002Fblob\u002Fmain\u002Fexamples\u002Fconfig-llmenv-dir\u002Fbundles\u002Frust-dev\u002Fskills\u002Fbuild-check\u002FSKILL.md",[],[]]