[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M737C76NRC1KCJJS57TGTPZV":3,"skill-same:01M737C76NRC1KCJJS57TGTPZV":59},{"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":37,"commitSha":38,"skillDirectory":39,"forksCount":40,"repositoryHtmlUrl":41,"repositoryHomepageUrl":6,"ownerHtmlUrl":42,"ownerBlogUrl":43,"ownerDescription":6,"updatedAt":44,"install":45,"resources":58},"01M737C76NRC1KCJJS57TGTPZV","choose-loop-wakeup-interval",null,"Select a `delaySeconds` value when scheduling a loop wakeup via the `ScheduleWakeup` tool or the `\u002Floop` slash command. Covers the three-tier cache-aware decision (cache-warm under 5 minutes, cache-miss 5 minutes to 1 hour, idle default 20 to 30 minutes), the 300-second anti-pattern, the [60, 3600] runtime clamp, the minute-boundary rounding quirk, and writing a telemetry-worthy `reason` field. Use when designing an autonomous loop, when a heartbeat cadence is being planned, when polling cadence is being tuned, or when post-hoc review of loop costs reveals interval mis-sizing.","roohe\u002Fagentic-super-skills","roohe","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F99054084?v=4","01M734WCDFP6RZVT5CNM00QR26","01M734WCE4BD0T4NZS5PCV9V5F",10,"MIT","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fchoose-loop-wakeup-interval\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: choose-loop-wakeup-interval\nlocale: caveman-lite\nsource_locale: en\nsource_commit: 82c77053\ntranslator: \"Julius Brussee homage — caveman\"\ntranslation_date: \"2026-04-19\"\ndescription: >\n  Select a `delaySeconds` value when scheduling a loop wakeup via the\n  `ScheduleWakeup` tool or the `\u002Floop` slash command. Covers the three-tier\n  cache-aware decision (cache-warm under 5 minutes, cache-miss 5 minutes to\n  1 hour, idle default 20 to 30 minutes), the 300-second anti-pattern, the\n  [60, 3600] runtime clamp, the minute-boundary rounding quirk, and writing\n  a telemetry-worthy `reason` field. Use when designing an autonomous loop,\n  when a heartbeat cadence is being planned, when polling cadence is being\n  tuned, or when post-hoc review of loop costs reveals interval mis-sizing.\nlicense: MIT\nallowed-tools: \"\"\nmetadata:\n  author: Philipp Thoss\n  version: \"1.0\"\n  domain: general\n  complexity: intermediate\n  language: multi\n  tags: loop, wakeup, cache, scheduling, delay, general\n---\n\n# Choose Loop Wakeup Interval\n\nPick a `delaySeconds` value for `ScheduleWakeup` that respects the prompt cache's 5-minute TTL, the scheduler's whole-minute granularity, and the `[60, 3600]` runtime clamp. The decision is structurally non-trivial: the common instinct \"wait about 5 minutes\" lands in the worst-of-both zone — pay the cache miss without amortizing the wait.\n\nThe reasoning travels with the `ScheduleWakeup` tool description at tool-call time, but by then the loop is already being scheduled. This skill hoists that reasoning to planning time, where it belongs.\n\n## When to Use\n\n- Designing an autonomous `\u002Floop` or `ScheduleWakeup`-driven continuation and picking the per-tick delay\n- Planning a heartbeat cadence for a long-running agent that will poll, watch, or iterate\n- Tuning polling cadence against cost or cache-warmth pressure\n- Post-hoc reviewing loop costs and discovering the interval was mis-sized\n- Writing a guide, runbook, or worked example that involves picking `delaySeconds`\n\n## Inputs\n\n- **Required**: What the loop is waiting for (a specific event, a state transition, an idle tick, a periodic check)\n- **Required**: Whether the reader of this tick will need fresh context (cache-warm) or can tolerate a cold re-read (cache-miss acceptable)\n- **Optional**: Any known lower bound on when the awaited event could possibly occur (e.g. \"the build takes at least 4 minutes\")\n- **Optional**: A cost ceiling on the total loop (number of ticks × per-tick cost)\n\n## Procedure\n\n### Step 1: Classify the Wait\n\nDecide which tier the wait belongs to:\n\n- **Active watch (cache-warm)**: something is expected to change within the next 5 minutes — a build nearing completion, a state transition being polled, a process that was kicked off\n- **Cache-miss wait**: nothing worth checking sooner than 5 minutes from now; the context cache will go cold and that is acceptable\n- **Idle**: no specific signal to watch; the loop is checking in because it might find something, not because it will\n\n**Got:** A clear classification: active-watch, cache-miss, or idle.\n\n**If fail:** If the wait cannot be classified — if there is no honest answer to \"what am I waiting for?\" — the loop probably should not exist. Skip to Step 5 and consider not scheduling a wakeup at all.\n\n### Step 2: Apply the Three-Tier Decision\n\nPick a `delaySeconds` based on the classification:\n\n| Tier | Range | Cache behaviour | Use when |\n|---|---|---|---|\n| Cache-warm | **60 – 270 s** | Cache stays warm (under 5-minute TTL) | Active watch — the next tick needs fast, cheap re-entry |\n| Cache-miss | **1200 – 3600 s** | Cache goes cold; one miss buys a long wait | Genuinely idle, or the awaited event cannot happen sooner |\n| Idle default | **1200 – 1800 s** (20–30 min) | Cache goes cold | No specific signal; periodic check with user able to interrupt |\n\n**Do not pick 300 s.** It is the worst-of-both interval: the cache misses, but the wait is too short to amortize the miss. If you find yourself reaching for \"about 5 minutes,\" drop to 270 s (stay warm) or commit to 1200 s+ (amortize the miss).\n\n**Got:** A specific `delaySeconds` value chosen from one of the three tiers, not a round-number-minute value picked out of habit.\n\n**If fail:** If the choice keeps landing on 300 s, the underlying question is usually \"should this loop exist at this cadence at all?\" — re-examine Step 1.\n\n### Step 3: Size for the Minute Boundary\n\nThe scheduler fires on whole-minute boundaries. A `delaySeconds` of `N` produces an actual delay of `N` to `N + 60` s, depending on what second of the minute you call the tool.\n\nWorked example:\n\n> Calling `ScheduleWakeup({delaySeconds: 90})` at `HH:MM:40` produces a target of `HH:(MM+2):00` — i.e. an actual wait of 140 s, not 90 s.\n\nConsequence: sub-minute intent is meaningless. Treat the value you pass as a **floor**, not a precise schedule. If a minute of skew matters, your loop cadence is too tight for this mechanism.\n\n**Got:** You have accepted that the actual wait will be up to 60 s longer than the requested `delaySeconds`. For cache-warm ticks this matters — 270 s can become ~330 s in practice, tipping into cache-miss territory.\n\n**If fail:** If near-the-ceiling values (e.g. 265 s when targeting cache-warmth) are common, pad downward — use 240 s instead of 270 s to preserve the cache-warm guarantee even under worst-case minute-boundary skew.\n\n### Step 4: Respect the Clamp\n\nThe runtime clamps `delaySeconds` to `[60, 3600]` — values outside that range are silently adjusted. Telemetry distinguishes what the model asked for (`chosen_delay_seconds`) from what actually scheduled (`clamped_delay_seconds`) and sets `was_clamped: true` on any mismatch.\n\nPlan against the clamped value, not the requested one:\n\n- Request below 60 → actual wait is 60 s plus minute-boundary skew (up to 120 s in practice)\n- Request above 3600 → actual wait is 3600 s (1 hour)\n- No runtime extends the ceiling; multi-hour waits require multiple ticks\n\n**Got:** Your chosen value falls inside `[60, 3600]`, or you have deliberately accepted the clamped behaviour.\n\n**If fail:** If the need is genuinely multi-hour (e.g. \"wake me in 4 hours\"), chain wakeups — schedule a 3600 s tick that itself reschedules — or use a cron-based loop (`CronCreate` with `kind: \"loop\"`) instead.\n\n### Step 5: Write a Specific `reason`\n\nThe `reason` field is telemetry, user-visible status, and prompt-cache warmth reasoning in one line. It is truncated to 200 chars. Make it specific.\n\n- Good: `checking long bun build`, `polling for EC2 instance running-state`, `idle heartbeat — watching the feed`\n- Bad: `waiting`, `loop`, `next tick`, `continuing`\n\nThe reader of this field is a user trying to understand what the loop is doing without having to predict your cadence in advance. Write for them.\n\n**Got:** A concrete, one-phrase reason that would make sense to a user glancing at status.\n\n**If fail:** If no specific reason can be given, revisit whether the loop should exist (Step 1 and Step 6).\n\n### Step 6: Recognize the Don't-Loop Case\n\nNot every \"come back later\" impulse warrants a scheduled wakeup. Do NOT schedule a tick when:\n\n- The user is actively watching — their input is the right trigger, not a timer\n- There is no convergence criterion — the loop has no definition of \"done\"\n- The task is interactive (asks the user questions between ticks)\n- The cadence needed is shorter than the clamp floor (60 s) — polling that tight belongs to an event-driven mechanism, not a loop\n\n**Got:** A conscious choice between scheduling a wakeup and not looping at all. \"Because I could\" is not a reason to loop.\n\n**If fail:** If you keep scheduling wakeups that the user interrupts before they fire, the pattern is wrong — not the interval.\n\n## Validation\n\n- [ ] The wait was classified as active-watch, cache-miss, or idle (one of three)\n- [ ] The chosen `delaySeconds` falls in one of the three tier ranges (60–270, 1200–3600, or 1200–1800 for idle)\n- [ ] The value is not 300 (worst-of-both)\n- [ ] The value is inside `[60, 3600]` or the clamped behaviour is explicitly accepted\n- [ ] Minute-boundary skew has been accounted for (treat the value as a floor)\n- [ ] `reason` is concrete and under 200 chars\n- [ ] The don't-loop check was performed — the wakeup is warranted\n\n## Pitfalls\n\n- **Round-minute default (300 s)**: The single most common mistake. \"About 5 minutes\" feels natural and is exactly wrong. Drop to 270 s or commit to 1200 s+.\n- **Ignoring minute-boundary skew**: Requesting 60 s near the end of a minute can produce ~120 s of actual delay. For cache-warm ticks, this can push the tick past the 5-minute TTL unexpectedly.\n- **Chasing sub-minute precision**: The scheduler has minute granularity. Asking for 85 s vs. 90 s vs. 95 s is noise — pick a value and move on.\n- **Opaque `reason` fields**: `\"waiting\"` tells the user nothing and makes telemetry less useful. Write the reason as if the user will read it on a status line.\n- **Using this skill to justify an unnecessary loop**: If the honest answer to \"what am I watching for?\" is vague, no interval choice will help — the loop should not exist.\n- **Hand-clamping in the prompt**: Do not clamp in the model's reasoning (\"I'll cap at 3600 to be safe\"). The runtime clamps. Let it.\n- **Forgetting the 7-day age-out**: A dynamic loop is reaped after 7 days by default (user-configurable up to 30 days). Long-running loops should be designed to end well before that ceiling, not to race against it.\n\n## Examples\n\n### Example 1 — Cache-warm active watch\n\nA `bun build` was kicked off; the agent wants to check in quickly so the cache is still warm when results arrive.\n\n- Classification: active watch (Step 1)\n- Tier: cache-warm (Step 2), pick **240 s**\n- Minute boundary (Step 3): worst-case actual wait ~300 s — still under the 5-minute TTL with the 60 s buffer\n- Reason (Step 5): `checking long bun build`\n\n### Example 2 — Idle heartbeat\n\nAn autonomous agent watches a low-volume feed once an hour for anything worth acting on.\n\n- Classification: idle (Step 1)\n- Tier: idle default (Step 2), pick **1800 s** (30 min)\n- Minute boundary (Step 3): irrelevant — 60 s of skew is negligible at this cadence\n- Reason (Step 5): `idle heartbeat — watching the feed`\n\n### Example 3 — The anti-pattern\n\nAn agent wants to \"wait 5 minutes\" while a remote API retries. The request is 300 s.\n\n- Problem: the cache goes cold at 5 minutes, so 300 s pays the miss — but 300 s is too short to amortize the miss\n- Fix: either drop to 270 s (stay warm) or commit to 1500 s (amortize the miss). Do not pick 300.\n\n## Related Skills\n\n- `manage-token-budget` — cost ceilings for long-lived agent loops; cache-aware sizing is one lever\n- `du-dum` — observe\u002Fact separation pattern; this skill sizes the observe-clock interval when the loop is cron-less\n- `read-continue-here` — cross-session handoff; this skill covers within-session wakeups\n- `write-continue-here` — the complement of `read-continue-here`\n\n\u003C!-- Keep under 500 lines. Current: ~200 lines. -->\n","# Choose Loop Wakeup Interval\n\nPick a `delaySeconds` value for `ScheduleWakeup` that respects the prompt cache's 5-minute TTL, the scheduler's whole-minute granularity, and the `[60, 3600]` runtime clamp. The decision is structurally non-trivial: the common instinct \"wait about 5 minutes\" lands in the worst-of-both zone — pay the cache miss without amortizing the wait.\n\nThe reasoning travels with the `ScheduleWakeup` tool description at tool-call time, but by then the loop is already being scheduled. This skill hoists that reasoning to planning time, where it belongs.\n\n## When to Use\n\n- Designing an autonomous `\u002Floop` or `ScheduleWakeup`-driven continuation and picking the per-tick delay\n- Planning a heartbeat cadence for a long-running agent that will poll, watch, or iterate\n- Tuning polling cadence against cost or cache-warmth pressure\n- Post-hoc reviewing loop costs and discovering the interval was mis-sized\n- Writing a guide, runbook, or worked example that involves picking `delaySeconds`\n\n## Inputs\n\n- **Required**: What the loop is waiting for (a specific event, a state transition, an idle tick, a periodic check)\n- **Required**: Whether the reader of this tick will need fresh context (cache-warm) or can tolerate a cold re-read (cache-miss acceptable)\n- **Optional**: Any known lower bound on when the awaited event could possibly occur (e.g. \"the build takes at least 4 minutes\")\n- **Optional**: A cost ceiling on the total loop (number of ticks × per-tick cost)\n\n## Procedure\n\n### Step 1: Classify the Wait\n\nDecide which tier the wait belongs to:\n\n- **Active watch (cache-warm)**: something is expected to change within the next 5 minutes — a build nearing completion, a state transition being polled, a process that was kicked off\n- **Cache-miss wait**: nothing worth checking sooner than 5 minutes from now; the context cache will go cold and that is acceptable\n- **Idle**: no specific signal to watch; the loop is checking in because it might find something, not because it will\n\n**Got:** A clear classification: active-watch, cache-miss, or idle.\n\n**If fail:** If the wait cannot be classified — if there is no honest answer to \"what am I waiting for?\" — the loop probably should not exist. Skip to Step 5 and consider not scheduling a wakeup at all.\n\n### Step 2: Apply the Three-Tier Decision\n\nPick a `delaySeconds` based on the classification:\n\n| Tier | Range | Cache behaviour | Use when |\n|---|---|---|---|\n| Cache-warm | **60 – 270 s** | Cache stays warm (under 5-minute TTL) | Active watch — the next tick needs fast, cheap re-entry |\n| Cache-miss | **1200 – 3600 s** | Cache goes cold; one miss buys a long wait | Genuinely idle, or the awaited event cannot happen sooner |\n| Idle default | **1200 – 1800 s** (20–30 min) | Cache goes cold | No specific signal; periodic check with user able to interrupt |\n\n**Do not pick 300 s.** It is the worst-of-both interval: the cache misses, but the wait is too short to amortize the miss. If you find yourself reaching for \"about 5 minutes,\" drop to 270 s (stay warm) or commit to 1200 s+ (amortize the miss).\n\n**Got:** A specific `delaySeconds` value chosen from one of the three tiers, not a round-number-minute value picked out of habit.\n\n**If fail:** If the choice keeps landing on 300 s, the underlying question is usually \"should this loop exist at this cadence at all?\" — re-examine Step 1.\n\n### Step 3: Size for the Minute Boundary\n\nThe scheduler fires on whole-minute boundaries. A `delaySeconds` of `N` produces an actual delay of `N` to `N + 60` s, depending on what second of the minute you call the tool.\n\nWorked example:\n\n> Calling `ScheduleWakeup({delaySeconds: 90})` at `HH:MM:40` produces a target of `HH:(MM+2):00` — i.e. an actual wait of 140 s, not 90 s.\n\nConsequence: sub-minute intent is meaningless. Treat the value you pass as a **floor**, not a precise schedule. If a minute of skew matters, your loop cadence is too tight for this mechanism.\n\n**Got:** You have accepted that the actual wait will be up to 60 s longer than the requested `delaySeconds`. For cache-warm ticks this matters — 270 s can become ~330 s in practice, tipping into cache-miss territory.\n\n**If fail:** If near-the-ceiling values (e.g. 265 s when targeting cache-warmth) are common, pad downward — use 240 s instead of 270 s to preserve the cache-warm guarantee even under worst-case minute-boundary skew.\n\n### Step 4: Respect the Clamp\n\nThe runtime clamps `delaySeconds` to `[60, 3600]` — values outside that range are silently adjusted. Telemetry distinguishes what the model asked for (`chosen_delay_seconds`) from what actually scheduled (`clamped_delay_seconds`) and sets `was_clamped: true` on any mismatch.\n\nPlan against the clamped value, not the requested one:\n\n- Request below 60 → actual wait is 60 s plus minute-boundary skew (up to 120 s in practice)\n- Request above 3600 → actual wait is 3600 s (1 hour)\n- No runtime extends the ceiling; multi-hour waits require multiple ticks\n\n**Got:** Your chosen value falls inside `[60, 3600]`, or you have deliberately accepted the clamped behaviour.\n\n**If fail:** If the need is genuinely multi-hour (e.g. \"wake me in 4 hours\"), chain wakeups — schedule a 3600 s tick that itself reschedules — or use a cron-based loop (`CronCreate` with `kind: \"loop\"`) instead.\n\n### Step 5: Write a Specific `reason`\n\nThe `reason` field is telemetry, user-visible status, and prompt-cache warmth reasoning in one line. It is truncated to 200 chars. Make it specific.\n\n- Good: `checking long bun build`, `polling for EC2 instance running-state`, `idle heartbeat — watching the feed`\n- Bad: `waiting`, `loop`, `next tick`, `continuing`\n\nThe reader of this field is a user trying to understand what the loop is doing without having to predict your cadence in advance. Write for them.\n\n**Got:** A concrete, one-phrase reason that would make sense to a user glancing at status.\n\n**If fail:** If no specific reason can be given, revisit whether the loop should exist (Step 1 and Step 6).\n\n### Step 6: Recognize the Don't-Loop Case\n\nNot every \"come back later\" impulse warrants a scheduled wakeup. Do NOT schedule a tick when:\n\n- The user is actively watching — their input is the right trigger, not a timer\n- There is no convergence criterion — the loop has no definition of \"done\"\n- The task is interactive (asks the user questions between ticks)\n- The cadence needed is shorter than the clamp floor (60 s) — polling that tight belongs to an event-driven mechanism, not a loop\n\n**Got:** A conscious choice between scheduling a wakeup and not looping at all. \"Because I could\" is not a reason to loop.\n\n**If fail:** If you keep scheduling wakeups that the user interrupts before they fire, the pattern is wrong — not the interval.\n\n## Validation\n\n- [ ] The wait was classified as active-watch, cache-miss, or idle (one of three)\n- [ ] The chosen `delaySeconds` falls in one of the three tier ranges (60–270, 1200–3600, or 1200–1800 for idle)\n- [ ] The value is not 300 (worst-of-both)\n- [ ] The value is inside `[60, 3600]` or the clamped behaviour is explicitly accepted\n- [ ] Minute-boundary skew has been accounted for (treat the value as a floor)\n- [ ] `reason` is concrete and under 200 chars\n- [ ] The don't-loop check was performed — the wakeup is warranted\n\n## Pitfalls\n\n- **Round-minute default (300 s)**: The single most common mistake. \"About 5 minutes\" feels natural and is exactly wrong. Drop to 270 s or commit to 1200 s+.\n- **Ignoring minute-boundary skew**: Requesting 60 s near the end of a minute can produce ~120 s of actual delay. For cache-warm ticks, this can push the tick past the 5-minute TTL unexpectedly.\n- **Chasing sub-minute precision**: The scheduler has minute granularity. Asking for 85 s vs. 90 s vs. 95 s is noise — pick a value and move on.\n- **Opaque `reason` fields**: `\"waiting\"` tells the user nothing and makes telemetry less useful. Write the reason as if the user will read it on a status line.\n- **Using this skill to justify an unnecessary loop**: If the honest answer to \"what am I watching for?\" is vague, no interval choice will help — the loop should not exist.\n- **Hand-clamping in the prompt**: Do not clamp in the model's reasoning (\"I'll cap at 3600 to be safe\"). The runtime clamps. Let it.\n- **Forgetting the 7-day age-out**: A dynamic loop is reaped after 7 days by default (user-configurable up to 30 days). Long-running loops should be designed to end well before that ceiling, not to race against it.\n\n## Examples\n\n### Example 1 — Cache-warm active watch\n\nA `bun build` was kicked off; the agent wants to check in quickly so the cache is still warm when results arrive.\n\n- Classification: active watch (Step 1)\n- Tier: cache-warm (Step 2), pick **240 s**\n- Minute boundary (Step 3): worst-case actual wait ~300 s — still under the 5-minute TTL with the 60 s buffer\n- Reason (Step 5): `checking long bun build`\n\n### Example 2 — Idle heartbeat\n\nAn autonomous agent watches a low-volume feed once an hour for anything worth acting on.\n\n- Classification: idle (Step 1)\n- Tier: idle default (Step 2), pick **1800 s** (30 min)\n- Minute boundary (Step 3): irrelevant — 60 s of skew is negligible at this cadence\n- Reason (Step 5): `idle heartbeat — watching the feed`\n\n### Example 3 — The anti-pattern\n\nAn agent wants to \"wait 5 minutes\" while a remote API retries. The request is 300 s.\n\n- Problem: the cache goes cold at 5 minutes, so 300 s pays the miss — but 300 s is too short to amortize the miss\n- Fix: either drop to 270 s (stay warm) or commit to 1500 s (amortize the miss). Do not pick 300.\n\n## Related Skills\n\n- `manage-token-budget` — cost ceilings for long-lived agent loops; cache-aware sizing is one lever\n- `du-dum` — observe\u002Fact separation pattern; this skill sizes the observe-clock interval when the loop is cron-less\n- `read-continue-here` — cross-session handoff; this skill covers within-session wakeups\n- `write-continue-here` — the complement of `read-continue-here`\n\n\u003C!-- Keep under 500 lines. Current: ~200 lines. -->\n",{"name":5,"locale":23,"license":14,"metadata":24,"translator":31,"description":32,"allowed-tools":33,"source_commit":34,"source_locale":35,"translation_date":36},"caveman-lite",{"tags":25,"author":26,"domain":27,"version":28,"language":29,"complexity":30},"loop, wakeup, cache, scheduling, delay, general","Philipp Thoss","general","1.0","multi","intermediate","Julius Brussee homage — caveman","Select a `delaySeconds` value when scheduling a loop wakeup via the `ScheduleWakeup` tool or the `\u002Floop` slash command. Covers the three-tier cache-aware decision (cache-warm under 5 minutes, cache-miss 5 minutes to 1 hour, idle default 20 to 30 minutes), the 300-second anti-pattern, the [60, 3600] runtime clamp, the minute-boundary rounding quirk, and writing a telemetry-worthy `reason` field. Use when designing an autonomous loop, when a heartbeat cadence is being planned, when polling cadence is being tuned, or when post-hoc review of loop costs reveals interval mis-sizing.\n","","82c77053","en","2026-04-19","master","f483e54f3ad5f202a77d45f2e57f8d970b71195f","skills_library\u002Fchoose-loop-wakeup-interval",2,"https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills","https:\u002F\u002Fgithub.com\u002Froohe","yoou.link","2026-05-19 15:56:07",{"source":8,"skillName":5,"commands":46,"prompt":56,"zipAvailable":57},[47,50,53],{"tool":48,"command":49},"npx","npx skills add roohe\u002Fagentic-super-skills --skill choose-loop-wakeup-interval",{"tool":51,"command":52},"bunx","bunx skills add roohe\u002Fagentic-super-skills --skill choose-loop-wakeup-interval",{"tool":54,"command":55},"pnpm","pnpm dlx skills add roohe\u002Fagentic-super-skills --skill choose-loop-wakeup-interval","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fchoose-loop-wakeup-interval\u002FSKILL.md",true,[],[60,67,74,81,88,95],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":18},"01M73D865CZME2FCMKA4PQM348","zarr-python","Chunked N-D arrays for cloud storage. Compressed arrays, parallel I\u002FO, S3\u002FGCS integration, NumPy\u002FDask\u002FXarray compatible, for large-scale scientific computing pipelines.","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fzarr-python\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":18},"01M73D7Z64J4ABWZJD7P44XBBF","youtube-downloader","Download and process YouTube content for research. Use when: downloading competitor videos for analysis; extracting audio for podcasts; getting transcripts for content repurposing; archiving webinars; research content curation","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fyoutube-downloader\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":18},"01M73D7K8778TGZV3GJFR3703D","yc-pitch-deck","Create a compelling startup pitch deck that follows the structure proven to raise billions from top investors. Master the YC and Sequoia formats that get founders funded. Use when: **Fundraising** to create investor pitch decks; **YC application** to structure your narrative; **Demo Day prep** to craft your 2-minute pitch; **Angel investors** to communicate your opportunity; **Partnership pitches** to structure compelling asks","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fyc-pitch-deck\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":18},"01M73D70KJSE0E8Z28YMNNRT04","x-twitter-scraper","Use when the user needs X (Twitter) data or confirmation-gated X actions through Xquik: tweet search, user lookup, follower extraction, media download, monitoring, webhooks, MCP, SDKs, posting, likes, DMs, and profile updates. Requires a Xquik API key. Never ask for X login material.","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fx-twitter-scraper\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":18},"01M73D6ED01GV077R7K4NZNFZJ","write-vignette","Create R package vignettes using R Markdown or Quarto. Covers vignette setup, YAML configuration, code chunk options, building and testing, and CRAN requirements for vignettes. Use when adding a Getting Started tutorial, documenting complex workflows spanning multiple functions, creating domain-specific guides, or when CRAN submission requires user-facing documentation beyond function help pages.","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fwrite-vignette\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":18},"01M73D69YJR0BK3NFHE0CYG3EF","write-validation-documentation","Write IQ\u002FOQ\u002FPQ validation documentation for computerized systems in regulated environments. Covers protocols, reports, test scripts, deviation handling, and approval workflows. Use when validating R or other software for regulated use, preparing for a regulatory audit, documenting qualification of computing environments, or creating and updating validation protocols and reports for new or re-qualified systems.","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fwrite-validation-documentation\u002FSKILL.md",[],[]]