Missed Digest Items
- Repo stars 640
- License MIT
- Author updated Live
- Author repo honeclaw
- Domain
- Other
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 94 / 100 · audit passed
- Author / version / license
- @B-M-Capital-Research · MIT
- Token usage
- Lean
- Setup complexity
- Plug-and-play
- External API key
- Not required
- Operating systems
- Unspecified (assume cross-platform)
- Runtime requirements
- No special requirements
- Permissions
-
- Read-only
- Write / modify
- Network behavior
- Local-only
- Install commands
- 26 variants
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools，默认拥有全部工具权限。
---
name: Missed Digest Items
description: 当用户敲 /missed 或自然语言问「digest 没推什么」时,调 missed_events 工具捞回 event-engine 的 delivery_log,把被主动筛掉的事件用人话报…
category: other
runtime: no special runtime
---
# Missed Digest Items output preview
## PART A: Task fit
- Use case: 当用户敲 /missed 或自然语言问「digest 没推什么」时,调 missed_events 工具捞回 event-engine 的 delivery_log,把被主动筛掉的事件用人话报给用户。 用户提到「最近一周」「7 天」之类时把 since_hours 调到 168: missedevents({"sincehours": 168}) 用户嫌列表太长,可以缩 limit(默认 30): runs entirely locally. Works with Claude Code, Cursor, Cline and 23 more..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “职责 / 工具调用模板 / 输出格式约定(回给用户)” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “当用户敲 /missed 或自然语言问「digest 没推什么」时,调 missed_events 工具捞回 event-engine 的 delivery_log,把被主动筛掉的事件用人话报给用户。 用户提到「最近一周」「7 天」之类时把 since_hours 调到 168: missedevents({"sincehours": 168}) 用户嫌列表太长,可以缩 limit(默认 30): runs entirely locally. Works with Claude Code, Cursor, Cline and 23 more.”.
- **02** When the source has headings, the agent prioritizes “职责 / 工具调用模板 / 输出格式约定(回给用户)” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files; mostly runs locally; usually needs no extra API key.
## Running Rules
- read files, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options.The source mentions slash commands such as `/missed`; use them first when your agent supports command triggers.
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, write/modify files.
Start with a small task and check whether the result follows “职责 / 工具调用模板 / 输出格式约定(回给用户)”. Inspect diffs, logs, previews, or tests before expanding scope.
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: Missed Digest Items
description: 当用户敲 /missed 或自然语言问「digest 没推什么」时,调 missed_events 工具捞回 event-engine 的 delivery_log,把被主动筛掉的事件用人话报…
category: other
source: B-M-Capital-Research/honeclaw
---
# Missed Digest Items
## When to use
- 当用户敲 /missed 或自然语言问「digest 没推什么」时,调 missed_events 工具捞回 event-engine 的 delivery_log,把被主动筛掉的事件用人话报给用户。 用户提到「最近一周」「7 天」之类…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “职责 / 工具调用模板 / 输出格式约定(回给用户)” and keep inference separate from source facts.
- read files, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies.The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "Missed Digest Items" {
input -> user goal + target files + boundaries + acceptance criteria
context -> 职责 / 工具调用模板 / 输出格式约定(回给用户)
rules -> SKILL.md triggers / order / output contract
runtime -> no special runtime | read files, write/modify files | mostly runs locally
guardrails -> usually needs no extra API key + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
}职责
当用户敲 /missed 或自然语言问「digest 没推什么」时,调 missed_events 工具捞回
event-engine 的 delivery_log,把被主动筛掉的事件用人话报给用户。
工具调用模板
默认看过去 24 小时:
missed_events()用户提到「最近一周」「7 天」之类时把 since_hours 调到 168:
missed_events({"since_hours": 168})用户嫌列表太长,可以缩 limit(默认 30):
missed_events({"since_hours": 24, "limit": 10})输出格式约定(回给用户)
按下面这个 schema 渲染,不要把工具的原始 JSON 直接贴出来:
🗂 过去 N 小时被筛掉的事件 · 共 X 条
【数量上限截断】(capped / price_capped)
• $AMD [新闻] · AMD's earnings preview 标题
来源:fmp.stock_news:foo · 时间:HH:MM
【同 ticker 冷却】(cooled_down / price_cooled_down)
• ...
【噪音过滤】(omitted)
• ...
【你的偏好过滤】(filtered)
• ...按 status 分组,每组只在确实有条目时才列出标题。每条 1-2 行(标题 +
来源 + 时间)。Symbol 用 $AAPL 形式开头让用户一眼看到关注的标的。
URL 有就用 <a> 链接(渠道支持时);否则不强加。
注意
- 用户问「为什么 X 没推」: 工具结果里
status+reason字段已经回答了, 原文报给用户。如果工具没返回 X,大概率 X 根本没进 router(没匹配到持仓, 或被全局 disabled_kinds 砍),这种情况告诉用户「没在最近 N 小时的 digest 策略里被处理过,可能根本没进 event 引擎」。 - 工具只查当前用户自己的;构造期已硬绑定 actor,用户不能用此命令查 别人。
- 工具默认 24 小时;不要无理由扩到 168(全 7 天数据量大,渲染长)。
Decide Fit First
Design Intent
How To Use It
Boundaries And Review