agentleFS
the-abraham-brandthe-abraham-brand/my-business-brain/skills/ask/SKILL.md

ask

Skill0 starsChanged 51 days agoMITView on GitHub

My Business Brain answer. Answers a question about the user's own business from the brain, answer first, citing the entries used, flagging stale or disputed entries and conflicts, and saying plainly when the brain does not know. Uses ranked hybrid search over entries and source documents, and checks every cited figure, date and quote against its entry before answering. Use when the user runs /my-business-brain:ask, or asks what the business charges, agreed, decided, uses, owes, or how a policy or procedure works.

83 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use daily-arxiv, exp-eval and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • LambenthanSkill

    daily-arxiv

    每日从 arXiv 拉取新论文,过滤相关性,auto-ingest 高优先级论文,检测 SOTA 更新

    Also in 5 projects that use this

  • LambenthanSkill

    exp-eval

    实验判决门:Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges

    Also in 5 projects that use this

  • skyllwtSkill

    exp-pilot-eval

    Pilot result evaluation — read pilot results, apply success criteria, update idea page (pilot_result, failure_reason if failed), generate PILOT_VERDICT_REPORT. Called by /ideate Phase 5 after /exp-pilot-run.

    Also in 4 projects that use this

  • skyllwtSkill

    exp-pilot-run

    Pilot experiment execution — read Pilot Spec YAML, write pilot code, run experiment(Confirm with the user before operation and require the applicant to conduct manual inspection), return results. Called by /ideate Phase 5. Does NOT modify wiki pages or judge pass/fail.

    Also in 4 projects that use this

  • phanghonghaoSkill

    poster

    HTML/CSS A4 海报生成。从沙龙/活动 Markdown 文件生成科技风 A4 海报 PDF/PNG。Use when user mentions: poster, 海报, 海报生成, make poster, generate poster, 活动海报, 沙龙海报.

    Also in 4 projects that use this

  • +6 more from Lambenthan
  • +1 more from skyllwt

The file

Files
SKILL.md

/my-business-brain:ask

Answer from what the business knows, with the receipts.

  1. Load the my-business-brain skill from this plugin (via the Skill tool). If it cannot be loaded, read ../my-business-brain/SKILL.md directly. Follow Answering a question.
  2. Search with scripts/brain_search.py (from the core skill folder) using 2–4 phrasings of the question, including the business's own terms (on a large brain, --brief first, then scripts/brain_get.py for the entries that matter); add --include-archive for history questions such as "what did we charge last year?". Read the top results and keep the ones that truly answer it. Apply relevant lessons and preferences.
  3. Draft answer first, with a citation after every factual sentence ([[entry-id]] or [[sources/file.md#Lx-Ly]]) and [calc] on calculated figures, then run scripts/cite_check.py on the draft (with --audience external if the answer will be sent outside the business) and fix every failure. When the answer is sent or acted on, add --log "<the question>" --kind answer (or email, proposal, quote, report) and --recipient so later changes to those facts raise an impact alert.
  4. Present the verified answer: the answer in one or two sentences, the supporting detail, then the sources as entry titles and file names with their dates. Flag anything past its review date, disputed, low confidence or historical. If two entries conflict, show both and ask which is current.
  5. If the brain does not know, say so. Give a general-knowledge answer only if clearly labelled, and offer to store the confirmed answer. If the question depends on official rules, vet them first. When it needs outside information, use the research tools the toolkit lists (scripts/toolkit.py <brain> show) and install nothing; if a missing helper would have made it easier, say so in one line. Anything found on social or community sources is a lead or sentiment (scripts/signals.py), reported as "not confirmed" and never cited as support.
  6. Log the question in _system/questions.md; if it has come up before unanswered, suggest documenting it.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.