agentleFS
Sign inStart free
envisioningenvisioning/skills/skills/scope/SKILL.md

scope

Skill2 starsChanged 51 days agoMITView on GitHub

Turn a vague foresight request into a briefing — the decision it serves, the boundary, the horizon, the audience, what's out, and which playbook fits — by asking a few questions and writing the answers down before any scanning starts. Use when the user says "we want to look at the future of X", "scope this", "set up a scan", "what should we research", or when any scan skill is invoked without a clear boundary. Stage: sense (before it).

42 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use develop, visual and 9 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.
  • hong9LeeSkill

    develop

    빌드, 아키텍처, git 관련 작업 시 OMS MSA 공통 인프라 규칙을 적용한다. 기술 스택, 빌드 명령, 헥사고날 아키텍처 구조, git 워크플로우, AI Context 동기화 규칙을 다룬다. 코드 작성 컨벤션은 /convention, 테스트 컨벤션은 /test-guide 스킬을 참조.

    Also in 6 projects that use this

  • minhtran3124Skill

    visual

    Skill graph visualizer — scans all SKILL.md files in skills/, builds a directed relationship graph from explicit `relationships` frontmatter (falling back to content inference), and generates both a Mermaid markdown summary and an interactive HTML graph at .docs/skill-graph.html. Trigger: /visual

    Also in 3 projects that use this

  • MicrosoftSkill

    sync

    Sync the current session branch with its upstream branch, or publish the current session branch to a remote. Use when the user asks to sync a branch, pull latest changes, rebase onto upstream, push current branch, publish branch, or set upstream.

    Also in 7 projects that use this

  • nicolasestremSkill

    document

    Create focused documentation for specific components or features

    Also in 5 projects that use this

  • Skeln-ioSkill

    copy

    Direct response copywriting using proven frameworks. Brand-aware — reads ICP, voice, and tone from your brand config. Covers product descriptions, SEO meta, email, social, press angles.

    Also in 3 projects that use this

  • kt057Skill

    check

    lint, typecheck, test を一括実行して結果をサマリーする

    Also in 5 projects that use this

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 3 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 39 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read first: ../../core/envisioning.md, ../../core/playbooks/ (the seven boundaries), ../../core/voice.md.

    line 12
  2. Distinctive:

    Ask, in order, one at a time.

    line 17
  3. Very specific:

    If there is no decision, it is curiosity — fine, say so and set decision: none, but the scan will be broad and the report short.

    line 21
  4. Distinctive:

    Every scan skill reads this file first when it exists for the boundary.

    line 78
  5. Very specific:

    Don't write a briefing the user hasn't answered.

    line 82
  6. Distinctive:

    Don't start the scan from here.

    line 84

“Common” is measured: kept by at least 6 in 10 of the 39 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

scope

Most foresight work fails at the start: the question is a topic, not a decision, and the boundary is "everything". This skill produces the briefing every downstream skill reads.

Read first: ../../core/envisioning.md, ../../core/playbooks/ (the seven boundaries), ../../core/voice.md.

Procedure

Ask, in order, one at a time. Skip anything the user already stated. Offer a default in each question so a one-word answer works.

  1. Decision. What will someone decide differently because of this? If there is no decision, it is curiosity — fine, say so and set decision: none, but the scan will be broad and the report short.
  2. Boundary. Where does it stop? Named industry / geography / function / competitor set / home position / exposure surface / jurisdiction. Push once if the answer is a topic ("AI") rather than a boundary ("AI in claims handling, EU insurers").
  3. Horizon. When does it need to be true to matter? 1 · 3 · 10 years. Default 3.
  4. Audience. Who reads the result, and in what meeting? This sets the report type.
  5. Out of scope. What are we explicitly not looking at? Two items minimum; "nothing" is an answer that predicts a panorama.
  6. Prior work. Ground: search for existing cards, scans, reports on this boundary. Show what exists; the briefing links it.

Then pick the playbook from the boundary shape:

the boundary is a…playbook
topic / domain, macrohorizon-scan
field / sector, capabilitiestechnology-scan
industry / function, practicesinnovation-radar
named competitor setcompetitive-scan
home positionadjacency-scan
jurisdiction + topicregulatory-scan
exposure surfacerisk-radar

Two playbooks may fit; say which runs first and why. Downstream skills after the scan (frames, scenarios, grill-the-future, report) are listed as the plan.

Output

---
kind: briefing
title: <boundary> · <horizon>y
decision:
boundary:
horizon: <1|3|10>
audience:
report_type:
out_of_scope: []
playbook: <slug>
plan: [<skills in order>]
prior: [<cards, scans, reports found>]
subject: <core:kind:id, if for a client>
---
## Decision
## Boundary
## Out of scope
## Plan

Persist to /foresight/briefings/<slug> with category: brief, or ./foresight/briefings/. message: scope · new briefing.

Every scan skill reads this file first when it exists for the boundary.

Refusals

  • Don't write a briefing the user hasn't answered; a guessed briefing is worse than none because downstream skills trust it.
  • Don't start the scan from here. End with the briefing and the first command to run.

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.

Check your setup, free