agentleFS
Sign inStart free
vaaynevaayne/agent-kit/skills/scout/SKILL.md

scout

Skill54 starsChanged 27 days agoMITView on GitHub

Scout the territory before building — a map-vs-territory diagnostic plus eight lightweight techniques (blindspot pass, brainstorm prototypes, interview, references, decision-first plans, deviation notes, explainers, quizzes) for finding your unknowns before they get expensive, applied inline with no workflow ceremony. Use when the user starts unfamiliar work, says "scout this", "blindspot pass", "unknown unknowns", "我不熟这块", "帮我找盲区", can't articulate what they want, or a long-horizon task came back wrong and planning harder isn't helping.

47 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use expand, explain 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.
  • andrewclark88Skill

    expand

    Expand a project's scope by updating its foundation documents. Reads existing north-star.md (or north-star-<project>.md), architecture.md, and roadmap.md, understands the codebase state, then interviews the user about the expansion. Updates foundation docs and roadmap so design can consume them in the next phase. Use when adding a major capability, new subsystem, or architectural shift — not for small one-offs (use feature for those).

    Also in 3 projects that use this

  • sunnyclinches44Skill

    explain

    Explains code using real-world analogies and ASCII diagrams

    Also in 5 projects that use this

  • WordPressSkill

    blueprint

    Use when the deliverable is WordPress Playground Blueprint JSON or a Blueprint bundle, including creating, editing, reviewing, validating schema keys, choosing steps/resources, and debugging Blueprint files. For only running or sharing a Playground environment, use wp-playground.

    Also in 3 projects that use this

  • AWSSkill

    issue

    Implement a GitHub issue end-to-end — branch, code, test, docs, and commit.

    Also in 3 projects that use this

  • bradtraversySkill

    feature

    Manage current feature workflow - start, review, explain or complete

    Also in 3 projects that use this

  • HK-hubSkill

    distill

    Strip designs to their essence by removing unnecessary complexity. Great design is simple, powerful, and clean. Use when the user asks to simplify, declutter, reduce noise, remove elements, or make a UI cleaner and more focused.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 43 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before picking a technique, collect the user's starting point — experience with the domain, familiarity with this part of the codebase, …

    line 24
  2. Distinctive:

    When a long-horizon task comes back wrong, the instinct is to plan harder.

    line 52

“Common” is measured: kept by at least 6 in 10 of the 43 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

Scout

Distilled from Thariq's A Field Guide to Fable: Finding Your Unknowns.

Premise: the prompt and context are the map; the codebase and its real constraints are the territory. The gap between them is the user's unknowns, and work quality is bottlenecked by clarifying them — before, during, and after implementation. This skill is a toolkit, not a workflow: diagnose, pick one technique, run it inline. Produce no artifact beyond what the technique itself outputs.

Diagnose first

Before picking a technique, collect the user's starting point — experience with the domain, familiarity with this part of the codebase, where they are in their thought process. Every technique below degrades to generic output without it. Then place the unknowns:

QuadrantSignalTechnique
Known knownsAlready in the promptJust work
Known unknowns"I haven't decided X yet"Interview
Unknown knowns"I'll know it when I see it"Prototypes, References
Unknown unknownsUnfamiliar domain or code areaBlindspot pass first

Before implementation

  • Blindspot pass — the user doesn't know what questions to ask. Survey the territory for them: what good looks like, prior art in the repo, common potholes, the domain vocabulary. Teach, don't list — the output should upgrade their next prompt, not just enumerate gaps.
  • Brainstorm + prototypes — criteria they'd only recognize on sight. Show several genuinely different directions with fake data before wiring anything up (HTML artifact for anything visual). Also works for scope: brainstorm interventions from cheapest to most ambitious and let them react.
  • Interview — one question at a time, prioritizing questions whose answers would change the architecture. The grill skill is the heavy-duty version.
  • References — when pointing beats describing. Source code is the best reference: read the implementation they like (any language) and reimplement its semantics, not its surface.
  • Decision-first plan — order the plan by what the user is most likely to tweak: data models, type interfaces, user-facing flows on top; mechanical refactors at the bottom.

During implementation

  • Deviation notes — unknowns surface mid-flight no matter how good the plan. On hitting one: pick the conservative option, log it under a Deviations heading in implementation-notes.md, keep going. The log feeds the next attempt's map.

After implementation

  • Explainer / pitch — reviewers start with the same unknowns the user had. Package prototype, spec, and deviation notes into one doc that answers them up front.
  • Quiz — the user merges only what they can pass a quiz on. Report what changed with context and intuition, quiz at the bottom, perfect score before merge. The teach skill is the full loop.

The habit

When a long-horizon task comes back wrong, the instinct is to plan harder; the fix is usually to find the unknowns the plan was silent about. Every technique here is a cheap way to learn something before it gets expensive to fix.

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.

Reviews can't be read right now.

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