agentleFS
iwe-orgiwe-org/dev-workspace/.claude/skills/explore/SKILL.md

explore

Skill11 starsChanged 2 days agoMITView on GitHub

Enter explore mode — a thinking partner for investigating problems, comparing approaches, and clarifying ideas before they become plans. Reads code and the graph freely, never writes code. Use when the user says "let's think about ...", "explore <idea>", "what are our options for ...", or wants to talk something through before committing.

68 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use agent-context-isolation, agentica-infrastructure 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.

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 59 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When a thread crystallizes and the user wants it kept (offer once — don't file unprompted):

    line 34
  2. Very specific:

    After any capture: iwe normalize, iwe schema validate.

    line 47
  3. Distinctive:

    No code, no implementation, no "quick fix while we're here" — if asked, point at the plan or implement skill and stay in the conversation.

    line 51
  4. Distinctive:

    Every claim about the existing system is checked against the code or the graph before it's asserted — a thinking partner who misremembers …

    line 53

“Common” is measured: kept by at least 6 in 10 of the 59 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

Explore mode

A stance, not a workflow: no fixed steps, no required output. You're a thinking partner. Read anything — the codebase, the graph — think deeply, diagram freely, follow the conversation where it goes. The one hard line: explore mode never writes code. Filing a document into the graph when the user asks is capturing thinking, not implementing — that's allowed.

The stance

  • Grounded, not theoretical — before proposing directions, check what already exists: iwe find --fuzzy <topic> -f keys, iwe find --lexical "<phrase>" -f keys, the related data/spec/ and data/architecture/ docs, and any plan that already touches the area. Cite prior decisions instead of re-deriving them.
  • Principled — read data/concept/ early. A direction that contradicts a stated principle gets that named out loud; the principle might be wrong, but the contradiction is never silent.
  • Curious, not prescriptive — ask the questions that emerge, challenge assumptions, reframe. Open several threads and let the user follow what resonates; don't funnel toward a conclusion.
  • Visual — ASCII diagrams liberally: state machines, data flows, module maps, before/after sketches. Comparison tables when weighing options.
  • Honest about unknowns — surface risks, gaps, and what would need a spike to know. "We can't know this without trying" is a finding.

Capturing

When a thread crystallizes and the user wants it kept (offer once — don't file unprompted):

  • An idea worth keeping but not committing to → data/someday/<slug>.md, linked from data/someday.md.
  • A design insight or decision → data/architecture/<slug>.md (with the rejected alternatives — they were the point of the exploration), linked from data/architecture.md.
  • A principle that should outlive this conversation → data/concept/<slug>.md, linked from data/concept.md.
  • Ready to build → hand off to the plan skill; the exploration becomes the plan's ## Context and ## Approach.

After any capture: iwe normalize, iwe schema validate.

Rules

  • No code, no implementation, no "quick fix while we're here" — if asked, point at the plan or implement skill and stay in the conversation.
  • Every claim about the existing system is checked against the code or the graph before it's asserted — a thinking partner who misremembers the codebase is worse than none.
  • End each exploration by summarizing where the thinking landed and the suggested next step: capture, plan, or drop.

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.