agentleFS
saintdlesaintdle/agentflow/.agents/skills/wayfinder/SKILL.md

wayfinder

Skill2 starsChanged 14 days agoApache-2.0View on GitHub

Map a large, uncertain, multi-session effort into a Beads graph of decisions and investigations before implementation planning. Use when the destination is understood but the route is unclear, major architectural or product choices remain unresolved, or the work cannot yet be safely decomposed into implementation tickets. Do not use when an approved plan is already ready for to-tickets.

194 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use setup-ts-deep-modules, to-questionnaire 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.
  • liufeng1976Skill

    setup-ts-deep-modules

    Wire dependency-cruiser into a TypeScript repo so each package is a deep module — implementation hidden in subfolders, reachable only through its entry-point files. User-invoked.

    Also in 42 projects that use this

  • AWSSkill

    to-questionnaire

    Turn a decision you can't fully answer into a questionnaire for someone else to fill in.

    Also in 87 projects that use this

  • AWSSkill

    wizard

    Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.

    Also in 124 projects that use this

  • RoentekSkill

    loop-me

    Grill me about specs for the workflows I want to build, within this workspace.

    Also in 50 projects that use this

  • LesaniSkill

    writing-beats

    Shape an article as a journey of beats, choose-your-own-adventure style. The user picks a starting beat from the raw material, you write only that beat, then offer options for where to pivot next, beat by beat, until the article reaches a natural end. Use when the user has raw material and wants to assemble it as a narrative rather than an argument.

    Also in 54 projects that use this

  • ryotaroh180105Skill

    claude-handoff

    Hand the current conversation off to a fresh background agent that picks up the work immediately.

    Also in 40 projects that use this

  • +2 more from aws

The file

We split this skill into the rules it gives an agent

10 rules. 0 are common, 7 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 179 edited versions we read keep these.

  • 7

    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:

    If Beads is unavailable, stop and recommend agentflow beads init.

    line 17
  2. Distinctive:

    Create one parent bead:

    line 21
  3. Distinctive:

    Create child beads only for unresolved decisions or bounded investigations:

    line 27
  4. Very specific:

    Use --no-inherit-labels for children.

    line 35
  5. Very specific:

    If delegation is explicitly authorized, use orchestrate-agents for bounded read-only investigation.

    line 41
  6. Distinctive:

    Update the parent with a one-line decision gist and link.

    line 43
  7. Distinctive:

    Add, remove, or rewire child decisions as the route changes.

    line 44
  8. Distinctive:

    Do not store prompts, transcripts, or duplicated research documents in Beads.

    line 46
  9. Distinctive:

    every route-changing question is resolved or explicitly accepted as a constraint.

    line 52
  10. Distinctive:

    no decision child remains ready, blocked, or in progress.

    line 53

“Common” is measured: kept by at least 6 in 10 of the 179 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

Wayfind an Uncertain Effort

Wayfinding resolves uncertainty. It does not disguise implementation work as research.

Define the destination

  1. State the desired destination, why it matters, constraints, non-goals, and evidence that the route is clear.
  2. Inspect repository instructions, existing decisions, source artifacts, current issues, and Beads state.
  3. Identify unresolved decisions whose answers materially change the plan. Separate decisions from facts that can be discovered directly.
  4. Process new user information immediately. Rework the frontier when an answer invalidates earlier assumptions.

If Beads is unavailable, stop and recommend agentflow beads init. Do not create a competing Markdown tracker.

Create the decision map

Create one parent bead:

  • Type: epic or feature
  • Label: af:kind:workflow
  • Purpose: destination, boundaries, route-clear exit conditions, and concise decisions-so-far

Create child beads only for unresolved decisions or bounded investigations:

  • Type: decision for a choice; task only for evidence-gathering
  • Labels: exactly one af:stage:plan, one af:role:decision, and only material af:cap:* labels
  • Acceptance: the evidence and decision required to close the node
  • Dependencies: an edge only when one answer is required before another can be decided
  • Metadata: sources, owner, approved model/tool budget when delegated, and expected decision artifact

Use --no-inherit-labels for children. Keep the initial frontier small. Do not pre-create speculative downstream branches.

Resolve the frontier

  1. Query only ready children below the approved map. Refer to every item as <human title> (<id>), never a bare identifier.
  2. Claim one ready decision. Prefer deterministic inspection and primary sources before using an agent.
  3. If delegation is explicitly authorized, use orchestrate-agents for bounded read-only investigation. The worker returns evidence and options; the controller owns the decision.
  4. Record the decision, evidence, rejected alternatives, consequences, and newly exposed questions on its bead, then close it.
  5. Update the parent with a one-line decision gist and link; keep full detail on the child.
  6. Add, remove, or rewire child decisions as the route changes. Check dependency cycles after structural changes.

Do not store prompts, transcripts, or duplicated research documents in Beads. Store conclusions and artifact references.

Finish at the planning boundary

The map is complete when:

  • every route-changing question is resolved or explicitly accepted as a constraint;
  • no decision child remains ready, blocked, or in progress;
  • decisions are mutually consistent and traceable to evidence;
  • the destination can be expressed as an approvable goal or implementation plan.

Synthesize the route into shape-goal when the goal contract still needs approval, or to-tickets when an approved plan is ready for implementation decomposition. Do not implement from the Wayfinder map unless the user separately authorizes execution.

Return the destination, decisions made, remaining constraints, closed and open nodes in human terms, the resulting plan/spec artifact, and exactly one copy/paste-ready next request.

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.