wayfinder
Skill0 starsChanged 6 days agoMITView on GitHub
Charts an idea too big for one session as a map of open decisions in a local file, then resolves one decision per session until the way to the goal is clear.
195 other projects use a version of this.
Adopted by
Most recently taken up by
- therealtinhtute/mono-harnesstheir own version, first seen Nov 8, 2026
- domengabrovsek/agent-configtheir own version, first seen Nov 8, 2026
- domengabrovsek/claudetheir own version, first seen Nov 8, 2026
- The-Vibe-Company/quivrtheir own version, first seen Nov 8, 2026
- 5thlayer/skillworkstheir own version, first seen Nov 8, 2026
- zhikedan/mattpocock-skills-dshtheir own version, first seen Nov 8, 2026
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.
liufeng1976Skillsetup-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
AWSSkillto-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
AWSSkillwizard
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
RoentekSkillloop-me
Grill me about specs for the workflows I want to build, within this workspace.
Also in 50 projects that use this
LesaniSkillwriting-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
ryotaroh180105Skillclaude-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
Other versions195 projects use a version of this.
Word for word · 1
- josechifflet/setup★ 0100% same
Edited · 0
None found.
Wrote their own version · 194
- mattpocock/skills★ 309ksame name
- QuivrHQ/quivr★ 40ksame name
- The-Vibe-Company/quivr★ 40ksame name
- ArcReel/ArcReel★ 6.3ksame name
- vinvcn/mattpocock-skills-zh-CN★ 5.5ksame name
- withcoral/coral★ 4.9ksame name
- epicenter-md/epicenter★ 4.8ksame name
- EpicenterHQ/epicenter★ 4.8ksame name
- bestofjs/bestofjs★ 3.1ksame name
- CelestoAI/SmolVM★ 1.2ksame name
184 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository23 other files it gives its agents.
- AGENTS.mdAGENTS.md
- codex/AGENTS.mdAGENTS.md
- grok/AGENTS.mdAGENTS.md
- opencode/AGENTS.mdAGENTS.md
- src/AGENTS.mdAGENTS.md
- claude/CLAUDE.mdCLAUDE.md
- context-doctorSkill
- diagnoseSkill
- handoffSkill
- intentSkill
- paper-useSkill
- retroSkill
- skills-claudeSkill
- ui-principlesSkill
- verify-setupSkill
- agent-browserSkill
- grillingSkill
- ponytail-auditSkill
- ponytail-debtSkill
- ponytail-reviewSkill
- ponytailSkill
- security-auditSkill
- thermo-nuclear-code-quality-reviewSkill
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 4 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 179 edited versions we read keep these.
4
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
- Distinctive: line 56
If no fog remains and the work fits one session, say so and stop.
- Distinctive: line 57
Write the map. Leave Decisions empty.
- Distinctive: line 58
Stop; charting resolves nothing.
- Very specific: line 62
Read the map. Without a path, use the only map in ~/.local/state/maps/<repo>/, or ask which one when there are several.
- Distinctive: line 66
Update the map: add new precise questions to Open.
- Very specific: line 67
Stop after one question; research questions are the exception.
- Very specific: line 69
When Open and Fog are empty, the way is clear.
“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.
Files
Wayfinder
Find the way to a goal that is too big and too unclear for one session. Decide; do not build. The map is done when nothing is left to decide before the work starts. When you want to start the work, the map is probably done.
The map
One file outside the repository, so nothing commits it: ~/.local/state/maps/<repo>/<slug>.md. <repo> is the repo root's folder name without a leading dot; <slug> is two or three words from the idea.
# Map: <slug>
Goal: <what done looks like: a spec, a decision or a change; 2 lines at most>
Notes: <constraints, sources to read, standing preferences>
## Decisions
- Q<n> <question>: <answer, one line>. Evidence: <path:line, URL, or the user and the date>
## Open
- Q<n> <question>: <ask | research | try | task>, after: <Q numbers, or none>
## Fog
- <a question you can see coming but cannot yet state precisely>
## Out of scope
- <work past the goal>: <why>- A question goes to Open when you can state it precisely now, even if it waits on another question. Otherwise it goes to Fog, as loosely as you see it. Keep fog coarse: one patch can become several questions, or none.
- Each decision lives in one place. An answer longer than one line goes to
<slug>/Q<n>.mdbeside the map, linked from its decision line. - To the user, name a question by its words, not only by its number.
Question types
ask: only the user can decide. Ask one question at a time, with the options, the evidence and your pick. Never answer for the user.research: a fact from code, docs, data or the web. Find it yourself and record the source.try: the question is how something looks or behaves. Make a cheap, rough sample (a sketch, a stub, a sample output) under onemktemp -ddirectory, show it, and let the user decide.task: a step that must happen before a decision, such as access, an account or sample data. Do it when you can; else give the user numbered steps. Record what was done and the facts that later questions need.
Chart (argument: an idea)
- Settle the goal with the user first; it sets the scope.
- List the open decisions across the whole idea, broad before deep. Research what a read can answer before you ask.
- If no fog remains and the work fits one session, say so and stop. No map.
- Write the map. Leave Decisions empty.
- Stop; charting resolves nothing. Report the map path and the first open questions.
Work (argument: a map path, optional question)
- Read the map. Without a path, use the only map in
~/.local/state/maps/<repo>/, or ask which one when there are several. - Take the question the user names, else the first one in Open whose
afterquestions are all decided and that no other session markedtaken. Mark ittakenbefore you start. - Resolve it by its type.
- Move it to Decisions with its answer and evidence.
- Update the map: add new precise questions to Open; move fog that is now precise to Open and delete it from Fog; move work past the goal to Out of scope with the reason; change or delete each question the answer makes wrong.
- Stop after one question;
researchquestions are the exception. Report the decision and the next open question.
When Open and Fog are empty, the way is clear. Say so, and name the next step: the work itself, or the planner, with this map's path, for more than one sitting. Delete the map only when the user asks.
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
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.

