wayfinder
Skill4 starsChanged 16 days agoMITView on GitHub
Plan work too large for one agent session as durable Work Tracker decision tickets.
194 other projects use a version of this, 161 of them edited.
Adopted by
Most recently taken up by
- therealtinhtute/mono-harnesstheir own version, first seen Nov 8, 2026
- domengabrovsek/agent-configedited, first seen Nov 8, 2026
- domengabrovsek/claudeedited, first seen Nov 8, 2026
- The-Vibe-Company/quivredited, first seen Nov 8, 2026
- 5thlayer/skillworksedited, first seen Nov 8, 2026
- zhikedan/mattpocock-skills-dshedited, first seen Nov 8, 2026
Used with
Projects with it also use setup-ts-deep-modules, loop-me and 7 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
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
LesaniSkillwriting-shape
Take a markdown file of raw material and shape it into an article through a conversational session — drafting candidate openings, growing the piece paragraph by paragraph, arguing about format (lists, tables, callouts, quotes) at each step. Use when the user has a pile of notes, fragments, or a rough draft and wants help turning it into something publishable.
Also in 53 projects that use this
AWSSkillimplement-spec
Implement the result of /to-spec and /to-tickets in code.
Also in 64 projects that use this
- +1 more from Lesani
Other versions194 projects use a version of this.
Word for word · 0
None found.
Edited · 161
- mattpocock/skills★ 309k68% same
- QuivrHQ/quivr★ 40k71% same
- The-Vibe-Company/quivr★ 40k71% same
- ArcReel/ArcReel★ 6.3k68% same
- withcoral/coral★ 4.9k68% same
- epicenter-md/epicenter★ 4.8k74% same
- EpicenterHQ/epicenter★ 4.8k74% same
- bestofjs/bestofjs★ 3.1k73% same
- CelestoAI/SmolVM★ 1.2k71% same
- moeru-ai/xsai★ 66771% same
151 more not listed
Wrote their own version · 33
- vinvcn/mattpocock-skills-zh-CN★ 5.5ksame name
- stevesolun/ctx★ 583same name
- devcxl/mattpocock-skills-zh★ 522same name
- PromptPartner/agentsmith★ 173same name
- drvoss/everything-copilot-cli★ 48same name
- KrishP147/skills★ 37same name
- gaia-research/gaia-skill-tree★ 22same name
- imMamdouhaboammar/matts-skills-into-chatgpt★ 8same name
- Boom-Vitt/skills-thai★ 5same name
- therealtinhtute/mono-harness★ 5same name
23 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 repository31 other files it gives its agents.
- AGENTS.mdAGENTS.md
- ask-smittSkill
- change-walkthroughSkill
- closeoutSkill
- codebase-designSkill
- code-reviewSkill
- deliver-specSkill
- deliver-ticketSkill
- diagnosing-bugsSkill
- domain-modelingSkill
- grill-with-docsSkill
- implementSkill
- improve-codebase-architectureSkill
- prototypeSkill
- prSkill
- researchSkill
- resolving-merge-conflictsSkill
- review-feedbackSkill
- setup-federated-workflowSkill
- tddSkill
- to-specSkill
- to-ticketsSkill
- triageSkill
- wizardSkill
- grillingSkill
- grill-meSkill
- handoffSkill
- teachSkill
- to-questionnaireSkill
- wait-whatSkill
- writing-for-agentsSkill
The file
We split this skill into the rules it gives an agent
6 rules. 1 is common, 3 are distinctive, and 2 are very specific to this project.
1
Common
Most of the 179 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 7
Read Work Tracker context assembly before charting a Map, navigating one, or resolving a Decision Ticket.
- Distinctive: line 21
Before charting or resolving a map:
- Very specific: line 23
Read docs/agents/issue-tracker.md when present and use its configured Work Tracker locator, terminology, claim, dependency, comment, and …
- Very specific: line 24
When docs/agents/domain.md is present, read domain orientation, then the configured file, before selecting domain sources or composing …
- Distinctive: line 25
If a Domain Federation is relevant, put its portable Home identity and the relevant Repository-qualified Context Pointers in the map's …
- Common: line 134
Stop. Charting is one session's work.
“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
Read Work Tracker context assembly before charting a Map, navigating one, or resolving a Decision Ticket.
A loose idea has arrived — too big for one agent session, and wrapped in fog: the way from here to the destination isn't visible yet. Wayfinding is about finding that way, not charging at the destination. Chart the way as a shared map on the configured Work Tracker, then resolve its decision tickets one at a time until the route is clear. Each ticket resolves a decision rather than a build slice.
The destination varies per effort, and naming it is the first act of charting — it shapes every ticket. It might be a spec to hand off and iterate on, a decision to lock before planning starts, or a change made in place like a data-structure migration. The map is domain-agnostic — engineering work, course content, whatever fits the shape.
Plan, don't do
Wayfinder is planning by default: each ticket resolves a decision, and the map is done when the way is clear — nothing left to decide before someone goes and does the thing. The pull to just do the work is usually the signal you've reached the edge of the map and it's time to hand off. An effort can override this in its Notes — carrying execution into the map itself — but absent that, produce decisions, not deliverables.
Ordinary planning does not write future-state terms, map changes, or architecture decisions into canonical repository documents. While resolving an active ticket, maintain every returned Domain Model Delta at full fidelity in that ticket's single ## Resolution draft.
Configured authority
Before charting or resolving a map:
- Read
docs/agents/issue-tracker.mdwhen present and use its configured Work Tracker locator, terminology, claim, dependency, comment, and Wayfinding operations. Do not infer the tracker from a Git remote. - When
docs/agents/domain.mdis present, read domain orientation, then the configured file, before selecting domain sources or composinggrill-with-docs. - If a Domain Federation is relevant, put its portable Home identity and the relevant Repository-qualified Context Pointers in the map's Notes so later sessions can orient without checkout-local paths.
For every durable Map or Decision source whose content informs the work, invoke the shared Context Assembly contract with the Ticket Origin Repository, the selected profile, and one permanent root. Tracker metadata used only to locate, select, or claim a ticket may be read directly through the configured Wayfinding operations. Accept only Complete and retain its returned file path unchanged. The active Wayfinder session consumes that file instead of reading the provider. Pass its path unchanged to any research subagent working from the source; the subagent consumes the file and performs no provider read or Context Assembly.
The Wayfinder frontier is the open, unblocked, unclaimed children of one map. It remains separate from the Delivery frontier. Wayfinder artifacts use only the map and ticket shapes below.
Refer by name
Every map and ticket is a Work Tracker item, so it has a name — its title. In everything the human reads — narration, the map's Decisions-so-far — refer to it by that name, never by a bare id, number, or slug. A wall of #42, #43, #44 is illegible; names read at a glance. The id and URL don't vanish — a name wraps its link — but they ride inside the name, never stand in for it.
The Map
The map is one item on the configured Work Tracker, carrying the configured wayfinder:map label — the canonical artifact. Its tickets are child items of the map.
The map is an index, not a store. Accepted content lives in recognized Resolution records, so the Map gists it and links through permanent references rather than restating it. Preserve historical and effective entries under the Context Assembly succession contract.
Where the map, its child tickets, blocking, and frontier queries physically live is tracker-specific. The Work Tracker binding should have been provided to you — run the applicable setup skill if not. Consult its "Wayfinding operations" section for how this repository expresses them. If no binding has been provided and no configured federation is in play, preserve standalone behavior by using the local-Markdown tracker.
The map body
The whole map at low resolution supplies initial session orientation. Open tickets are not listed — they are open child items, found by the configured query.
## Destination
<what reaching the end of this map looks like — the spec, decision, or change this effort is finding its way to. One or two lines; every session orients to it before choosing a ticket.>
## Notes
<domain; skills every session should consult; standing preferences for this effort>
## Decisions so far
<!-- map index -->
- [<closed ticket title>](link) — <one-line gist of the answer>
## Not yet specified
<!-- see "Fog of war": in-scope fog you can't ticket yet; graduates as the frontier advances -->
## Out of scope
<!-- see "Out of scope": work ruled beyond the destination; closed, never graduates -->Tickets
Each ticket is a child item of the map; the Work Tracker's item id is its identity. Its body is the question, sized to one 100K token agent session:
## Question
<the decision or investigation this ticket resolves>Each ticket carries a wayfinder:<type> label — one of research, prototype, grilling, task (see Ticket Types).
A session claims a ticket by assigning it to the dev driving the map, first, before any work, so concurrent sessions skip it. That assignee is the claim: an open, unassigned ticket is unclaimed.
Blocking uses the Work Tracker's native dependency relationship — essential because it renders the frontier visually in the tracker UI, so the human sees what's takeable without opening the map. Only a tracker that lacks native blocking falls back to its configured body convention. A ticket is unblocked when every ticket blocking it is closed; eligible children enter the Wayfinder frontier.
The answer isn't part of the body — it's recorded on resolution (see Work through the map). Assets created while resolving a ticket are linked from its Work Tracker item, not pasted in.
Ticket Types
Every ticket is either HITL — human in the loop, worked with a human who speaks for themselves — or AFK, driven by the agent alone. A HITL ticket only resolves through that live exchange; the agent never stands in for the human's side of it (a grilling agent that answers its own questions has broken this).
- Research (AFK): Reading documentation, third-party APIs, or local resources like knowledge bases to surface a fact a decision waits on. A frontier research ticket may be claimed and resolved by a
researchsubagent. Use when knowledge outside the current working directory is required. - Prototype (HITL): Raise the fidelity of the discussion by making a cheap, rough, concrete artifact to react to — an outline, a rough take, a stub, or UI/logic code via the /prototype skill. Links the prototype as an asset. Use when "how should it look" or "how should it behave" is the key question.
- Grilling (HITL): Conversation via
grill-with-docs. The default case. - Task (HITL or AFK): Manual work that must happen before a decision can be made — nothing to decide, prototype, or research, but the discussion is blocked until it's done. Signing up for a service so its API can be judged, provisioning access, moving data so its shape can be seen. This is the one type that does rather than decides, and it earns its place by unblocking a decision, not by delivering the destination. The agent drives it alone where it can (AFK); otherwise it hands the human a precise checklist (HITL). Resolved when the work is done; the answer records what was done and any resulting facts (credentials location, new URLs, row counts) later tickets depend on.
Fog of war
The map is deliberately incomplete: don't chart what you can't yet see. Beyond the live tickets lies the fog of war — the dim view of decisions and investigations you can tell are coming but can't yet pin down, because they hang on questions still open. Resolving a ticket clears the fog ahead of it, graduating whatever's now specifiable into fresh tickets — one at a time, until the way to the destination is clear and no tickets remain.
The map's Not yet specified section is where that dim view is written down: the suspected question, the area to revisit later. It's the undiscovered frontier toward the destination — everything here is in scope, just not sharp enough to ticket. Write as loosely or as fully as the view allows; it doubles as a signpost for collaborators reading where the effort is headed.
Fog or ticket? The test is whether you can state the question precisely now — not whether you can answer it now.
- Ticket when the question is already sharp — even if it's blocked and you can't act on it yet.
- Not yet specified when you can't yet phrase it that sharply. Don't pre-slice the fog into ticket-sized pieces: it's coarser than a ticket, and one patch may graduate into several tickets, or none, once the frontier reaches it.
Not yet specified excludes what's already decided (Decisions so far), what's already a live ticket, and what's out of scope (the next section).
Out of scope
Fog only ever gathers toward the destination. The destination fixes the scope, so work beyond it is out of scope — it isn't fog, and it doesn't belong in Not yet specified. It gets its own Out of scope section on the map: work you've consciously ruled out of this effort. Scope, not sharpness, lands it here.
Out-of-scope work never graduates — the frontier stops at the destination — so it returns only if the destination is redrawn, and then as a fresh effort, not a resumption.
Ruling something out of scope is a scoping act, not a step on the route. When a ticket that already exists turns out to sit past the destination — mis-scoped in while charting, or exposed by a resolution — close it (a closed ticket is unambiguously off the frontier) and leave one line in the Out of scope section: the gist plus why it's out of scope, linking the closed ticket. It stays out of Decisions so far, which records the route actually walked — a scope boundary isn't a step on it.
Modes
Two modes. Either way, never hand-resolve more than one ticket per session — research tickets may be delegated in parallel.
Chart the map
Input: a loose idea.
- Name the destination. Use
grillingto pin down what this map is finding its way to — the spec, decision, or change. The destination fixes the scope, so it's settled first. Charting may define the destination, fog, and decision questions, but it does not confirm domain-model changes: turn any material domain-language or architecture question into a decision ticket rather than resolving or storing a Domain Model Delta in the map. - Map the frontier. Continue with
grilling, breadth-first this time: fan out across the whole space rather than deep on any one thread, surfacing the open decisions and the first steps takeable now. If this surfaces no fog — the way to the destination is already clear, the whole journey small enough for one session — you don't need a map. Stop and ask the user how they'd like to proceed. - Create the map (configured
wayfinder:maplabel): Destination and Notes filled in, Decisions-so-far empty, the fog sketched into Not yet specified. Include configured Domain Federation orientation when relevant. - Validate the Map. Invoke fresh shared Context Assembly for
Map Contextat the created Map's permanent reference and finish the step only when its returned file saysComplete. - Create the tickets you can specify now. Validate each proposed Decision Ticket against the planning artifact contracts, then create it. Invoke fresh shared Context Assembly for
Decision Contextat its permanent reference and continue only withComplete. Wire blocking edges in a second pass because items need ids before they can reference each other. Wiring sorts them into the frontier and the blocked; everything you can't yet specify stays in the fog under Not yet specified. - Rebuild the Map. Invoke fresh shared Context Assembly for
Map Contextat the Map's permanent reference after wiring the children, then proceed only when its returned file saysComplete. - Claim frontier research. Re-read the newly wired children and select only
researchtickets on the Wayfinder frontier: open, unblocked, and unassigned. Assign each selected ticket to the dev driving the map, then re-read and verify its claim and blocker state before starting oneresearchsubagent. A failed or changed claim stays on the tracker and does not start. Start each assignment only after fresh shared Context Assembly returnsCompleteDecision Context for that ticket. Pass the accepted file path unchanged to the subagent. The subagent reads that file instead of the provider, captures its findings as the configured linked asset, and finalizes that ticket's Resolution through the shared succession and reconciliation rules. - Stop. Charting is one session's work; it hand-resolves nothing.
Work through the map
Input: a map (URL or number). A ticket is optional — without one, pick the next decision yourself rather than asking the user to choose.
- Choose the ticket from tracker metadata. If the user named one, use it. Otherwise take the first frontier ticket in order. Claim it: assign it to yourself before any work and verify the claim.
- Invoke fresh shared Context Assembly for Decision Context at the ticket's permanent reference. Continue only with
Completeand retain its file path. Use the Map content carried by that Decision Context for orientation. - Resolve it, zooming into additional permanent sources when needed and invoking the skills named in the Map's
## Notes. If in doubt, rungrill-with-docsin the current session with the accepted Decision Context file path unchanged. Maintain the ticket's single complete## Resolution draftas decisions are confirmed, incorporating every returned Domain Model Delta without reduction. - Record the Resolution. Apply the shared succession procedure through the configured binding while finalizing the active ticket's Workflow-Identity-owned draft, closing the ticket, and updating the Map index. Then start reconciliation for the accepted Resolution. Do not publish a competing summary Resolution.
- Add newly surfaced tickets with create-then-wire. Graduate fog the answer has made specifiable, clearing each graduated patch from Not yet specified so it lives only as its new ticket. If the answer reveals a ticket sits beyond the destination, rule it out of scope rather than resolving it on the route.
- Complete the shared reconciliation procedure for every affected context before ending the session.
The user may run unblocked tickets in parallel, so expect other sessions to be editing the tracker concurrently.
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.

