|
|
|
@@ -1,108 +1,129 @@
|
|
|
|
|
---
|
|
|
|
|
name: wayfinder
|
|
|
|
|
description: Chart a route through a foggy problem — turn a loose idea into a map of investigation tickets and resolve them one at a time until the way to the goal is clear.
|
|
|
|
|
disable-model-invocation: true
|
|
|
|
|
description: Chart a route through a foggy problem — turn a loose idea into a shared map of investigation tickets on your issue tracker, and resolve them one at a time until the way to the goal is clear.
|
|
|
|
|
---
|
|
|
|
|
|
|
|
|
|
A loose idea has arrived — too big for one agent session, and wrapped in fog: the route from here to a plan isn't visible yet. This skill charts it: stand up a map, then work its tickets one at a time until the way to the goal is clear. The map is domain-agnostic — engineering work, course content, whatever fits the shape.
|
|
|
|
|
A loose idea has arrived — too big for one agent session, and wrapped in fog: the route from here to a plan isn't visible yet. This skill charts it as a **shared map** on the repo's issue tracker, then works its tickets one at a time. The map is domain-agnostic — engineering work, course content, whatever fits the shape.
|
|
|
|
|
|
|
|
|
|
## Refer by name
|
|
|
|
|
|
|
|
|
|
Every map and ticket is an issue, so it has a **name** — its title. In everything the human reads — narration, the map's Decisions-so-far, the Handoff — 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, and Handoff commands still paste the URL — but they ride *inside* the name, never stand in for it.
|
|
|
|
|
|
|
|
|
|
## The Map
|
|
|
|
|
|
|
|
|
|
The map is a single compact Markdown file, one per wayfinding effort, git-tracked alongside the project. It is the canonical artifact — the **whole map is loaded as context into every session**, so it must stay compact.
|
|
|
|
|
The map is a single issue on this repo's issue tracker, labelled `wayfinder:map` — the canonical artifact. Its tickets are child issues of the map.
|
|
|
|
|
|
|
|
|
|
Assets created during tickets should be linked to from the map, not duplicated within it.
|
|
|
|
|
The map is an **index**, not a store. It lists the decisions made and points at the tickets that hold their detail; a decision lives in exactly one place — its ticket — so the map never restates it, only gists it and links.
|
|
|
|
|
|
|
|
|
|
### Structure
|
|
|
|
|
**Where the map, its child tickets, blocking, and frontier queries physically live is tracker-specific.** Consult `docs/agents/issue-tracker.md` (the "Wayfinding operations" section) for how _this_ repo expresses them. If that doc is absent, default to the local-markdown tracker.
|
|
|
|
|
|
|
|
|
|
Entries ("tickets"), each its own section keyed by a short dash-case slug that
|
|
|
|
|
reads as a mini-title (e.g. `relational-db`, `auth-strategy`, `cache-layer`) —
|
|
|
|
|
terse enough to stay token-efficient, and unique within the map.
|
|
|
|
|
### The map body
|
|
|
|
|
|
|
|
|
|
The whole map at low resolution, loaded once per session. Open tickets are **not** listed — they are open child issues, found by query.
|
|
|
|
|
|
|
|
|
|
```markdown
|
|
|
|
|
## relational-db: Relational Or Non-Relational Database?
|
|
|
|
|
## Notes
|
|
|
|
|
|
|
|
|
|
Blocked by: <slug>, <slug>
|
|
|
|
|
Status: open | in-progress | resolved
|
|
|
|
|
Type: Research | Prototype | Grilling | Task
|
|
|
|
|
<domain; skills every session should consult; standing preferences for this effort>
|
|
|
|
|
|
|
|
|
|
### Question
|
|
|
|
|
## Decisions so far
|
|
|
|
|
|
|
|
|
|
<question-here>
|
|
|
|
|
<!-- the index — one line per closed ticket: enough to judge relevance, then zoom the link for the detail the ticket holds -->
|
|
|
|
|
|
|
|
|
|
### Answer
|
|
|
|
|
- [<closed ticket title>](link) — <one-line gist of the answer>
|
|
|
|
|
|
|
|
|
|
<answer-here>
|
|
|
|
|
## Fog
|
|
|
|
|
|
|
|
|
|
<!-- see "Fog of war" for what belongs here -->
|
|
|
|
|
```
|
|
|
|
|
|
|
|
|
|
The slug is the canonical id, used in every `Blocked by` edge and prose
|
|
|
|
|
reference; the title after the colon is optional. A ticket
|
|
|
|
|
is **unblocked** when every ticket in its `Blocked by` list is `resolved`. A
|
|
|
|
|
session **claims** its ticket by setting `Status: in-progress` and saving the map
|
|
|
|
|
before any work, so concurrent sessions skip it.
|
|
|
|
|
### Tickets
|
|
|
|
|
|
|
|
|
|
Each ticket must be sized to one 100K token agent session.
|
|
|
|
|
Each ticket is a **child issue** of the map; the tracker's issue id is its identity. Its body is the question, sized to one 100K token agent session:
|
|
|
|
|
|
|
|
|
|
```markdown
|
|
|
|
|
## Question
|
|
|
|
|
|
|
|
|
|
<the decision or investigation this ticket resolves>
|
|
|
|
|
```
|
|
|
|
|
|
|
|
|
|
Two label families:
|
|
|
|
|
|
|
|
|
|
- `wayfinder:<type>` — one of `research`, `prototype`, `grilling`, `task` (see [Ticket Types](#ticket-types)).
|
|
|
|
|
- `wayfinder:claimed` — a session sets this **first**, before any work, so concurrent sessions skip it.
|
|
|
|
|
|
|
|
|
|
Blocking uses the tracker's native semantics. A ticket is **unblocked** when every ticket blocking it is closed. The **frontier** is the open, unblocked, unclaimed children — the edge of the known.
|
|
|
|
|
|
|
|
|
|
The answer isn't part of the body — it's recorded on resolution (see [Work through the map](#work-through-the-map)). Assets created while resolving a ticket are linked from the issue, not pasted in.
|
|
|
|
|
|
|
|
|
|
## Ticket Types
|
|
|
|
|
|
|
|
|
|
There are four types of tickets:
|
|
|
|
|
|
|
|
|
|
- **Research**: Reading documentation, third-party API's, or local resources like knowledge bases. Creates a markdown summary as an asset. Use this when knowledge outside the current working directory is required.
|
|
|
|
|
- **Prototype**: 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. Creates the prototype as an asset. Use this when "how should it look" or "how should it behave" is the key question.
|
|
|
|
|
- **Research**: Reading documentation, third-party APIs, or local resources like knowledge bases. Creates a markdown summary as a linked asset. Use when knowledge outside the current working directory is required.
|
|
|
|
|
- **Prototype**: 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**: Conversation with the agent. Uses the /grilling and /domain-modeling skills. Asks one question at a time. The default case.
|
|
|
|
|
- **Task**: Literal manual work that must be done before the discussion can move forward — nothing to decide, prototype, or research. Moving data from one place to another, signing up for a third-party service, provisioning access. The agent automates it where it can; otherwise it hands the human a precise checklist to do by hand. 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.
|
|
|
|
|
- **Task**: Literal manual work that must be done before the discussion can move forward — nothing to decide, prototype, or research. Moving data, signing up for a service, provisioning access. The agent automates it where it can; otherwise it hands the human a precise checklist. 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 beyond the frontier — don't chart what you can't yet see. The frontier is the unblocked tickets at the edge of the known; resolve them to push it forward. Push back the fog of war one ticket at a time, until the way to the goal is clear and no tickets remain.
|
|
|
|
|
The map is _deliberately_ incomplete: don't chart what you can't yet see. Beyond the tickets lies fog — 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 goal is clear and no tickets remain.
|
|
|
|
|
|
|
|
|
|
The map's **Fog** section is where that dim view is written down: the suspected question, the area to revisit later, the risk you're deferring. 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.
|
|
|
|
|
- **Fog when** you can't yet phrase it that sharply. Don't pre-slice 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.
|
|
|
|
|
|
|
|
|
|
Fog excludes only what's already decided (that's Decisions so far) and what's already a ticket.
|
|
|
|
|
|
|
|
|
|
## Invocation
|
|
|
|
|
|
|
|
|
|
Two branches. Either way, **every session ends with a [Handoff](#handoff)** — never resolve more than one ticket per session.
|
|
|
|
|
Two modes. Either way, **every session ends with a [Handoff](#handoff)** — never resolve more than one ticket per session.
|
|
|
|
|
|
|
|
|
|
### Chart the map
|
|
|
|
|
|
|
|
|
|
User invokes with a loose idea.
|
|
|
|
|
|
|
|
|
|
1. Run a `/grilling` and `/domain-modeling` session to surface the open decisions.
|
|
|
|
|
2. Write a new map — mostly fog, frontier identified, trivially-decidable entries resolved inline.
|
|
|
|
|
3. Handoff. Charting the map is one session's work; do not also resolve tickets.
|
|
|
|
|
2. **Create the map** (label `wayfinder:map`): Notes filled in, Decisions-so-far empty, Fog sketched.
|
|
|
|
|
3. **Create the tickets you can specify now** as child issues of the map — then wire blocking edges in a **second pass** (issues 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.
|
|
|
|
|
4. Handoff. Charting the map is one session's work; do not also resolve tickets.
|
|
|
|
|
|
|
|
|
|
### Work through the map
|
|
|
|
|
|
|
|
|
|
User invokes with a path to an existing map. A ticket slug is **optional** — without one, you pick the next decision, not the user.
|
|
|
|
|
User invokes with a map (URL or number). A ticket is **optional** — without one, you pick the next decision, not the user.
|
|
|
|
|
|
|
|
|
|
1. Load the **whole map** as context.
|
|
|
|
|
2. Choose the ticket. If the user named one, use it. Otherwise pick the first `open` ticket in document order that is [unblocked](#structure). [Claim it](#structure): set `Status: in-progress` and save before any work.
|
|
|
|
|
3. Resolve it, invoking skills as needed — including any the `## Notes` block names. If in doubt, use `/grilling` and `/domain-modeling`.
|
|
|
|
|
4. Record the answer in the ticket's body and set `Status: resolved`.
|
|
|
|
|
5. Add newly-discovered tickets with correct `Blocked by` edges. If the decisions made invalidate other parts of the map, update or delete those tickets.
|
|
|
|
|
1. Load the **map** — the low-res view, not every ticket body.
|
|
|
|
|
2. Choose the ticket. If the user named one, use it. Otherwise take the first frontier ticket in order. **Claim it**: set `wayfinder:claimed` and save before any work.
|
|
|
|
|
3. Resolve it — **zoom as needed**: fetch the full body of any related or closed ticket on demand; invoke the skills the `## Notes` block names. If in doubt, use `/grilling` and `/domain-modeling`.
|
|
|
|
|
4. Record the resolution: post the answer as a **resolution comment**, **close** the issue, and **append a context pointer** to the map's Decisions-so-far.
|
|
|
|
|
5. Add newly-surfaced tickets (create-then-wire); graduate any fog the answer has made specifiable, clearing each graduated patch from the Fog so it lives only as its new ticket. If the decision invalidates other parts of the map, update or delete those tickets.
|
|
|
|
|
6. Handoff.
|
|
|
|
|
|
|
|
|
|
The user may run unblocked tickets in parallel, so expect other agents to be editing the map in their own sessions.
|
|
|
|
|
The user may run unblocked tickets in parallel, so expect other sessions to be editing the tracker concurrently.
|
|
|
|
|
|
|
|
|
|
## Handoff
|
|
|
|
|
|
|
|
|
|
End every session by clearing the context and opening one or more fresh sessions. Close with a **Next steps** block the user can copy-paste. Two cases:
|
|
|
|
|
**Recheck your claims first.** Before you show the frontier, reread every assertion you're about to hand off — the resolution answer, the Decisions-so-far line you appended, any facts later tickets will depend on — against the actual tracker state and the assets you linked, and fix whatever doesn't hold. The available sessions and the new frontier the human is about to act on are only as sound as the claims underneath them.
|
|
|
|
|
|
|
|
|
|
**Open tickets remain.** List the currently-unblocked tickets, then give two copy-paste options: a bare command for one session (you pick the next ticket), and one pinned command per unblocked ticket for running them in parallel. Paste one line per fresh window — opening one, some, or all of them.
|
|
|
|
|
Then end every session with a **Next steps** block the user can copy-paste. Two cases:
|
|
|
|
|
|
|
|
|
|
> **Next steps** — 3 tickets unblocked: `auth-strategy`, `cache-layer`, `rate-limits`.
|
|
|
|
|
> Clear the context, then open fresh sessions.
|
|
|
|
|
**Open tickets remain.** Query the map for the currently-unblocked children, then give two copy-paste options: a bare command for one session (you pick the next ticket), and one pinned command per unblocked ticket for running them in parallel. Paste one line per fresh window — opening one, some, or all of them.
|
|
|
|
|
|
|
|
|
|
> **Next steps** — *<map name>*: 3 tickets unblocked. Clear the context, then open fresh sessions.
|
|
|
|
|
>
|
|
|
|
|
> **One session** — resolves the next unblocked ticket:
|
|
|
|
|
>
|
|
|
|
|
> ```
|
|
|
|
|
> Invoke /wayfinder with the map at <path>.
|
|
|
|
|
> Invoke /wayfinder with the map <map-url>.
|
|
|
|
|
> ```
|
|
|
|
|
>
|
|
|
|
|
> **Parallel** — paste one line per window, up to all 3:
|
|
|
|
|
>
|
|
|
|
|
> ```
|
|
|
|
|
> Invoke /wayfinder with the map at <path>, ticket auth-strategy.
|
|
|
|
|
> Invoke /wayfinder with the map at <path>, ticket cache-layer.
|
|
|
|
|
> Invoke /wayfinder with the map at <path>, ticket rate-limits.
|
|
|
|
|
> Invoke /wayfinder with the map <map-url>, ticket <issue-url>. # <ticket name>
|
|
|
|
|
> Invoke /wayfinder with the map <map-url>, ticket <issue-url>. # <ticket name>
|
|
|
|
|
> Invoke /wayfinder with the map <map-url>, ticket <issue-url>. # <ticket name>
|
|
|
|
|
> ```
|
|
|
|
|
|
|
|
|
|
**No open tickets remain.** The fog is pushed back far enough that the way to the goal is clear — the map is done. (The initial grilling may also surface no fog at all, in which case there was never a map to chart.) Recommend implementing directly, or using `/to-prd` to schedule a multi-session implementation.
|
|
|
|
|
|
|
|
|
|
## Notes
|
|
|
|
|
|
|
|
|
|
An optional block declaring the **domain**, any skills every session should `consult`, and freeform standing preferences for this effort.
|
|
|
|
|
