agentleFS
p10ns11yp10ns11y/skills/stellar-spacemap/SKILL.md

stellar-spacemap

Skill2 starsChanged 40 days agoMITView on GitHub

Authors evidence-driven architecture backlog docs (coming-next style): scorecards, mermaid diagrams, blueprint cards SN-*, thrive vision, gantt order. Use when creating or updating roadmaps, spacemaps, arch-design/coming-next.md, backlog after PRs, or when the user wants blueprint cards, Musk 5-step, or optimistic 10-year plans. Formerly stellar-roadmap. Pairs with ai-optimization, fusion-sage, and higher-order-decision-architect. Triggers: stellar-spacemap, stellar-roadmap, coming-next, SN-*, blueprint cards.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 3 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    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:

    Create or refresh coming-next.md, ROADMAP.md, or arch-design/* backlog

    line 38
  2. Distinctive:

    After a large PR: split done log vs next blueprint cards

    line 39
  3. Very specific:

    Use references/document-template.md.

    line 85
  4. Distinctive:

    No spaces in node IDs (use camelCase)

    line 133
  5. Very specific:

    Prefer flowchart / sequenceDiagram / stateDiagram-v2 / gantt / mindmap

    line 135
  6. Distinctive:

    Always include a References table linking:

    line 153

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Stellar Spacemap — Architecture Backlog Blueprint

Load rule: Formal SoT (section map + card contract). Full template → references/document-template.md only if drafting a new § block.
Rename: formerly stellar-roadmap — same contract.
CLT: ../rules/clt-dual-load.mdc — tables/cards over prose walls (extraneous ↓); evidence columns are germane, not optional.

// Mission
SpaceMapDoc ≔ scorecards + mermaid + SN-* blueprint cards + thrive + gantt
// evidence columns mandatory; thrive ≻ funeral framing

// Axioms
A1  Tables/diagrams ≻ prose walls
A2  Every scorecard row has Evidence (file|test|metric)
A3  Pre-mortem → guardrails (refuse vs build) — not closing defeat
A4  SN-1 dogfood gate before feature cards
A5  Compose: scout([ai-optimization](../ai-optimization/SKILL.md)) → decide([higher-order-decision-architect](../higher-order-decision-architect/SKILL.md)) → synthesize([fusion-sage](../fusion-sage/SKILL.md)) → write(this)

Provenance pattern: examples/shell-kernel.md.


When to use

  • Create or refresh coming-next.md, ROADMAP.md, or arch-design/* backlog
  • After a large PR: split done log vs next blueprint cards
  • User asks for: blueprint cards, scorecard, thrive vision, SN-* items, gantt sprint order
  • User attaches /ai-optimization /fusion-sage /higher-order-decision-architect for roadmap work

Do not use for: single-file bug fixes, code-only tasks, or pessimistic "this feature will die" post-mortems without a thrive north star.


Companion skills (load together)

SkillRole in this workflow
ai-optimizationHierarchy first; compress scout; tables > prose; never drop evidence columns
fusion-sageFused abstraction (1 diagram); surplus item at end; binding energy on backlog items
higher-order-decision-architectConsequence chain table; guardrails not funeral; confidence % on thrive bets

Internal order: scout (Context Sage) → decide (HODA) → synthesize (Fusion) → write doc (this skill).


Tone rules (non-negotiable)

  1. Thrive, not survive — platform shifts are cosmic weather you punch through; bottlenecks are judgment/trust, not typing.
  2. Evidence columns — every scorecard row: Grade | One line | Evidence (file, test, metric).
  3. Short Orwellian English — one idea per line; no hedge walls.
  4. Metaphor tier — default spacecraft (ship computer, command bridge, hull, launch). User may say "plain" to drop metaphor.
  5. Risk ≠ defeat — pre-mortem becomes trajectory guardrails (refuse vs build toward 2036). No "optional workflow that may die" framing for core product pillars the user cares about.
  6. Plain rule — one closing sentence at footer; memorable, actionable.

Mandatory workflow

1. Intake (ask only if missing)

InputRequired
Target file pathYes
Mission (one sentence)Yes
What shipped (PR / commits)Yes
Thrive picture (3–5 year horizon)Yes
Backlog items (raw bullets OK)Yes
Metaphor tierDefault spacecraft

2. Structure (13 sections)

Use references/document-template.md. For scout, load a repo-type overlay first: examples/ (shell-kernel, eve-agent) — expand full coming-next.md only for cards being edited.

Section map:

§Purpose
0Mission one sentence
0bTen-year thrive picture (mermaid + table)
1Scorecard shipped vs open
2System map today
3Precedence / data-flow (if applicable)
4Musk 5-step on backlog
5Trajectory forces (not "why we'll fail")
6Guardrails refuse vs build
7Blueprint cards SN-*
8Scope lock (user decisions)
9Gantt sprint order
10Monitoring signals
11Done log
12File touch mindmap
13References

3. Blueprint card format (batch-2 style)

Each card must include:

### SN-N · Title (verb-first)

**Problem:** One line.

```mermaid
[flow | sequence | state — pick one]
FileWork
pathaction

Done when: Observable pass condition.

Verify: Commands or dogfood steps.


Priority: **SN-1 dogfood gate** (no new code) before feature cards.

### 4. Mermaid guardrails

- No spaces in node IDs (use camelCase)
- Subgraph titles in quotes if they contain special chars
- Prefer `flowchart` / `sequenceDiagram` / `stateDiagram-v2` / `gantt` / `mindmap`

### 5. Fusion pass before write

One fused abstraction in §0b or §2, e.g.:

> Kernel (ship computer) + Bridge (verification) + PLUGIN (hull bays) → host-agnostic manifest

Trace to ≥2 real paths in the repo.

### 6. Close with surplus

End agent reply (not necessarily the doc) with one **⚡ Fusion Surplus** line: backlog item or invariant that saves future roadmap tokens.

---

## External style sources (§13 pattern)

Always include a **References** table linking:

| Source | Use |
|--------|-----|
| Project boundary doc | e.g. PLUGIN.md |
| Risk / depth analysis | optional; thrive §0b is north star |
| collab-finder [intuitive-shell-plan](https://github.com/p10ns11y/collab-finder/blob/main/reports/intuitive-shell-plan.md) | Blueprint cards |
| collab-finder [batch-2-blueprints](https://github.com/p10ns11y/collab-finder/blob/main/reports/batch-2-engineering-blueprints.md) | Scorecard, gantt, done-when |
| collab-finder [single-pr-intuitive-product](https://github.com/p10ns11y/collab-finder/blob/main/reports/single-pr-intuitive-product.md) | Musk 5-step, 2nd/3rd order |

Full list: [references/external-sources.md](references/external-sources.md).

---

## Output checklist

- [ ] §0 mission is optimistic and concrete
- [ ] §0b thrive mermaid + 2036 table present
- [ ] Scorecard has Evidence column
- [ ] ≥3 blueprint cards with done-when + verify
- [ ] Gantt matches card priority
- [ ] No defeatist language on pillars user wants to keep
- [ ] References §13 complete
- [ ] Footer plain rule present

---

## Additional resources

- Full section template: [references/document-template.md](references/document-template.md)
- Lens integration detail: [references/companion-skills.md](references/companion-skills.md)
- **Repo-type overlays (scout ~30% cheaper):** [examples/README.md](examples/README.md) — [shell-kernel](examples/shell-kernel.md) · [eve-agent](examples/eve-agent.md) ([Eve](https://vercel.com/eve))
- Example output pattern: [examples/shell-kernel.md](examples/shell-kernel.md)
- Repo-specific full doc: copy overlay into target project or see skills library [shellyxz-shell-kernel overlay](../../examples/overlays/shellyxz-shell-kernel.md)

---

## Install

```bash
ln -sfn "$SKILLS_ROOT/stellar-spacemap" ~/.cursor/skills/stellar-spacemap
# or: .agents/skills/stellar-spacemap | .cursor/skills/stellar-spacemap per project

Invoke: /stellar-spacemap + companion skills for full pipeline.

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.