⏳ This skill is pending AI review.
Scores will appear once the review pipeline completes.
aesthetic-instrument
great_cto's own committed aesthetic — the instrument panel. Dark five-step surface ladder, exactly one accent, two faces divided by MEANING (Geist speaks, Geist Mono is machine-truth), tabular numerals, and a dash that is not a nought. Twelve checkable rules measured from packages/board and greatcto.systems, not designed for this file. Use when building or extending any great_cto surface — the board, the site, a report, a share page.
Choose how to use this skill
You do not need every option. Choose the path your AI client supports. The stable page stays the same; versioned files are immutable.
1. Native installer
This listing has no registered native installer command. Use the complete package or source fallback below, depending on what your client supports.
Do not guess an installer command or replace an existing version without reviewing the diff.
2. Complete package recommended
Download the ZIP when available. It includes SKILL.md plus the references, security notes and version metadata.
No complete ProSkills package is published for this listing yet.3. Prompt-only
Copy the prompt above when the agent can read the stable page or when you want to adopt the workflow without installing a skill.
Need only the instruction file?
Download SKILL.md only if your client requires a single file. The complete ZIP is safer for a full installation because it preserves the references and release context.
No path installs or executes anything by itself. Your agent still needs access to the project files. Before updating, compare the installed version and review the diff.
// RATINGS
Not yet listed on ClawHub or SkillsMP
// README
See the work. Trace the decisions.
Actual 3.70 interface. The graph uses an offline controller run with stub responses, not live models.
Legacy 3.70.1 command. See the verified distribution boundary below for current activation limits.
npx great-cto init
Website · One real run → · Blog · Changelog
Русский · 简体中文 · 繁體中文 · 日本語 · 한국어 · Español · Português · Deutsch · Français
Keep the task, its checks and your next decision connected.
great_cto coordinates Claude Code workflows and experimental controlled Codex runs through explicit stages, review and gates. The local board brings tasks, recorded execution, project documents and consumption into one workspace. Missing evidence stays unknown; a successful worker is not proof that a task was accepted, merged or deployed. You use your own provider account; great_cto is MIT and bills nothing.
Project focus presents eight core roles plus the selected project's required reviewers. The full catalog of 73 agents remains available. Catalog availability is not proof of execution or expertise.
Quick start
Verified distribution boundary (ADR-045): this implementation replaces mutable installers
with verified artifact admission. init, native plugin refresh and automatic
companion installation currently refuse activation. Plain npm self-update needs
the separately configured verifier and a signed release artifact set. This is
not evidence of an installed or published update. See
verified updates for the supported boundary.
The commands below describe the legacy 3.70.1 installation flow; they are not
an activation route for this implementation.
npx great-cto init
Restart Claude Code. Day to day there are three things:
| In Claude Code | In the terminal | |
|---|---|---|
| Start work | /start "add Google login" | great-cto run "add Google login" |
| See what needs you | /inbox | great-cto status |
| Continue | /resume | great-cto resume |
/start takes a new product or a task in an existing project and picks the
workflow itself. /resume continues only what you already approved; a pending
decision still waits for you. Everything else — /review, /spec, /save,
/digest and the rest — is there when you need it:
all commands.
Setting up through an AI agent? Paste the one prompt in Quick start for AI agents into Claude Code or Codex.
One project, five views
Run great-cto board to open the local board, normally at localhost:3141.
Readings such as unverifiable, unmeasured and unavailable are not passes.
| View | What you can inspect |
|---|---|
| Work | Tasks, acceptance criteria, the next supported action, and Overview / Execution / Evidence tabs |
| Decisions | Pending decisions and existing gate controls, without broadening their authority |
| Knowledge | Read-only project Markdown, ADRs and a bounded diagram viewer with Mermaid source fallback |
| Insights | Recorded task outcomes, project-scoped token consumption, estimates and budgets kept separate |
| Settings | Executors, Runtime, Capabilities and General controls |

Execution shows controller-recorded causal history for controlled runs, including attempts, checks, verification, gates and repair. Native and legacy sessions stay partial or unavailable; missing edges are not inferred. This is not a live terminal or workflow editor. The sample graph comes from offline stub responses, not models.

A role verdict is not independent-review proof. Merge, release and deployment need their own evidence; unknown is not zero or pass.

Documents keep their original language. The application interface is English. The diagram describes declared architecture, not a running task.

These screenshots use isolated synthetic ACME records. They do not measure host quality, acceptance rate or quality uplift. Capture contract.
Eight core roles, task-dependent specialists
| Responsibility | Role |
|---|---|
| Problem and acceptance | product-owner |
| System design and tradeoffs | architect |
| Plan and dependencies | pm |
| Implementation | senior-dev |
| Independent code review | code-reviewer |
| Verification and regressions | qa-engineer |
| Risk and ship gate | security-officer |
| Authorized deployment | devops |
These are responsibility contracts, not eight mandatory model calls or eight concurrent agents. Project focus is a presentation view; it does not remove specialists, change dispatch or waive required checks. Risk-specific reviewers remain governed by project policy.
Web frontends and mobile builds are not deployed by devops: it hands them to
release-manager, which builds once from the CI-green commit, stages the build on a
preview URL or an internal test track, has e2e-test-engineer test that exact build,
and promotes or prepares the store submission only after gate:release. A release
counts as done when its receipt in .great_cto/releases/ names the build, the tests,
the landed version and the rollback. /release ship <web|ios|android|ota> starts it.
Focused engineering context
Five versioned, opt-in domain pack candidates cover four focus areas:
| Area | Engineering invariants | Boundary |
|---|---|---|
| Money & crypto execution | Payment idempotency, ambiguous sends, scoped authority; signing boundaries, paper/live separation and chain finality | Two technical packs; no investment-performance claim |
| Telemedicine workflows | Clinician authority, prescription state transitions and evidence integrity | No clinical efficacy or certification claim |
| Venture evidence | Claim provenance, entity lineage and quarantine of unverified assertions | No investment-outcome claim |
| Mental wellbeing safety | Subject isolation, crisis escalation precedence and clinical-claim boundaries | Separate from diagnosis, treatment and clinical validation |
Packs add engineering context. They do not broaden permissions or change required-reviewer routing. Their presence does not prove invocation,
// HOW IT'S BUILT
// FILES
2 files shipped with this skill. Inline text is the catalog copy. The upstream link is the source repository.
skills/aesthetic-instrument/SKILL.md7.6 KBupstream ↗
--- name: aesthetic-instrument description: "great_cto's own committed aesthetic — the instrument panel. Dark five-step surface ladder, exactly one accent, two faces divided by MEANING (Geist speaks, Geist Mono is machine-truth), tabular numerals, and a dash that is not a nought. Twelve checkable rules measured from packages/board and greatcto.systems, not designed for this file. Use when building or extending any great_cto surface — the board, the site, a report, a share page." when_to_use: | Apply when: - building or extending ANY great_cto surface (board screen, site section, share report) - a new element must sit beside existing ones without re-deciding the system Do NOT apply when: - designing a CLIENT product — this is our identity, not a default. See rule 0. effort: low allowed-tools: Read, Write, Edit, Grep, Glob --- # The instrument panel A committed aesthetic in the sense of [`skills/committed-aesthetic/SKILL.md`](../committed-aesthetic/SKILL.md): every rule below is checkable, and every value was **read out of the source** — `packages/board/public/index.html` and `great_cto-site/styles.css` — rather than chosen to write this document. The subject is an instrument, not a brochure. One person reads it to decide what a machine may do next. Everything below follows from that. ## Rule 0 — this is the CATEGORY default, and calling it ours was wrong The first version of this file opened "this is ours, not a default". Measured against a real corpus on 2026-09-01, that is false, and the correction matters more than anything below it. Refero's top ten styles for a dark technical developer landing describe: near-black canvas (Depot, Warp, Supabase, Trunk, Checkly, Cron, Linear, Eraser), depth from surface shifts or borders **rather than shadows** (Warp, Supabase, Trunk, Linear), and **one green accent used sparingly** (Depot, Warp, Supabase, Trunk). Four of them are described with the words "instrument panel", "command center" or "cockpit". Every one of those is a rule below. This aesthetic is not great_cto's identity — it is what every infrastructure product looks like, and this file codified the modal choice and labelled it a differentiator. A skill that does that produces template work while asserting it does not. **What follows is still correct, and its correctness is functional, not distinctive.** Dark, dense, one accent, tabular numerals and a dash that is not a nought are right for a surface one operator reads all day to decide what a machine may do next. Keep them for the BOARD. Just do not mistake them for a voice. Where the category default costs something is the LANDING, where a visitor who has seen Depot, Warp and Supabase cannot tell us apart. Differentiation there is a brand decision made through `committed-aesthetic`, not a repaint of this file. And for a client product — a dental practice does not want an instrument panel — go through `committed-aesthetic` and choose deliberately. ## The DNA **1. Five surface steps, each about 5% apart, and depth is always a step.** `--bg-page #0a0e0c` → `--bg-card #11161a` → `--bg-muted #161c1f` → `--bg-elevated #1a2025` → `--bg-strong #1e272c`. A raised element takes the next step up. It does not take a shadow. **2. Exactly one accent, and it is mostly not a fill.** `--accent #00d97e` appears as a 1px border, a 3px rail on the active nav item, and a 6% glow. It fills only a badge count and a swatch. Two accents is a different design; adding one is a decision, not a tweak. **3. One shadow in the system carries colour.** Card hover: `0 1px 2px rgba(0,0,0,.4), 0 8px 24px rgba(0,217,126,.06)` — the accent at 6%. Everywhere else depth is rule 1. **4. Two faces, divided by MEANING rather than by taste.** Geist is the voice the surface speaks in — headings, navigation, controls, prose. Geist Mono is *machine truth*: anything a person would select and paste. Ids, agent slugs, paths, money, versions, timestamps, verdict tokens, commands. The test is one question: **would someone copy this?** Measured: 115 mono uses against 9 display. A task title is Geist and its id beside it is Geist Mono — the two faces on one row are the point, not an inconsistency. **5. Numerals are tabular, always.** `font-variant-numeric: tabular-nums` at `letter-spacing: -0.02em`. A figure that changes width as it changes value reads as motion the operator did not cause. **6. A dash is not a nought.** Unmeasured renders as `—` in a lighter weight and `--text3`; a measured zero renders as `0` in the numeral treatment. Every count on every surface carries a third state, and it must be visibly different from zero. This is the house rule the whole product rests on; it is a typographic rule here. **7. Twelve type tokens, never a raw size.** 11 · 12 · 13 · 14 · 15 · 16 · 19 · 22, plus numerics 24 · 30 · 36 · 52, as `--fs-*`. If a size is not on the scale, either the scale is wrong or the element is. **8. Tracking moves one way at each end.** ≥22px → `-0.02em`. 11px uppercase → `+0.10em`. Nothing in between is tracked. **9. Geist Mono never above weight 500.** It is vendored `wght 400 500`; above the axis the browser synthesises a smeared bold. Geist runs 400–700; 500 is the workhorse, 600 is emphasis, 700 exists for badge counts only. **10. Desktop density is deliberate, and does not travel.** Controls are 30–32px, chips 20px — below the 44px touch floor on purpose, because this is a pointer surface for one operator. **A mobile or client surface must not inherit these numbers**; it takes rules 1–9 and its own sizes. **11. One hue per meaning, and colour never carries meaning alone.** Every status colour is paired with a glyph or a word. A ▲/▼/— goes with the green/red/grey, so the row survives a reader who cannot distinguish them. **12. Latin subset, self-hosted, 52 KB.** Two variable faces, `font-display: swap`, no CDN. Cyrillic and anything outside latin falls to the system stack mid-line — a known look, decided for the byte count, not a bug to re-discover. ## What NOT to port | Do not take | Why | Instead | |---|---|---| | The 30–32px control heights, to anything touched by a finger | rule 10 — this is a pointer surface for one operator | 44px minimum, keep rules 1–9 | | `clamp()` fluid type from the site, to the board | a marketing page is read at every width; an instrument at one | fixed steps from rule 7 | | The dark ladder, to a client product | rule 0 — it is our identity | choose through `committed-aesthetic` | | `--max: 1100px`, to board screens | the board's content is rows and cards, not paragraphs | only the Docs reader caps measure, at 72ch | ## The component gallery Rendered, with every measurement on the artboard, in the published board spec — foundations, components, shell, screens, typography and the open findings. Working sources in `.design-spec/`. Read the gallery before adding a component; it is faster than deriving one from the rules and it is what the rules were written from. ## Where the rules came from, and where they are still broken This aesthetic is measured, which means it is also **measured to be imperfect**. `docs/reference/` and the spec's findings artboard carry the open list — spacing and radius are not tokenised (11 raw `gap` values, 11 raw radii), the site carries 46 distinct font sizes against rule 7, and the light theme has three values under the AA floor. A rule this file states and the source violates is a finding, not a licence to violate it further. Related: [`skills/committed-aesthetic/SKILL.md`](../committed-aesthetic/SKILL.md) for the form · [`skills/ui-ux-pro-max/SKILL.md`](../ui-ux-pro-max/SKILL.md) for the catalogue you consult when this does not apply.README.mdupstream ↗
Contents are not inlined in the catalog. Open the upstream file.
Plain-text copy, no login: /skill-bundles/avelikiy-great-cto-skills-aesthetic-instrument.md