architect

Files (4)

• SKILL.md
• design-red-flags.md · references/
• rationale-template.md · references/
• runner-prompt.md · references/

SKILL.md (first lines)

# Architect

Design before implementing. Sketch types, function signatures, class shapes, and module boundaries with `not implemented` bodies and pseudocode. Synthesize across multiple model perspectives, then fill in code against the chosen sketch. If implementation proves the sketch wrong, throw it out and redesign.

## Start

Open a todolist with one entry per phase before starting. If no task-list tool is exposed, keep the same phase list in the response and disclose that limit.

1. Ground
2. Sketch
3. Agree
4. Implement
5. Scrap

## Session capabilities and authorization

Read [host capabilities](../../references/host-capabilities.md), [model roles](../../references/model-roles.md) and the [assignment contract](../../references/orchestration-contract.md). Use only observed exposed tools within user authorization. Read and follow each required skill in full. If direct invocation is unavailable, disclose that limit and execute its complete workflow inline as reduced capability. A missing required skill remains blocked. Record worker identities, requested and observed selections, rejections, result artifacts and limits.

Independent exploration requires authorized workers with observed spawn and result inspection. Without workers, disclose reduced capability and produce at least two sequential, structurally distinct alternatives using the complete arena workflow and runner discipline. Sequential alternatives are not independent model perspectives. Unverified or identical observed models do not establish model diversity. Denied source reads block grounding; denied writes leave a read-only design and an explicit implementation block.

## Phase A: Ground the problem

Build a real mental model of every system the new code touches. Run the **how** skill over the relevant subsystems.

Naming a file isn't grounding. Produce the traced model `how` prescribes. If the design redefines ownership or layering, also run the **why** skill on the existing shape so the rationale becomes a constraint, not a guess.

Skip Phase A only when the work is genuinely greenfield with no surrounding system to integrate.

## Phase B: Sketch

Run the **arena** skill with the design-sketch task and the Phase A grounding artifacts. Pass `references/runner-prompt.md` as each runner's prompt. Each candidate produces a design package shaped per `references/rationale-template.md`.

Take runner preferences from an available user-supplied `architect runners` configuration, in place of arena runner preferences. When no architect runner preferences are supplied, request inherited selection per the model-role contract. Preserve the goal of distinct model perspectives when supported and verified; inheritance does not establish diversity. Resolve aliases and rejected entries through the complete **arena** Phase A rules and current model-role contract. Select explicit models only when the exposed operation supports them; otherwise disclose inherited selection and unverified diversity. If an exact selection is required but unavailable, block that selection instead of silently replacing it.

Design it twice. Require at least two structurally distinct candidates before synthesis, even when the first looks sufficient. This is the **exhaust-the-design-space** principle skill made concrete. Whole-shape alternatives, not point fixes inside one shape.

Screen every candidate against [`references/design-red-flags.md`](references/design-red-flags.md) before synthesis. Assume the next contributor is an agent that sees only the files it opened, copies the nearest example, and takes the shortest path that compiles. Prefer the design where a change that looks right from one file is right for the whole repo.

Compare viable candidates on interface depth. Prefer the design that hides more complexity behind a smaller, simpler public surface. A rich interface can keep call chains short by concentrating capability instead of scattering it across layers.

Arena returns one synthesized design package. The synthesis decision populates the rationale's "Synthesis decision" section.

## Phase C: Agree (opt-in)

Default: proceed directly to implementation with the synthesized design when implementation is already authorized. No additional human checkpoint. Design-only scope does not authorize implementation.

Opt in to a checkpoint when the invoker explicitly asks: "/architect with checkpoint," "stop and show me before implementing," or similar. Then surface the synthesized design and pause for sign-off.

With explicit commit authorization, the synthesis can ship as its own commit either way, as the "scaffold first" mode of the **foundational-thinking** principle skill. Planned and scoped breakage during fill-in is fine, per the **outcome-oriented-execution** principle skill. For adversarial pressure on the design before implementing, run the **interrogate** skill on the synthesized sketch.

If the human pushes back on the shape (in a checkpoint or after the fact), treat that as Phase A evidence. Re-ground and re-run Phase B before writing more code.

## Phase D: Implement against the sketch

Replace `not implemented` bodies with code, pseudocode with logic. The synthesized sketch is the contract.

Deviations from the sketch are signal worth surfacing, not friction to absorb silently. If a function needs a parameter the sketch didn't anticipate, ask whether the sketch was wrong, the requirement was missed, or the implementation is overreaching.

## Phase E: Scrap when the architecture is wrong

If implementation keeps producing friction the sketch can't absorb, throw the sketch out. Don't bolt fixes onto a wrong design, per the **redesign-from-first-principles** and **fix-root-causes** principle skills.

The signal is a *pattern*, not single instances. Tells:

- The same shape of workaround appearing repeatedly across unrelated code.
- Multiple unrelated edge cases that all need special-case branches.
- Types that need escape hatches (`any`, casts, optional fields always set in practice) to compile.
- The "we need a lock" reflex when the sketch said the state wasn't shared.
- Callers having to know the abstraction's internal rules to use it.
- Two or more independent Phase D deviations of the same shape across the implementation.

Use judgment. A few edge cases don't condemn an architecture. Some problems are legitimately complex. Complexity in the data is not complexity in the design.

When you scrap:

1. Re-run the **how** skill over what's been built.
2. Redesign as if the new constraints had been day-one assumptions, per redesign-from-first-principles.
3. Subtract before adding, per the **subtract-before-you-add** principle skill. The new sketch should be smaller than the old one before it grows.
4. Return to Phase B and re-run arena.

## Outputs

The caller's usage is written first and the type sketch derived from it. One file with new types and signatures for small changes. Module map plus type definitions for larger work. The rationale ships alongside, shaped per `references/rationale-template.md`, including the usage sketch and the synthesis decision.

Apply [unslop](../unslop/SKILL.md) to generated rationale and reports without changing facts or principle meanings.

From yabasha/pstack-openai, MIT.

More from yabasha/pstack-openai