prekuter/dryforge / codex/plugin/skills/ready
ready
VerifiedUnderstand what you mean before anything is built. Takes anything — a one-line idea, notes, a spec, or a mix — reads the project first, asks only what is yours to decide, and writes your intent down for you to approve. Use when the user invokes the `ready` skill. Requires git.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 27.0 KB |
| agents/openai.yaml | config | 233 B |
| references/3-doc-gate.md | markdown | 6.0 KB |
| references/decompose.md | markdown | 11.2 KB |
| references/dependency-calc.md | markdown | 6.1 KB |
| references/elicitation.md | markdown | 18.2 KB |
| references/example-3doc.md | markdown | 7.8 KB |
| references/first-cycle-review.md | markdown | 3.1 KB |
| references/foundation-format.md | markdown | 5.3 KB |
| references/gap-analysis.md | markdown | 4.7 KB |
| references/grounds-gate.md | markdown | 3.6 KB |
| references/intent-completeness.md | markdown | 6.3 KB |
| references/intent-review.md | markdown | 4.0 KB |
| references/output-format.md | markdown | 10.0 KB |
| references/project-design-domain.md | markdown | 4.4 KB |
| references/project-design-technical.md | markdown | 4.2 KB |
| references/project-scoping.md | markdown | 3.5 KB |
| references/review-fidelity.md | markdown | 4.6 KB |
references/first-cycle-review.md
View on GitHub# first-cycle-review.md — the foundation-sufficiency rubric (shared)
The rubric for one question: *is the spec + Project Foundation deep enough to be the foundation of the
whole project?* Adversarial stance — find the holes, don't bless the work. Used **only in the first
cycle**, in **two places** that share this one rubric:
- **ELICIT (generative)** — the first-cycle loop (`elicitation.md`) presses against this floor *during
dialogue*, while the user is present to fill a gap.
- **3-doc-gate (independent)** — the foundation-sufficiency pass (`3-doc-gate.md`) judges the
*written* Foundation against this same rubric, from a fresh session that never saw the dialogue
(the A=A backstop).
Both use the failure modes and floor below; they differ only in *when* and *with what session access*.
**Floor, not ceiling.** The failure modes and floor are the floor; how hard you press each is
risk-proportional judgment.
## Failure modes to hunt
- **Domain too shallow** — entity *names* present, but rules / invariants / edge-case dispositions
missing. A concept without its four facts (what it is / does / cannot do / how it ends) is a name,
not a model.
- **Domain too narrow** — a core feature/entity is missing — the trace of closing without asking the
user "are there others?" (the breadth guard was skipped).
- **Technical decision left open** — a "decide later" / "TBD" survives. An open load-bearing technical
question is a gap (the executor will fill it arbitrarily).
- **Security generality** — "security considered" with no project-specific policy (auth approach,
authorization model, audit scope).
- **Scoping mismatch** — the design is heavier or lighter than the project's confirmed character.
- **Vague modifiers remain** — "appropriately," "if needed," "as suitable" still present.
## Floor
- Every domain concept meets `project-design-domain.md`'s depth floor.
- Every technical decision is closed by user confirmation (no open question).
- **Zero** vague modifiers.
- Design depth is consistent with the CALIBRATE character profile.
## On a miss — reopen the foundation gap, don't self-fill
A finding here is one of two kinds:
- **Internally resolvable** (a vague modifier you can concretize from what's already on the record, an
altitude slip) → fix it.
- **A gap only the user can fill** (a missing domain rule, an unsettled technical decision, a security
policy) → **do not auto-fill it.** Auto-filling a foundation gap bakes a guess into the whole
project.
- If found by ELICIT (during dialogue): **reopen the foundation gap in the loop** — add it to the
open-set and ask, in its mode (domain = extract, technical = present).
- If found by the 3-doc-gate (after the docs are written): the orchestrator relays it to the user
and reopens ELICIT for that gap only → updates SPEC/Foundation (`3-doc-gate.md`).
## Universality guard
Stack-agnostic. The rubric checks depth, breadth, and decision-closure — never conformance to a stack.
What counts as a domain rule or a technical decision is whatever this project is, judged at runtime.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |