prekuter/dryforge / claude/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 | 27.1 KB |
| 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/project-scoping.md
View on GitHub# project-scoping.md — first-cycle CALIBRATE (project character → depth profile)
The calibration step of the first-cycle ELICIT loop (no harness exists yet). Before deepening any
axis, establish the project's **identity, scale, and constraints** — its character — which then sets
the *depth floor* of every foundation axis the loop will close (domain, technical, and beyond). Loaded
and run only in the first cycle. (It is not a separate phase that must finish before the rest — it
seeds the floor; the loop then closes the axes in gap-driven order, see `elicitation.md`.)
**Floor, not ceiling.** This sets the floor and the guardrails; how you reach the user's confirmed
read of the project is your judgment.
## The mechanism — your judgment + user confirmation
Do **not** freeze scope from the user's opening description. A project's real character emerges
through dialogue, and you update your read in real time as it does (it started as "a personal
note-taker" but a workspace/sharing feature appears → re-read it as a collaboration tool). Before the
loop deepens into the foundation axes, present your final read explicitly and get the user to confirm
it.
Flow: **tentative read → dialogue → update → final presentation → user confirmation.**
- Form a tentative read from the opening description.
- Through dialogue, pin the project's purpose, audience, scale, and hard constraints — updating the
read as new character surfaces.
- Before leaving calibration, present: *"This project is [character] at [scale]. I'll take the domain
to [depth] and the technical decisions to [depth]."* — and get confirmation before deepening the
axes.
## Project character controls depth — not a formal grade
Let the project's character *itself* be the context that sets the foundation design's depth. Do
**not** assign a formal tier (L/M/H, small/medium/large as a label). A grade becomes a **ceiling** —
"it's a small project, so design shallow" — which violates floor-not-ceiling. State the character in
prose ("a single-user local tool with no network surface and no multi-user state") and let that
prose carry the depth, so domain depth, technical-design depth, and security depth come out
proportional to what the project actually is.
## YAGNI gate
The calibration read caps the scale of all downstream design. A personal tool that starts producing
enterprise architecture gets caught here. The gate is **not** a unilateral cut: if, while deepening an
axis, you sense a design is heavier than the project's character warrants, surface it with your
reasoning
("this is more infrastructure than a single-user tool needs because ...") and let the user decide —
proceed if they need it, scale down if they agree it's overkill. Never silently shrink scope, and
never silently inflate it.
## Hard constraints
Capture the hard constraints — technical (a platform that must be targeted, a dependency that must
be used or avoided) and business (a deadline, a compliance boundary, a cost limit) — because they
bound every later decision. These are user-held; ask for them, don't assume them.
## Completion bar
Calibration is done when the project's character and the depth direction are **confirmed by the
user**, so the loop can deepen the foundation axes against that floor. An unconfirmed read is not a
basis for design — present and confirm before proceeding.
## Universality guard
Stack-agnostic. Project character, scale, and constraints are described in the project's own terms,
discovered at runtime — no stack is assumed and no fixed catalog of "project types" is imposed.
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 |