Read-set manifest: devrites-engine context --skills-root .devin/skills <slug> --skill rite-pressure-test (no workspace: --out <path>) bundles every file named below into one deduplicated read.
/rite-pressure-test: diverge then converge
Use when the idea—not only requirements—is rough. Compare directions before
/rite-spec; never implement. Read core.md
first and write only workspace/ticket artifacts.
Diverge (widen)
- Search
decisions.md, accepted ADRs, and relevant archives for rejected directions;
revive one only with evidence that answers its recorded reason, citing both.
- Generate 3-5 different shapes, including obvious, smaller, and different-boundary/data/
flow options, plus a do-nothing baseline (cost of not building) that every option
must beat. Use named lenses— inversion, constraint removal, audience shift, 10×, or
expert practice—without padding. Borrow analogous mechanisms, not branding.
- For each, name concrete entities/flows/surfaces, optimization, rough cost, and main risk.
Converge (commit)
- Weigh options against the goal, constraints, and existing codebase conventions.
- Prefer felt pain over nice-to-have. Rank differentiation: new capability > 10× gain >
new audience > new context > better UX > cheaper; do not dress a vitamin as a painkiller.
- Recommend one, with the reason and the key trade-off accepted. When no option beats
the do-nothing baseline, recommend Kill: record the reason in
decisions.md and
do not route to /rite-spec.
- Note what would change the recommendation (the decision's hinge).
Premise evidence floor
If the hinge is an uncertain material fact, freeze at most three questions for
devrites-evidence-scout. Validate every citation; missing/malformed/unverifiable output is
unavailable, never support. Record claim, support, strongest contrary evidence, and
supported | assumption | refuted. Refutation changes the recommendation; an assumption
advances only when non-decisive with bounded downside. Weak/conflicting decisive evidence
returns Hold with the resolving evidence, never /rite-spec. Persist a Hold before
stopping; a reply-only Hold is lost. In an active workspace (has state.md), append an open
questions.md entry (gate: blocking, the premise and resolving evidence). Otherwise add a
Hold: line (premise + resolving evidence) under Not yet specified in the provisional
slug's investigation-map.md; /rite-spec carries it into questions.md on adoption. Tie-breaker:
see intent-map.md (rite-pressure-test
vs rite-spec). Do not research preferences
or reversible implementation choices.
Boundaries
- This is exploration, not specification. Output a direction, not a finished spec:
/rite-spec writes the spec.
- Don't over-explore: 3-5 options, one pass of convergence. If the user already knows
the direction, skip this and go straight to
/rite-spec. If the effort is too foggy for
one pass, start an investigation map at .devrites/work/<slug>/investigation-map.md
(create the directory; pick a provisional slug /rite-spec can adopt)
with Destination, Decisions so far, Not yet specified, Out of scope, plus one
frontier question per session.
- Ask the user to pick when two options are close and the choice changes the product.
- Name a "Not doing" list: the good options you deliberately cut. It's the highest-value
output of convergence: it hands
/rite-spec its scope boundary. When a cut is
durable, offer to record the reason in the active feature's decisions.md or
a durable ADR rather than a parallel rejection index.
Done: pressure test complete for <goal>.
Changed: workspace only
Evidence: options compared <n>; recommendation <option>; hinge <condition>; premises <supported/assumption/refuted + sources>
Open: <none | unresolved premise and resolving evidence>
Next: <when supported: /rite-spec <feature>; when Hold: none — requires <resolving evidence>; when Kill: none — not building: <reason>>
Record: <investigation-map.md path (incl. provisional Hold) | questions.md id (Hold) | not applicable>
↻ Hygiene: /clear before starting the lifecycle
1---2name: rite-pressure-test-73description: "Pressure-test a rough/vague idea: ideate, explore 3-5 approaches, radically different shapes, diverge then converge on direction before spec. Not for writing spec."4argument-hint: "[rough idea or plan to stress-test]"5metadata:6 source: https://skillmd.com/skills/viktorsbaikers/rite-pressure-test-77---89<!-- loads: {"always":["devrites-lib/reference/standards/core.md","devrites-lib/reference/intent-map.md"],"workspace":["decisions.md","questions.md"]} -->10> Read-set manifest: `devrites-engine context --skills-root .devin/skills <slug> --skill rite-pressure-test` (no workspace: `--out <path>`) bundles every file named below into one deduplicated read.1112# /rite-pressure-test: diverge then converge1314Use when the idea—not only requirements—is rough. Compare directions before15`/rite-spec`; never implement. Read [`core.md`](../devrites-lib/reference/standards/core.md)16first and write only workspace/ticket artifacts.1718## Diverge (widen)1920- Search `decisions.md`, accepted ADRs, and relevant archives for rejected directions;21 revive one only with evidence that answers its recorded reason, citing both.22- Generate 3-5 different shapes, including obvious, smaller, and different-boundary/data/23 flow options, plus a **do-nothing baseline** (cost of not building) that every option24 must beat. Use named lenses— inversion, constraint removal, audience shift, 10×, or25 expert practice—without padding. Borrow analogous mechanisms, not branding.26- For each, name concrete entities/flows/surfaces, optimization, rough cost, and main risk.2728## Converge (commit)2930- Weigh options against the goal, constraints, and existing codebase conventions.31- Prefer felt pain over nice-to-have. Rank differentiation: new capability > 10× gain >32 new audience > new context > better UX > cheaper; do not dress a vitamin as a painkiller.33- Recommend one, with the reason and the key trade-off accepted. When no option beats34 the do-nothing baseline, recommend **Kill**: record the reason in `decisions.md` and35 do not route to `/rite-spec`.36- Note what would change the recommendation (the decision's hinge).3738## Premise evidence floor3940If the hinge is an uncertain material fact, freeze at most three questions for41`devrites-evidence-scout`. Validate every citation; missing/malformed/unverifiable output is42`unavailable`, never support. Record claim, support, strongest contrary evidence, and43`supported | assumption | refuted`. Refutation changes the recommendation; an assumption44advances only when non-decisive with bounded downside. Weak/conflicting decisive evidence45returns **Hold** with the resolving evidence, never `/rite-spec`. Persist a Hold before46stopping; a reply-only Hold is lost. In an active workspace (has `state.md`), append an open47`questions.md` entry (`gate: blocking`, the premise and resolving evidence). Otherwise add a48`Hold:` line (premise + resolving evidence) under `Not yet specified` in the provisional49slug's `investigation-map.md`; `/rite-spec` carries it into `questions.md` on adoption. Tie-breaker:50see [`intent-map.md`](../devrites-lib/reference/intent-map.md) (`rite-pressure-test`51vs `rite-spec`). Do not research preferences52or reversible implementation choices.5354## Boundaries5556- This is exploration, not specification. Output a **direction**, not a finished spec:57 `/rite-spec` writes the spec.58- Don't over-explore: 3-5 options, one pass of convergence. If the user already knows59 the direction, skip this and go straight to `/rite-spec`. If the effort is too foggy for60 one pass, start an investigation map at `.devrites/work/<slug>/investigation-map.md`61 (create the directory; pick a provisional slug `/rite-spec` can adopt)62 with `Destination`, `Decisions so far`, `Not yet specified`, `Out of scope`, plus one63 frontier question per session.64- Ask the user to pick when two options are close and the choice changes the product.65- Name a **"Not doing" list**: the good options you deliberately cut. It's the highest-value66 output of convergence: it hands `/rite-spec` its scope boundary. When a cut is67 durable, offer to record the reason in the active feature's `decisions.md` or68 a durable ADR rather than a parallel rejection index.6970```71Done: pressure test complete for <goal>.72Changed: workspace only73Evidence: options compared <n>; recommendation <option>; hinge <condition>; premises <supported/assumption/refuted + sources>74Open: <none | unresolved premise and resolving evidence>75Next: <when supported: /rite-spec <feature>; when Hold: none — requires <resolving evidence>; when Kill: none — not building: <reason>>76Record: <investigation-map.md path (incl. provisional Hold) | questions.md id (Hold) | not applicable>77↻ Hygiene: /clear before starting the lifecycle78```