Adds the experiment-spec skill to the shared skills repo. This is the research analogue of feature-spec — same discipline (falsifiable hypothesis, quantitative criteria, explicit out-of-scope, null result protocol), adapted vocabulary for scientific/ML experiments.
Why now
The jepa-fx-risk project is the first research project in the stack. feature-spec is designed around product features and user stories. Research experiments need: hypothesis framing, baseline comparison, null result protocol, training cutoff discipline. These don't map cleanly onto feature-spec.
Key design decisions
Iron Laws mirror feature-spec (quantitative criteria, mandatory out-of-scope) but add: baseline is mandatory, null result protocol is mandatory, training cutoff is sacred
Brain MCP integration: brain_query wing=X hall=decisions + hall=failures at spec start; brain_write to hypotheses/ after approval
Cross-references to feature-spec (for component implementation within a phase), grill-me (stress-test before running), tdd (criteria → tests), session-retrospective (after phase)
Worked example uses Phase 0 SSL feasibility spec from jepa-fx-risk — concrete and immediately useful
Relates to
mathias/jepa-fx-risk PR #1 — first consumer of this skill
## What this does
Adds the `experiment-spec` skill to the shared skills repo. This is the research analogue of `feature-spec` — same discipline (falsifiable hypothesis, quantitative criteria, explicit out-of-scope, null result protocol), adapted vocabulary for scientific/ML experiments.
## Why now
The `jepa-fx-risk` project is the first research project in the stack. `feature-spec` is designed around product features and user stories. Research experiments need: hypothesis framing, baseline comparison, null result protocol, training cutoff discipline. These don't map cleanly onto `feature-spec`.
## Key design decisions
- Iron Laws mirror `feature-spec` (quantitative criteria, mandatory out-of-scope) but add: **baseline is mandatory**, **null result protocol is mandatory**, **training cutoff is sacred**
- Brain MCP integration: `brain_query wing=X hall=decisions` + `hall=failures` at spec start; `brain_write` to `hypotheses/` after approval
- Cross-references to `feature-spec` (for component implementation within a phase), `grill-me` (stress-test before running), `tdd` (criteria → tests), `session-retrospective` (after phase)
- Worked example uses Phase 0 SSL feasibility spec from `jepa-fx-risk` — concrete and immediately useful
## Relates to
- `mathias/jepa-fx-risk` PR #1 — first consumer of this skill
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
What this does
Adds the
experiment-specskill to the shared skills repo. This is the research analogue offeature-spec— same discipline (falsifiable hypothesis, quantitative criteria, explicit out-of-scope, null result protocol), adapted vocabulary for scientific/ML experiments.Why now
The
jepa-fx-riskproject is the first research project in the stack.feature-specis designed around product features and user stories. Research experiments need: hypothesis framing, baseline comparison, null result protocol, training cutoff discipline. These don't map cleanly ontofeature-spec.Key design decisions
feature-spec(quantitative criteria, mandatory out-of-scope) but add: baseline is mandatory, null result protocol is mandatory, training cutoff is sacredbrain_query wing=X hall=decisions+hall=failuresat spec start;brain_writetohypotheses/after approvalfeature-spec(for component implementation within a phase),grill-me(stress-test before running),tdd(criteria → tests),session-retrospective(after phase)jepa-fx-risk— concrete and immediately usefulRelates to
mathias/jepa-fx-riskPR #1 — first consumer of this skill