feat(experiments): add draft launchdarkly-experiment-hypothesis-builder skill

[mabramowitz-pixel]

Summary

Adds a draft skill, launchdarkly-experiment-hypothesis-builder, that coaches a user from a rough idea to a strong, testable experiment hypothesis (if/then/because structure, single-variable isolation, falsifiability, grounding), then emits a pre-resolved handoff payload that launchdarkly-experiment-setup consumes to scaffold the experiment with minimal re-prompting.

Includes a references/diagnostic-tree.md that diagnoses weak hypotheses by flaw type (vague intervention, no measurable metric, missing mechanism, not falsifiable, multi-variable, ungrounded, metric↔outcome mismatch) and walks each to a corrected hypothesis → flag → variations → metrics → guardrails → config summary.

Marked draft (v0.1.0, status: draft) for review — the handoff contract may still change. Scope is the new skill only; a follow-up could add the reverse pointer from launchdarkly-experiment-setup (route weak hypotheses here first).

Testing approaches

• python3 scripts/validate_skills.py → 42 skills validate successfully.
• Regenerated skills.json via python3 scripts/generate_catalog.py (new entry included).
• Manually exercised the skill against sample weak hypotheses to confirm the diagnose → correct → config-summary flow and the handoff payload shape map onto launchdarkly-experiment-setup's create-experiment steps.

Feature flags

N/A

🤖 Generated with Claude Code

[mabramowitz-pixel]

Superseded by #95 — reopened as a same-repo branch so the Skill Evals get the ANTHROPIC_API_KEY secret (fork PRs don't). Same commit/content.