ai-feature-spec
SolidUse when specifying one AI-powered feature end to end, including model choice, prompt and context contracts, output schema, fallbacks, human oversight, UX states, and evaluation.
Install
Quality Score: 85/100
Skill Content
Details
- Author
- peterbamuhigire
- Repository
- peterbamuhigire/chwezi-dev-engine
- Created
- 7 months ago
- Last Updated
- 3 days ago
- Language
- HTML
- License
- MIT
Integrates with
Similar Skills
Semantically similar based on skill content — not just same category
ai-feature-rollout-and-experimentation
Use when planning a controlled AI-feature rollout or experiment in multi-tenant SaaS: tenant/user feature flags, percentage and canary cohorts, holdout metrics, A/B tests of prompts or models, eval and SLO gates, automatic rollback, tenant opt-out and consent, or shadow mode for risky changes.
ai-entitlements-and-feature-gating
Use when defining or enforcing plan-based AI feature access, model tiers, context limits, quotas, tool permissions, tenant overrides, and upgrade behaviour.
feature-spec
Write a lightweight, AI-ready Feature Specification — a ~500-2000 token spec with Overview, EARS acceptance criteria, Design, and Edge Cases that an implementer or coding agent can act on directly. Use when a single feature needs a concise build-ready spec. Anti-trigger; for org-wide architecture use arc42-arch-doc, for a decision record use adr, for a multi-feature product doc use prd.