skills/convex-feature-spec/SKILL.md
Generate a complete Convex-first feature specification for a repo, including data model, API surface, rollout, and verification. Use when the user wants a new feature plan or architecture spec centered on Convex contracts. Do not use for audits of the existing implementation; use convex-audit for that.
npx skillsauth add bjornmelin/dev-skills convex-feature-specInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Use this skill for green-field or breaking-change-tolerant feature planning where the output is a complete implementation spec.
AGENTS.md./home/bjorn/.codex/skill-support/bin/convex-scan inventory --cwd <repo> --out <json> to ground the current backend surface.references/feature-spec.md.references/components.md if the feature may use existing Convex components or reusable backend patterns.references/rollout-and-migration.md before finalizing any spec that changes schema, auth, or rollout order.development
Pre-PR multi-model review, parallel opus and codex exec adversarial lanes, then adversarial verification of merged findings. Read-only. Use before shipping nontrivial diffs.
tools
Independent gpt-5.6 diff review via the Codex CLI, normal or steerable adversarial with JSON findings. Use before shipping nontrivial changes.
development
Delegate implementation, investigation, or bulk work to gpt-5.6 codex via pinned codex exec. Use for clear-spec builds, migrations, debugging, or any task MODELS.md routes to codex.
development
Adversarial pre-mortem: imagine the plan failed, work backwards to surface risky assumptions + irreversible bets, then harden them. Proactively offer it (after the current request; confirm first) before a hard-to-reverse or one-way-door call (API, schema, framework, a hire), an all-upside plan, or unvalidated assumptions. Also on request.