Convex feature spec
AgentSkills library: reusable skills for AI coding agents (AI SDK, Codex, LangGraph, Supabase, Docker, Vitest, pytest, Streamlit, Zod).
npx -y skills add BjornMelin/dev-skills --skill convex-feature-specAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
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.
SKILL.md
1.6 KB, as published. Nobody here has run it
Convex Feature Spec
Use this skill for green-field or breaking-change-tolerant feature planning where the output is a complete implementation spec.
Workflow
- Read the repo
AGENTS.md. - Run
/home/bjorn/.codex/skill-support/bin/convex-scan inventory --cwd <repo> --out <json>to ground the current backend surface. - Read
references/feature-spec.md. - Read
references/components.mdif the feature may use existing Convex components or reusable backend patterns. - Read
references/rollout-and-migration.mdbefore finalizing any spec that changes schema, auth, or rollout order. - Research the active APIs before locking any non-trivial design.
- Output an implementation-ready spec with task order, interfaces, risks, and verification.
Use When
- The user asks for a new feature spec, a Convex-first architecture plan, or a complete backend-driven design.
- The repo uses Convex and the planning output must include schema and function contracts.
Do Not Use When
- The task is reviewing or fixing the current implementation.
- The task is just docs alignment or dependency work.
Outputs
- feature objective
- schema and function contract changes
- rollout and migration plan
- ordered implementation and verification steps