Convex Feature Spec
- 5 installs
- 5 repo stars
- Updated August 5, 2026
- bjornmelin/dev-skills
convex-feature-spec is a skill that generates a complete Convex-first feature specification with data model, API surface, and rollout plan.
About
convex-feature-spec generates a complete Convex-first feature specification for a repo, including data model, API surface, rollout, and verification. A developer uses it for green-field or breaking-change-tolerant feature planning where the output is a full implementation spec. It grounds the design in the current backend via convex-scan inventory and outputs schema and function contract changes with a rollout plan.
- Generates a complete Convex-first feature specification including data model and API surface
- Grounds the spec in the current backend surface via convex-scan inventory before designing
- Outputs schema and function contract changes plus a rollout and migration plan
Convex Feature Spec by the numbers
- 5 all-time installs (skills.sh)
- Ranked #3,685 of 4,347 Backend & APIs skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
convex-feature-spec capabilities & compatibility
- Capabilities
- convex feature spec · backend design · api design · schema design
- Use cases
- api development · database · planning
What convex-feature-spec says it does
Use this skill for green-field or breaking-change-tolerant feature planning where the output is a complete implementation spec.
Generate a complete Convex-first feature specification for a repo, including data model, API surface, rollout, and verification.
Output an implementation-ready spec with task order, interfaces, risks, and verification.
npx skills add https://github.com/bjornmelin/dev-skills --skill convex-feature-specAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 5 |
|---|---|
| repo stars | ★ 5 |
| Last updated | August 5, 2026 |
| Repository | bjornmelin/dev-skills ↗ |
What it does
Produce a complete Convex-first feature spec with data model, API surface, rollout, and verification.
Who is it for?
Green-field or breaking-change-tolerant feature planning centered on Convex contracts.
Skip if: Auditing or fixing the existing implementation, which is handled by convex-audit.
When should I use this skill?
The user wants a new feature plan or architecture spec centered on Convex contracts.
What you get
An implementation-ready spec with task order, interfaces, risks, and verification steps.
- feature objective
- schema and function contract changes
- rollout and migration plan
By the numbers
- 7-step spec workflow
Files
Convex Feature Spec
Use this skill for green-field or breaking-change-tolerant feature planning where the output is a complete implementation spec.
Workflow
1. Read the repo AGENTS.md. 2. Run /home/bjorn/.codex/skill-support/bin/convex-scan inventory --cwd <repo> --out <json> to ground the current backend surface. 3. Read references/feature-spec.md. 4. Read references/components.md if the feature may use existing Convex components or reusable backend patterns. 5. Read references/rollout-and-migration.md before finalizing any spec that changes schema, auth, or rollout order. 6. Research the active APIs before locking any non-trivial design. 7. 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
interface:
display_name: "Convex Feature Spec"
short_description: "Write Convex-first feature specs with rollout and verification"
default_prompt: "Use $convex-feature-spec to generate a complete Convex-first feature plan with schema, API, rollout, and verification details."
policy:
allow_implicit_invocation: false
dependencies:
tools:
- type: "mcp"
value: "context7"
description: "Current API and library docs"
- type: "mcp"
value: "exa"
description: "Supplemental current research for edge cases"
Components and Reuse
Before inventing custom infrastructure:
1. check whether the feature can reuse existing Convex components or patterns 2. keep the architecture minimal 3. prefer one canonical path over layered abstractions
Convex Feature Spec
Every spec should include:
1. objective and success criteria 2. schema/index changes 3. function surface and auth model 4. client integration points 5. rollout, migration, and verification order
Do not leave the implementer to invent contracts or sequencing.
Rollout and Migration
When a feature changes schema or live behavior, specify:
1. rollout order 2. data migration/backfill needs 3. rollback safety 4. verification gates after each phase
If the repo is effectively pre-release, say so and simplify the migration path explicitly.
#!/usr/bin/env python3
from __future__ import annotations
import argparse
import json
from pathlib import Path
def main() -> int:
parser = argparse.ArgumentParser(description="Create a minimal feature-spec seed from repo context.")
parser.add_argument("--cwd", default=".")
parser.add_argument("--out", required=True)
args = parser.parse_args()
repo = Path(args.cwd).resolve()
payload = {
"repo_root": str(repo),
"notes": [
"Read README.md, AGENTS.md, and architecture docs before proposing feature scope.",
"Use convex-scan inventory output to keep schema and function changes grounded.",
],
}
Path(args.out).write_text(json.dumps(payload, indent=2) + "\n", encoding="utf-8")
print(args.out)
return 0
if __name__ == "__main__":
raise SystemExit(main())
Related skills
Lark Openapi ExplorerInstantly explore, test, and generate calls against the full Lark (Feishu) OpenAPI surface without leaving their agent workflow.493k
Lark EventConsume real-time events from Lark/Feishu as structured NDJSON streams inside AI agent workflows.387k16kLark Openapi ExplorerWhen an existing Lark/Feishu skill or CLI command cannot fulfill a specific requirement and they need to discover and invoke the exact native OpenAPI endpoint.386k16k
Just ScrapeQuickly search, crawl, extract structured JSON, or monitor web pages without writing custom scraping code.245k41Lark AppsQuery the current visibility and permission scope of a Lark (Feishu) app without writing HTTP client code.235k16k
Design An InterfaceGenerate multiple radically different interface or API designs in parallel before committing to one.188k198kFAQ
When should I not use it?
When reviewing or fixing the current implementation; use convex-audit instead.
What is in the output?
Feature objective, schema and function contract changes, a rollout and migration plan, and ordered implementation and verification steps.