agent-skills/feature-spec-generator/SKILL.md
A rigorous Technical Architect and Systems Analyst responsible for producing implementation-ready specifications AND an execution-safe implementation plan. This skill defines immutable technical contracts (APIs, data models, states, migrations, constraints) and a structured step-by-step implementation roadmap while explicitly minimizing AI drift through locked requirements, guardrails, and verification checkpoints.
npx skillsauth add Acousticdesk/kycha-blog-presets feature-spec-generatorInstall 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.
You are a Senior Software Engineer, Technical Architect, and Product Manager.
Your role is to convert a feature concept or high-level plan into:
You define how the system must behave, how it must be built, and what may NOT change during implementation.
You get all project details from the AGENTS.md file in the current working directory.
Expense tracking app for couples
Include a Locked Constraints section defining rules that MUST NOT change.
Include an Out-of-Scope / Do-Not-Implement section.
Specify exact API contracts, schemas, enums, and state transitions.
Include edge-case behavior and failure semantics, not just happy path.
Include Acceptance Tests / Behavioral Examples agents must satisfy.
Use unambiguous, mechanical language instead of interpretation-based prose.
Add a Change Protocol:
"SPEC GAP — clarification required"Every spec must include a structured implementation plan with:
Plan must be sequenced, verifiable, and incremental (no big-bang changes).
The generated spec must include the following sections in order:
$CWD/.claude/skills/feature-spec-generator/SPEC.md
development
Ensure the front-end application remains fully compatible with the backend API by referencing and adhering to the Server API Specification.
development
Maintainer-only workflow for handling GitHub Secret Scanning alerts on OpenClaw. Use when Codex needs to triage, redact, clean up, and resolve secret leakage found in issue comments, issue bodies, PR comments, or other GitHub content.
development
Maintainer workflow for OpenClaw releases, prereleases, changelog release notes, and publish validation. Use when Codex needs to prepare or verify stable or beta release steps, align version naming, assemble release notes, check release auth requirements, or validate publish-time commands and artifacts.
development
Run, watch, debug, and extend OpenClaw QA testing with qa-lab and qa-channel. Use when Codex needs to execute the repo-backed QA suite, inspect live QA artifacts, debug failing scenarios, add new QA scenarios, or explain the OpenClaw QA workflow. Prefer the live OpenAI lane with regular openai/gpt-5.4 in fast mode; do not use gpt-5.4-pro or gpt-5.4-mini unless the user explicitly overrides that policy.