Generate Claude Code Workflows using Spec Driven Development approach
Spec-driven workflow generator for Claude Code when prompt-chaining dominates AI coding.
Spec Driven Development Workflow
Context clearing between steps cuts costs, but hallucinated 2026 citations hurt trust.
Developers using Claude Code for medium-to-large projects
Aider · Cursor · SweAgent
Repo with claude plugin for spec driven development: https://github.com/sermakarevich/sddw
Spec-driven workflow generator for Claude Code when prompt-chaining dominates AI coding.
This repo actually wires the specfact CLI to a tiny, reproducible codebase so you can import-from-code, generate .specfact bundles, and run enforcement presets with one-liners. The backlog-sync adapter and a deliberately buggy sidecar demo make failure modes easy to exercise, and the README lists exact smoke commands and logs to verify results. Inferred specs will always risk false positives, but the project shows practical artifacts (change_tracking, results logs) rather than theory.
Another spec framework competing with GitHub's spec-kit but as a skill file.
Curated skill collection for spec-driven AI development, competing with other prompt libraries.
Independent critic agent with no access to builder's reasoning catches blind spots.
It extracts focused, executable operations from giant OpenAPI files (the GitHub REST YAML is shown) to shrink context and avoid sidecar adapter sprawl — a pragmatic answer to token bloat and brittle ad-hoc integrations. Useful and concrete: if it actually generates tidy, updateable skill units and runtime hooks it saves a lot of maintenance. That said, the idea competes with existing LangChain/openai-function patterns; the repo will need clear runtime, versioning, and update strategies to feel like more than a nicer converter.