development-flow-loop
Structured software delivery lifecycle for coding tasks that should move from planning to production with repeated quality gates. Use when building features, refactors, integrations, automations, or systems work where the expected flow is Plan, Architect, Evaluate, Implement, Test, Fix, Test, Improve, Test, Fix or Launch, Launch.
Best use case
development-flow-loop is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Structured software delivery lifecycle for coding tasks that should move from planning to production with repeated quality gates. Use when building features, refactors, integrations, automations, or systems work where the expected flow is Plan, Architect, Evaluate, Implement, Test, Fix, Test, Improve, Test, Fix or Launch, Launch.
Teams using development-flow-loop should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/development-flow-loop/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How development-flow-loop Compares
| Feature / Agent | development-flow-loop | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Structured software delivery lifecycle for coding tasks that should move from planning to production with repeated quality gates. Use when building features, refactors, integrations, automations, or systems work where the expected flow is Plan, Architect, Evaluate, Implement, Test, Fix, Test, Improve, Test, Fix or Launch, Launch.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
Cursor vs Codex for AI Workflows
Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.
SKILL.md Source
# Development Flow Loop ## Overview Follow this exact execution loop for development work. Advance only when each stage gate is satisfied. ## Lifecycle 1. Plan - Define objective, constraints, dependencies, risks, and success criteria. - Output: concise plan with explicit deliverables. 2. Architect - Choose structure, interfaces, data flow, and failure boundaries. - Output: implementation shape and file ownership. 3. Evaluate - Critique the design before coding: complexity, maintainability, testability, cost, and safety. - Output: go/no-go with concrete adjustments. 4. Implement - Ship the minimum correct version first. - Keep changes scoped; avoid unrelated edits. 5. Test - Run targeted tests first, then broader checks if needed. - Output: pass/fail evidence. 6. Fix - Resolve failures from step 5 with minimal blast radius. 7. Test - Re-run relevant tests until stable. 8. Improve - Upgrade quality after stability: readability, performance, docs, ergonomics, observability. 9. Test - Validate improvements did not regress behavior. 10. Fix or Launch Decision - If red or risky: fix and return to Test. - If green and acceptable risk: prepare launch. 11. Launch - Publish/deploy/release with verification and rollback awareness. - Output: release confirmation and post-launch check result. ## Operating Rules - Prefer small increments and frequent validation over large untested changes. - Keep a clear audit trail: what changed, why, what proved it works. - If blocked, reroute quickly, then merge best parts back into one path. - Treat this flow as iterative: repeat `Fix -> Test -> Improve -> Test` as needed.
Related Skills
scbe-shopify-money-flow
Execute revenue-focused Shopify operations using SCBE and HYDRA command lanes with deterministic evidence, cross-talk dispatch, and workflow tuning. Use when the goal is to improve Shopify conversion, publish or refresh digital offers, coordinate monetization agents, or run pre-launch smoke checks before live store actions.
scbe-internet-workflow-synthesis
Synthesize and operate SCBE end-to-end internet workflows by discovering local and GitHub architecture templates, generating a baseline web pipeline profile, running ingestion and governance scans, and tuning system variables after the first run. Use when users ask to build, repair, or optimize internet workflow pipelines, workflow architecture maps, n8n or agent orchestration flows, or post-baseline threshold and concurrency tuning.
scbe-gh-powershell-workflow
Manage GitHub workflows and SCBE-AETHERMOORE repository operations from PowerShell 7 preview. Use for authenticated gh CLI actions, PR and branch workflows, CI triage, and SCBE code-aware repository inspections.
scbe-docker-workflow
Coordinate SCBE Docker workflows from build to runtime. Use for SCBE container commands, docker-compose service startup, health checks, and troubleshooting of image/build failures, port conflicts, and container startup issues in SCBE repos.
scbe-claude-crosstalk-workflow
Use when two AI lanes (Codex and Claude) work in parallel and need deterministic handoff packets with session IDs, lane-bus appends, and repairable delivery checks.
polyhedral-workflow-mesh
Coordinate sub-agent communication, relay workflows, n8n-style automations, triggers, and cross-surface handoffs as one governed mesh. Use when a goal spans multiple agents, browser and terminal surfaces, automation hooks, or periodic and aperiodic work loops that need packets, scoreboards, relays, and proof-backed checkpoints instead of loose AI-to-AI chat.
novel-editor-flow
Assess fiction manuscripts and run a staged developmental-to-publication edit flow. Use when reading a novel draft or compiled manuscript to diagnose scene thinness, pacing, subtext, foreshadowing, emotional payoff, relationship arcs, or publication readiness, especially when turning a PDF or rough draft into an edited source, review packet, EPUB, and print-ready files.
hf-publish-workflow
Automate Hugging Face model/dataset/space publishing from PowerShell with one-time auth, README card generation, `hf upload` commands, and optional `--create-pr` review flow. Use when users ask to log in to Hugging Face CLI, publish artifacts, add or update model/dataset/space cards, wire a reusable profile publish function (for example `scbe-hf-publish`), or troubleshoot common `hf` command usage.
scbe-training-pair-authoring
Create prompt and response and metadata training pairs from SCBE documents, repair traces, terminal sessions, and operational workflows using the repository's canonical dataset contract and provenance rules.
scbe-spin-conversation-engine
Generate SFT training data via radial matrix conversation pivots with D&D-style combat research mode. Produces diverse, cost-effective training pairs with Sacred Tongue encoding, golden spiral problem distribution, and harmonic re-attunement.
scbe-research-training-bridge
Stage arXiv evidence and Obsidian markdown into source-grounded Hugging Face training bundles for research, review, and later SFT runs.
scbe-document-management
Consolidate overlapping docs, classify files by authority, and keep SCBE repo documents aligned with runtime truth. Use when the repo has drift between canonical docs, public docs, proposal notes, research branches, and generated evidence.