Menu
Use when working in a DevFlow project with .devflow/ directory and gate-based step-by-step workflows
The review-first prompt is selected by default. You can switch to a direct command or download a local copy.
Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
A direct command skips the review prompt. Inspect the source before running it.
npx skills add https://github.com/Dqz00116/skill-lib --skill devflowThe command stays on one line. Scroll horizontally to inspect it before copying.
Prefer a local copy? Download the files currently available to SkillsMP.
Showing SKILL.md
Based on SOC occupation classification
| name | devflow |
| description | Use when working in a DevFlow project with .devflow/ directory and gate-based step-by-step workflows |
| version | 2 |
CLI-driven progressive disclosure workflow. Advance one verified step at a time.
DevFlow enforces a disciplined development process where each step must be completed and verified before advancing. It uses TOML workflow definitions, gate-based verification, and a devflow done checkpoint system.
.devflow/workflows/*.toml filesdevflow commands in project docsWhen NOT to use: Project has no .devflow/ directory โ this is a standard project, use normal development.
devflow --help # Verify CLI is installed
If devflow is not found, install first:
pip install agent-devflow # From PyPI
Then start the workflow:
devflow list-workflows # See available workflows
devflow select-workflow MODE-A # Pick one
devflow current
1. devflow current -> Read what to do
2. Execute the step -> Write code, create docs, run tests
3. devflow done -> Check gates -> advance or retry
4. Repeat until "Workflow complete!"
Core rule: Only advance through devflow done. Never skip steps. Never create files for future steps.
| Command | Purpose |
|---|---|
devflow current | Show current step instruction |
devflow done | Check gates and advance |
devflow back | Go back one step |
devflow approve ITEM | Mark item as user-approved |
devflow set KEY VALUE | Set state variable |
devflow list-workflows | List available workflows |
devflow select-workflow ID | Select and start a workflow |
devflow run | Start autonomous Ralph Loop |
Gates block advancement until satisfied:
file_exists:path โ File must existfile_contains:path:content โ File must contain textcommand_success:{test_command} โ Command exits 0user_approved:ITEM โ Requires devflow approve ITEMstate_set:var โ State variable must be setWhen gates fail, the workflow may route based on failure count:
fails 1-2 -> retry or fallback step
fails 3+ -> escalate to human
Fail count persists across visits (resets only when gates pass).
| Workflow | Steps |
|---|---|
| MODE-A (Feature) | req-create -> req-approve -> brainstorm -> write-plan -> implement-sdd -> code-review -> test-run -> verify -> finish |
| MODE-B (Debug) | debug-root-cause -> debug-pattern -> debug-hypothesis -> debug-fix -> debug-question -> debug-verify -> debug-finish -> (auto -> MODE-A:write-plan) |
Cross-workflow references use WORKFLOW-ID:STEP-ID format.
| # | Law | Severity |
|---|---|---|
| 1 | Read using-superpowers skill first | Rigid |
| 2 | TDD: Test before code | Rigid |
| 3 | Verify before claim | Rigid |
| 4 | Root cause before fix | Strong |
| 5 | Debug -> Repeat full cycle | Strong |
| Mistake | Fix |
|---|---|
Writing code before devflow current | Stop. Run devflow current first |
| Creating files for future steps | Only create what the current step asks for |
Skipping devflow done | All advancement must go through devflow done |
| Ignoring gate failures | Fix the issue, then devflow done again |
Language: {{ project.language }} Stack: {{ project.stack }} Version: {{ project.version }}
{% if constraints.zero_warnings %}- ZERO warnings โ All builds must have zero warnings{% endif %} {% if constraints.zero_mocks %}- ZERO mocks โ Use real instances only in tests{% endif %} {% if constraints.nullable %}- Nullable enabled โ Use nullable reference types{% endif %}
{{ project.name }}/
โโโ .devflow/ # DevFlow configuration
โ โโโ workflows/ # Workflow definitions (TOML)
โ โโโ prompts/ # Reusable prompt files
โ โโโ config.toml # Project config
โ โโโ state.toml # Current state (gitignored)
โโโ {{ paths.src }}/ # Source code
โโโ {{ paths.tests }}/ # Tests
โโโ {{ paths.docs }}/ # Documentation
โ โโโ requirements/ # REQ files
โ โโโ features/ # FEAT files
โ โโโ superpowers/specs/ # Design docs
โ โโโ superpowers/plans/ # Implementation plans
โ โโโ evidence/ # Verification evidence
โ โโโ debug/ # Debug analysis
โ โโโ completion/ # Workflow completion summaries
โโโ SKILL.md # This file
# Build
{{ commands.build }}
# Test
{{ commands.test }}
{{ commands.test_unit }}
{{ commands.test_integration }}
# Lint
{{ commands.lint }}
Generated by DevFlow v2.0
Use when the current Agent LLM cannot process images directly and visual analysis is needed โ bridges images through KimiCode CLI print mode to a multimodal Kimi model for text description
Use when building HUDs, menus, inventory screens, settings panels, or any widget-based interface in Unreal Engine 5. Also use when connecting C++ logic to UMG Blueprint visuals, handling gamepad or keyboard focus navigation, managing UI state, creating widget animations, or troubleshooting UMG performance issues like frame drops, hitches, or widget memory leaks.
Use when contributing new skills to the skill-lib repository, installing skills locally, or verifying skill compliance with repository standards