burtenshaw/normies/normies-workflow
Claude Code and agent skill by burtenshaw/normies
- community
Checking that the SKILL.md file is still in the repository.
Orchestrate Docker-isolated, branch-based multi-agent git workflows with normies. Use for parallel edits, batched tasks, retries, and explicit review/integration gates. Prefer this over ad-hoc shell loops for multi-step coordination; skip for trivial one-file edits that do not need orchestration.
Install
npx vskill@latest install burtenshaw/normies/normies-workflowSKILL.md
Normies Workflow
When To Use
- Requests include multi-agent orchestration, parallel edits, batched fixes, or branch-isolated tasks.
- Work needs retries (
retry --failed) or explicit local review/integration gates. - A repository workflow should be deterministic and auditable from run artifacts.
When Not To Use
- A trivial single-file edit that does not need orchestration.
- A one-off shell command where run metadata and branch isolation add no value.
Run Workflow
- Confirm prerequisites.
Check normies --help. Run normies doctor --repo <repo>.
- Build a spec.
Use normies init for a guided wizard (minimal or baseline template). Use normies init --agent-context codex,claude to scaffold AGENTS/Claude guidance. Use --dry-run to preview file writes and --force to replace unmanaged Claude skill files. Use normies make-spec for fast, valid JSON specs. Read references/spec-guide.md for full field details and patterns.
- Execute the pipeline.
Run normies run --repo <repo> --spec <spec> --jobs <N>. Run normies retry --run-id <run_id> --failed --jobs <N> if any agents failed. Run normies review --latest (or --run-id <run_id>). Run normies integrate --latest (or --run-id <run_id>). Use the printed push command from integrate output to push manually.
- Triage failures.
Run normies status --latest. Run normies logs --latest --list-agents. Run normies logs --latest --agent <agent_name> --tail 200. Run normies logs --latest --agent <agent_name> --follow for live logs. Inspect .orchestrator/runs/<run_id>/run.json for full per-agent state.
- Clean up worktrees after completion.
Run normies cleanup --latest. Add --remove-run-dir when you also want to remove run metadata and artifacts.
Execution Defaults
- Keep
needs_networkdisabled unless the task requires network. - Keep
auto_commitenabled unless explicit manual commit behavior is needed. - Keep per-agent commands idempotent and non-interactive.
- Keep review checks explicit in
review.required_checks. - Use
--jsonwhen output is consumed by scripts/automation.
Status Interpretation
- Treat
failedas execution failure (container/command failed). - Treat
blockedas unresolved workflow state (for example dirty worktree withauto_commit: false). - Treat
no_changeas valid no-op. - Treat
okas successful output ready for review/integration.
Resources
references/spec-guide.md: Review spec schema, command sequence, and troubleshooting tips.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/normies-workflow/SKILL.md
Popularity
- 7-day trend score
- 5
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/burtenshaw/normies/normies-workflow)