autonomous-workflow

Proposal-first development workflow with commit hygiene and decision authority rules. Enforces: propose before modifying, atomic commits, no force flags, warnings-as-errors. Use for any project where AI agents are primary developers and need guardrails.

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "autonomous-workflow" with this command: npx skills add developerinlondon/agent-skills/developerinlondon-agent-skills-autonomous-workflow

Autonomous Workflow

Proposal-First (CRITICAL)

NEVER create or modify files without explicit approval. Always:

  1. PROPOSE the change (what, why, which files)
  2. WAIT for approval
  3. IMPLEMENT only after approval

Exceptions: bug fixes in already-approved work, read-only research, formatting.

Decision Authority (for approved work)

  • Fix bugs, warnings, missing error handling, broken imports: proceed without asking
  • Add missing tests, fix linting issues, update outdated deps: proceed without asking
  • Change architecture, add new infrastructure, switch libraries: ASK first
  • Delete or significantly restructure existing code: ASK first

After Every Change

  • Run the relevant test suite
  • Run the linter/type checker
  • Fix ALL warnings, not just errors
  • Run the project's formatter on changed files

Unused Variables

  • NEVER prefix unused variables with underscore (_var) to silence linters
  • Either USE the variable or REMOVE it entirely
  • If a function parameter is required by an interface but unused, restructure to avoid it
  • This applies to all languages: TypeScript, Rust, Python

Commit Hygiene

  • Never use --force, --no-verify, HUSKY=0 without explicit permission
  • Never commit .env files, credentials, or secrets
  • Atomic commits: one logical change per commit
  • Never add Co-authored-by, Ultraworked with, or any AI agent attribution to commits, PRs/MRs, comments, or changelogs. Keep commit messages clean and focused on the change itself.

Fresh Context for Large Work

Before starting large implementations (multi-phase plans, migrations, new stack deployments):

  • Commit and push all preparatory work (plans, config updates)
  • Start a fresh session / compact context to maximize available context window
  • Reference the plan file for implementation details rather than relying on conversation history

Continuous Config Improvement

Agent instructions are living documents. When you discover something that should be codified -- a new pattern, a gotcha, a convention, a lesson learned -- PROPOSE updating the relevant config file:

  1. What to codify: Recurring mistakes, new conventions, environment-specific gotchas, workflow patterns that should be standardized
  2. Always propose first: Never silently update config files. Describe what you learned and why it should be codified. Wait for approval.

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Coding

gitops-master

No summary provided by upstream source.

Repository SourceNeeds Review
Coding

documentation

No summary provided by upstream source.

Repository SourceNeeds Review
Coding

code-quality

No summary provided by upstream source.

Repository SourceNeeds Review
Coding

Planning with files

Implements Manus-style file-based planning to organize and track progress on complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when aske...

Registry SourceRecently Updated
8.4K22Profile unavailable