mirror of
https://github.com/uditgoenka/autoresearch.git
synced 2026-09-14 20:07:09 +08:00
uditgoenka
6c5abafad1
Align release metadata, capability-scoped support, installation guidance, hook boundaries, maintainer documentation, changelog ownership, and the PR-first release procedure with the stabilized distributions. Constraint: Canonical and Claude surfaces use 2.2.2 while the Codex manifest retains 2.2.2-codex.0. Rejected: Maintain two current changelogs | duplicate release authority drifts. Rejected: Publish before the Windows matrix passes | violates the accepted release state machine. Confidence: high Scope-risk: moderate Directive: Keep generated skill versions sourced from the canonical skill and preserve immutable release tags. Tested: hooks 228/228; orchestrator 195/195; regression 65/65; maintenance 50/50; transform; shell syntax; link/path sweep; diff check Not-tested: GitHub Windows runner remains blocked pending explicit approval for a fresh gate attempt
Everything you need to master autonomous iteration — from first run to advanced multi-command chains. Each guide is self-contained with examples, flags, chains, and tips.
Quick Start
npx skills add uditgoenka/autoresearch
/autoresearch
Guide Index
| Guide | Description |
|---|---|
| Getting Started | Installation, first run, core concepts |
| /autoresearch — Orchestrator | Autonomous orchestrator — type a plain-language goal, the system selects and loops the pipeline |
| /autoresearch | Core autonomous loop — modify, verify, keep/discard, repeat |
| /autoresearch:plan | One-shot wizard — Goal → Scope, Metric, Verify |
| /autoresearch:debug | Autonomous bug-hunting with scientific method |
| /autoresearch:fix | Error crusher — tests, types, lint, build |
| /autoresearch:security | STRIDE + OWASP + red-team security audit |
| /autoresearch:ship | 8-phase shipping workflow |
| /autoresearch:scenario | Scenario explorer — 12 dimensions |
| /autoresearch:predict | 5 expert personas debate before you act |
| /autoresearch:learn | Autonomous documentation engine |
| /autoresearch:reason | Adversarial refinement with blind judges |
| /autoresearch:probe | 8 personas interrogate requirements to saturation |
| /autoresearch:improve | Research ICP challenges, discover improvements, generate PRDs |
| /autoresearch:evals | Analyze results TSV — trends, plateaus, checkpoints |
| /autoresearch:regression | Stability gate — baseline diff, STABLE/UNSTABLE verdict before you push |
| Chains & Combinations | Multi-command pipelines with all 14 commands |
| Examples by Domain | Real-world examples: software, sales, marketing, DevOps, ML, HR |
| Advanced Patterns | Guards, MCP, CI/CD, evals checkpoints, transform.sh |
| Hooks Reference | 9 auto-firing hooks: safety gates, context injection, notifications |
| Scenario Guides | Real-world scenario walkthroughs |
Quick Decision Guide
| I want to... | Use |
|---|---|
| Give a plain-language goal, let it self-orchestrate | bare /autoresearch <goal> |
| Improve test coverage / reduce bundle size / any metric | /autoresearch |
| Don't know what metric to use | /autoresearch:plan |
| Requirements are unclear — surface hidden constraints | /autoresearch:probe |
| Run a security audit | /autoresearch:security |
| Ship a PR / deployment / release | /autoresearch:ship |
| Hunt all bugs in a codebase | /autoresearch:debug |
| Fix all errors (tests, types, lint) | /autoresearch:fix |
| Debug then auto-fix | /autoresearch:debug --fix |
| Check if something is ready to ship | /autoresearch:ship --checklist-only |
| Explore edge cases for a feature | /autoresearch:scenario |
| Generate test scenarios | /autoresearch:scenario --format test-scenarios |
| Get expert opinions before starting | /autoresearch:predict |
| Debate an architecture decision | /autoresearch:reason --domain software |
| Generate docs for a new codebase | /autoresearch:learn --mode init |
| Update existing docs after changes | /autoresearch:learn --mode update |
| Discover what to build next for your ICP | /autoresearch:improve |
| Analyze loop results, detect plateaus | /autoresearch:evals |
| Verify a change is safe to push (catch regressions) | /autoresearch:regression |
| Gate, auto-fix, then ship in one chain | /autoresearch:regression --predict --evals --fix --ship |
| Optimize without breaking existing tests | /autoresearch with Guard: npm test |
| Bound any looping command | Add Iterations: N inline |
Built by Udit Goenka | GitHub | Follow @iuditg