repo-change-loop
Runs the standard Robota change loop by identifying impact, building affected scope, running targeted verification, and summarizing residual risk. Use when making or reviewing repository changes that should end in an explicit verification result.
Best use case
repo-change-loop is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Runs the standard Robota change loop by identifying impact, building affected scope, running targeted verification, and summarizing residual risk. Use when making or reviewing repository changes that should end in an explicit verification result.
Teams using repo-change-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/repo-change-loop/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How repo-change-loop Compares
| Feature / Agent | repo-change-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?
Runs the standard Robota change loop by identifying impact, building affected scope, running targeted verification, and summarizing residual risk. Use when making or reviewing repository changes that should end in an explicit verification result.
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.
SKILL.md Source
# Repository Change Loop ## Rule Anchor - `.agents/rules/verification.md` > "Build Requirements" - `.agents/rules/verification.md` > "Behavioral Verification Before Push" - `.agents/rules/verification.md` > "Headless CLI Verification Requirement" - `.agents/rules/verification.md` > "Harness Direction" ## Use This Skill When - Modifying code under `packages/*/src/` or `apps/*/src/`. - Changing execution paths, examples, or verification-related behavior. - Reviewing a change and deciding what must be built or verified. ## Preconditions - Identify the changed files. - Identify the affected package or app scope. - Determine whether the change touches execution paths, scenarios, examples, or public contracts. ## Execution Steps 1. Classify the change scope: - code path - type surface - scenario or example behavior - documentation only 2. Determine the affected packages or apps from the changed paths. 3. If `packages/*/src/` changed, run the affected package build immediately. 4. Run the most relevant targeted checks: - package build - targeted tests - targeted lint or typecheck when the change affects contracts or boundaries 5. If the change affects CLI execution, transports, `InteractiveSession`, commands, model-routed tools, permissions, streaming, provider setup, or session persistence, run or add a headless verification path with structured runtime evidence. 6. If the change affects execution behavior, examples, or scenarios, run the relevant verification flow. 7. Do not repeat an already-passing stronger gate with a weaker duplicate. For example, after a final scoped harness verification or release-grade verification, do not manually re-run the same package checks unless files changed again. 8. Skip verification for Git operations that publish no repository content, such as deleting a merged remote feature branch. 9. Stop immediately on strict-policy failures, contract failures, or non-zero verification exits. 10. Summarize: - what was verified - what failed - what was not verified - any residual risks ## Stop Conditions - The affected package does not build. - A targeted test fails. - A scenario or example verification flow fails. - Logs include strict-policy or contract-violation signals that indicate the path is invalid. ## Checklist - [ ] Changed scope is identified before running commands. - [ ] Affected package build is run for package source changes. - [ ] Targeted tests or smoke checks are run for changed behavior. - [ ] CLI/transport/session behavior includes a headless verification path when applicable. - [ ] Scenario or execution verification is run when relevant. - [ ] No already-passing gate is repeated without new file changes. - [ ] Final summary distinguishes verified vs unverified areas. ## Focused Examples ```bash pnpm --filter @robota-sdk/agent-core build pnpm --filter @robota-sdk/agent-core test pnpm --filter @robota-sdk/agent-core lint pnpm --filter @robota-sdk/agent-core exec tsc -p tsconfig.json --noEmit ``` ```bash pnpm build pnpm test pnpm typecheck pnpm lint ``` ## Anti-Patterns - Editing package source and skipping the build step. - Running the full workspace by habit when the affected scope is narrow and known. - Re-running package checks after branch deletion, squash-merge cleanup, or other no-content Git operations. - Running `pnpm typecheck`, `pnpm lint`, and `pnpm test` manually immediately before `pnpm harness:pre-push` when the harness will execute the same final scoped checks. - Treating dependent package typechecks as mandatory for every local push. Use `HARNESS_PRE_PUSH_MODE=full pnpm harness:pre-push` or explicit `pnpm harness:verify -- --base-ref <ref>` when the change risk warrants broad dependent validation. - Reporting success without saying what was actually verified. - Treating documentation reading as equivalent to verification. - Treating TUI-only checks as sufficient for behavior also reachable through headless CLI mode. ## Related Harness Commands - Current: `pnpm harness:pre-push`, `HARNESS_PRE_PUSH_MODE=full pnpm harness:pre-push`, `pnpm harness:verify -- --scope <packages/foo|apps/bar> [--include-scenarios]`, `pnpm build`, `pnpm test`, `pnpm typecheck`, `pnpm lint` - Current review support: `pnpm harness:review -- --scope <packages/foo|apps/bar>`
Related Skills
repo-writing
Applies Robota's repository writing rules for `.design/`, general documentation, and conventional commit messages. Use when editing docs, ADRs, design notes, or preparing commit text.
pnpm-monorepo-build
Provide pnpm monorepo build commands and workflow guidance. Use when running package builds, filtered builds, or discussing build order.
web-design-guidelines
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
vitest-testing-strategy
Defines a practical testing strategy for TypeScript and JavaScript using Vitest across unit, integration, and type-level tests. Use when adding features, refactoring, or preventing regressions with fast feedback loops.
version-management
All packages must have the same version. Use changesets for coordinated version bumps. Never version packages independently.
vercel-react-native-skills
React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.
vercel-react-best-practices
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
vercel-composition-patterns
React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.
user-request-gate
Use immediately when the user requests any implementation, code change, feature addition, fix, or modification. Gates code writing behind a backlog draft document. Read-only exploration is always permitted.
type-boundary-and-ssot
Applies Robota's preferred workflow for trust-boundary validation, strict typing, quality gates, and owner-based SSOT reuse. Use when adding or reviewing type contracts, boundary parsing, shared contract ownership, or running quality checks.
tdd-red-green-refactor
Kent Beck's TDD workflow. Use when writing new code or modifying existing behavior. Enforces the Red-Green-Refactor cycle with small, verifiable steps.
task-tracking
Track work using task files in .agents/tasks/. Use when starting, progressing, or completing a task to maintain a persistent record of work.