agentleFS
ryanschueryanschue/automated-product-engineer/skills/codebase-onboarding/SKILL.md

codebase-onboarding

Skill0 starsChanged 24 days agoMITView on GitHub

Onboard an existing repository into Automated Product Engineer. Use when first analyzing a codebase, recording its local engineering contracts, selecting upgrade priorities, or creating a staged modernization program and project-specific skill overlay.

56 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use pytorch-patterns, continuous-agent-loop and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • Yog-SothoSkill

    pytorch-patterns

    PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading. Always activate when the user is writing PyTorch models or training scripts, reviewing deep learning code, debugging training loops or data pipelines, optimizing GPU memory or training speed, setting up reproducible experiments, implementing transfer learning or fine-tuning, or asks anything about nn.Module, DataLoader, autograd, AMP, or torch.compile.

    Also in 6 projects that use this

  • junimnjwSkill

    continuous-agent-loop

    Patterns for continuous autonomous agent loops with quality gates, evals, and recovery controls.

    Also in 7 projects that use this

  • loulanyueSkill

    nuxt4-patterns

    Nuxt 4 app patterns for hydration safety, performance, route rules, lazy loading, and SSR-safe data fetching with useFetch and useAsyncData.

    Also in 4 projects that use this

  • Arnav-0Skill

    api-test-suite-builder

    Use when the user asks to generate API tests, create integration test suites, test REST endpoints, or build contract tests.

    Also in 3 projects that use this

  • royaluniondesign-sysSkill

    content-hash-cache-pattern

    Cache expensive file processing results using SHA-256 content hashes — path-independent, auto-invalidating, with service layer separation.

    Also in 5 projects that use this

  • junimnjwSkill

    carrier-relationship-management

    Codified expertise for managing carrier portfolios, negotiating freight rates, tracking carrier performance, allocating freight, and maintaining strategic carrier relationships. Informed by transportation managers with 15+ years experience. Includes scorecarding frameworks, RFP processes, market intelligence, and compliance vetting. Use when managing carriers, negotiating rates, evaluating carrier performance, or building freight strategies.

    Also in 4 projects that use this

  • +3 more from junimnjw

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 5 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 52 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Start with .automated-product-engineer/onboarding/README.md when it exists.

    line 10
  2. Distinctive:

    Read references/onboarding-workflow.md for the full sequence.

    line 12
  3. Very specific:

    Do not rewrite every installed skill.

    line 28
  4. Distinctive:

    Add the smallest useful characterization or UI contract test before structural change.

    line 39
  5. Distinctive:

    Add focused domain, transport, persistence, or component proof at the owning boundary.

    line 40
  6. Distinctive:

    Add E2E coverage after the product contract and cross-boundary behavior are stable.

    line 42
  7. Distinctive:

    Update the local engineering context, decisions, program, and retrospective from evidence.

    line 44

“Common” is measured: kept by at least 6 in 10 of the 52 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Codebase Onboarding

Turn an unfamiliar repository into an explicit, team-owned operating system before broad implementation. Preserve what works, expose contradictions, and make later agent work follow the repository's real product and engineering decisions.

Start with .automated-product-engineer/onboarding/README.md when it exists. Run pnpm dlx automated-product-engineer onboard to create the initial workspace and refresh analysis.latest.json. Treat generated signals as hypotheses until callers, runtime behavior, tests, and documentation confirm them.

Read references/onboarding-workflow.md for the full sequence. Use references/domain-review-matrix.md to inspect each system boundary, references/local-skill-overlay.md to adapt the shared skills without forking them, and references/upgrade-program-and-feedback.md when executing selected upgrades.

Establish the baseline

Read repository instructions and all product, architecture, ADR, API, schema, design-system, security, testing, release, and runbook documentation before drawing conclusions. Trace representative user journeys from UI through state, transport, policy, persistence, and recovery. Compare written claims with code and tests; record contradictions rather than silently choosing one.

Maintain these project-owned artifacts:

  • CURRENT_PRACTICES.md: verified conventions, owners, evidence, and exceptions;
  • INCONSISTENCIES.md: conflicts between docs, code, runtime behavior, and tests;
  • PRODUCT_REQUIREMENTS.md: journeys, policies, failure recovery, and acceptance evidence;
  • DECISIONS.md: accepted local choices and rejected alternatives;
  • UPGRADE_PROGRAM.md: selected, ordered, reversible slices;
  • TEST_STRATEGY.md: characterization, focused, UI, E2E, native, and operational proof;
  • RETROSPECTIVES.md: observed results and fix-back changes.

Do not rewrite every installed skill. Keep reusable guidance upstream and put repository-specific differences in project-engineering-context, which every specialist must read before acting.

Let the user choose the program

Return a compact current-system brief: strengths to preserve, verified risks, useful opportunities, contradictions, and material unknowns. Group recommendations by product effect. Recommend at most three starting slices and ask only when the choice changes product behavior, authority, data lifetime, security, compatibility, or recovery. If the user has already selected the outcome, continue.

Execute in reviewable slices

For each selected slice:

  1. Pin the product requirement and current behavior.
  2. Add the smallest useful characterization or UI contract test before structural change.
  3. Add focused domain, transport, persistence, or component proof at the owning boundary.
  4. Implement one reversible vertical slice with explicit migration and rollback behavior.
  5. Add E2E coverage after the product contract and cross-boundary behavior are stable.
  6. Inspect the real browser or native runtime and run the relevant repository gates.
  7. Update the local engineering context, decisions, program, and retrospective from evidence.

Share progress through committed documentation, reviewable commits, and a draft pull request when authorized. Continue autonomously through safe, reversible work and verification. Stop for destructive data work, production access, release, merge, or a genuinely undecided material contract.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.