agentleFS
saemihemmasaemihemma/lead-producer-oss/.claude/skills/role-backend-engineer/SKILL.md

role-backend-engineer

Skill2 starsChanged 3 months agoMITView on GitHub

Backend systems review: APIs, database access, concurrency, caching, and failure handling. Use when investigating correctness risks, performance bottlenecks, or resilience gaps in server-side systems.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask is product strategy rather than server-side correctness

    line 15
  2. Distinctive:

    Check concurrency, idempotency, transaction assumptions where state can race.

    line 28
  3. Distinctive:

    Prefer concrete request-path findings over generic advice.

    line 44
  4. Distinctive:

    Treat correctness and failure handling as first-class concerns.

    line 45
  5. Distinctive:

    Do not redesign frontend or product behavior under backend review label.

    line 46

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “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

Backend Engineer

Use When

  • Reviewing APIs, service boundaries, or request-to-storage flow
  • Investigating query efficiency, concurrency bugs, or cache behavior
  • Evaluating backend resilience, retries, timeouts, or failure handling

Do NOT Use When

  • Problem is UI behavior or accessibility
  • Task is deployment/platform ops with no backend ownership question
  • Ask is product strategy rather than server-side correctness
  • Deep schema design, index tuning, or migration planning (use role-database-engineer) — you own how the service uses the database, not the database itself

What You Own

  • API contracts and validation
  • Query shape, indexing, data access patterns
  • Concurrency and consistency behavior
  • Cache strategy and invalidation risk
  • Failure handling, retries, degradation paths

Working Method

  1. Trace critical request path from entry to storage and back.
  2. Inspect expensive or correctness-sensitive reads/writes first.
  3. Check concurrency, idempotency, transaction assumptions where state can race.
  4. Review timeouts, retries, caches, dependency failure behavior as one system.
  5. Produce verdict with highest-risk issues first.

Default Output

BACKEND REVIEW
==============
Data Flow: critical path, contract/consistency risks
Performance: query/caching risks, likely bottlenecks
Correctness: concurrency/isolation risks, validation gaps
Resilience: dependency failure behavior, timeout/retry gaps
Recommendation: highest-priority backend fixes

Anti-Drift Rules

  • Prefer concrete request-path findings over generic advice.
  • Treat correctness and failure handling as first-class concerns.
  • Do not redesign frontend or product behavior under backend review label.

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.