CtrlK
BlogDocsLog inGet started
Tessl Logo

igmarin/rails-agent-skills

Curated library of 41 public AI agent skills for Ruby on Rails development. Organized by category: planning, testing, code-quality, ddd, engines, infrastructure, api, patterns, context, and orchestration. Covers code review, architecture, security, testing (RSpec), engines, service objects, DDD patterns, and TDD automation. Repository workflows remain documented in GitHub but are intentionally excluded from the Tessl tile.

95

1.77x
Quality

93%

Does it follow best practices?

Impact

96%

1.77x

Average score across 41 eval scenarios

SecuritybySnyk

Passed

No known issues

Overview
Quality
Evals
Security
Files

SKILL.mdskills/code-quality/respond-to-review/

name:
respond-to-review
license:
MIT
description:
Applies when a developer has received code review feedback on Rails code and needs to decide what to implement, how to respond, and in what order. Use when addressing PR comments, pull request feedback, or review comments on Rails code. Covers evaluating reviewer suggestions, pushing back with technical reasoning, avoiding performative agreement, implementing feedback safely one item at a time, and triggering a re-review when needed. Trigger scenarios: respond to reviewer, address review comments, handle pull request feedback.
metadata:
{"version":"1.0.0","user-invocable":"true"}

Respond to Review

Quick Reference

CategoryDescriptionAction
Correct + CriticalReal security, crash, or data riskFix immediately, re-review
Correct + SuggestionReal improvement, not blockingFix in this PR or ticket follow-up
Correct + Nice to haveStyle, minor optimizationOptional — acknowledge explicitly
IncorrectReviewer lacks context or misread the codePush back with technical reasoning
AmbiguousUnclear what change is actually requestedClarify before implementing

HARD-GATE

WHEN receiving code review feedback:

1. READ:      Read all feedback completely before reacting
2. UNDERSTAND: Restate each point as a technical requirement
3. VERIFY:    Check the suggestion against the actual codebase
4. EVALUATE:  Is this technically sound for THIS codebase?
5. RESPOND:   Technical acknowledgment, clarifying question, or reasoned pushback
6. IMPLEMENT: One item at a time — test after each change
7. RE-REVIEW: Trigger a re-review if any Critical items were addressed

DO NOT start implementing before completing steps 1-4.

Core Process

Use this skill when you have received review feedback on your own Rails code (PR comments, pair review, async review). This is the counterpart to code-review, which covers giving a review.

Core principle: Verify before implementing. Technical acknowledgment over performative agreement. Re-review after significant changes.

Forbidden Responses

These responses skip verification and add zero signal:

ForbiddenWhy
"You're absolutely right!"Performative — nothing was verified
"Great point!" / "Excellent feedback!"Signals compliance, not understanding
"Let me implement that now"Skips verification — reviewer may lack codebase context
"I'll fix all of these"Batch commitment before evaluating each item individually
"Fixed!" with no technical explanationAlways state what was checked and why the fix is correct

Instead: Restate the technical requirement, ask clarifying questions, push back with reasoning if wrong, or just start implementing one item after reading all feedback.

Evaluating Feedback

Before implementing any suggestion, classify it based on the Quick Reference table above.

Pushing Back

Push back when a suggestion is technically incorrect for the codebase. Use this structure:

  1. Acknowledge what the reviewer is concerned about
  2. Explain the relevant codebase constraint or reason
  3. Propose an alternative if one exists, or explain why no change is needed
"I see the concern about N+1 here. In this case the association is already
preloaded at line 42 via `includes(:orders)`. Adding another `eager_load`
would run a duplicate JOIN. Happy to add a comment clarifying this if helpful."

Never: Push back without technical evidence. If unsure, verify before claiming it's fine.

Implementation Order (Multi-Item Feedback)

  1. Clarify anything ambiguous FIRST — before touching code
  2. Critical blocking issues (crashes, security, data loss)
  3. Simple fixes (typos, naming, missing requires)
  4. Complex changes (refactoring, logic changes)
  5. Test each fix individually — run the relevant spec after each change
  6. Verify no regressions — run full suite before requesting re-review

Re-Review Trigger

After implementing feedback, decide whether to request a re-review:

SituationAction
Any Critical finding was addressedRequest re-review — mandatory
3+ Suggestion items changed logicRequest re-review — recommended
Only Nice to have or cosmetic fixesComment what was done — no re-review needed
Architecture or class structure changedRequest re-review — mandatory

Common Mistakes & Red Flags

Mistake / Red FlagReality
Treating all feedback as equally urgentClassify by severity — Critical before cosmetic
Closing review comments without verifyingComment what you checked and why you agree or disagree
All review comments closed without any pushbackMay indicate blind compliance — verify each item independently
Skipping re-review after Critical fixesA fix can introduce new issues — re-review is mandatory
Asking for re-review after cosmetic changesWastes reviewer time — only request when logic changed

Extended Resources

  • assets/response_templates.md provide copy-ready response patterns for common review outcomes.

Output Style

When responding to review feedback, output:

  1. Scope — State that the user received review feedback on their own Rails code; if the task is asking you to give a review instead, use code-review.
  2. Feedback table — For each reviewer point, include: restated technical requirement, code checked, classification, decision, and response.
  3. Verification evidence — Name the exact file, method, line, spec, or behavior checked before agreeing, implementing, or pushing back.
  4. Reasoned pushback — When a suggestion is incorrect, use the pushback structure: reviewer concern, codebase constraint/evidence, and alternative or no-change rationale. Never push back without technical evidence.
  5. Implementation order — List fixes one item at a time, with relevant spec after each logic change and full-suite regression check before re-review.
  6. Re-review decision — State whether re-review is mandatory, recommended, or unnecessary based on Critical fixes, logic changes, architecture changes, or cosmetic-only work.
  7. Language — Must be in English unless explicitly requested otherwise.

Integration

SkillWhen to chain
code-reviewThe counterpart — use when giving a review, not receiving
write-testsRun the TDD loop after implementing feedback that changes logic
refactor-codeWhen feedback suggests a larger structural change
security-checkWhen Critical feedback involves security — get a dedicated review

skills

code-quality

README.md

server.json

tile.json