Reviews, reproductions, and edits that leave the tests green.

• Leave code review notes on the risky linesCursor drafts code review comments for someone else's pull request, limited to behavior, missing tests, and risk.Cursor/Coding/20 min
• Review the diff before you mergeHand Claude Code the branch and ask for defects, missing tests, and anything a reviewer would bounce.Claude Code/Coding/20 min
• Move the tests without changing the behaviorAsk Cursor to port a test file to the repo's current runner while the assertions stay the same.Cursor/Coding/25 min
• Write the smallest script that reproduces the bugCodex turns a bug report into a tiny script or test that fails for the reason you described.Codex/Coding/30 min
• Explain what a dependency update actually changesClaude Code reads a dependency bump and writes what behavior in your app could change.Claude Code/Coding/20 min
• Rename the module and keep the tests greenCursor renames a module across imports and tells you which tests prove the rename is behavior-neutral.Cursor/Coding/25 min
• Summarize a pull request for the teamCursor reads a PR and writes a summary a non-author can read: what changed, why, and what to test.Cursor/Coding/18 min
• Add tests to legacy code without refactoring itClaude Code writes tests for untested legacy code and tells you which behavior it cannot safely assert.Claude Code/Coding/35 min
• Onboard to an unfamiliar codebase in an afternoonCursor maps an unfamiliar codebase and builds a mental model: entry points, data flow, test strategy, and where to start reading.Cursor/Coding/40 min
• Turn a pull request diff into review notes and a risk checklistCursor reads a PR diff and drafts review comments plus a short checklist of what could break in production.Cursor/Coding/22 min
• Package a repeatable team SKILL.md for Claude CodeClaude Code turns a workflow your team already runs into a portable SKILL.md with triggers, guardrails, and a done checklist.Claude Code/Coding/35 min
• Share a Cursor project skill without multi-machine driftCursor helps you store a project skill in the repo so every machine loads the same SKILL.md instead of a private Rules for me note.Cursor/Coding/30 min
• Keep one skill folder in sync for Codex and Claude CodeYou maintain a single skills directory in git that both Codex and Claude Code are pointed at, with a short compatibility note for each tool.Codex, Claude Code/Coding/40 min
• Fix a failing CI job from the logsCursor reads a failing CI log, proposes the smallest code change that addresses the real error, and gives you the command to verify locally.Cursor/Coding/25 min
• Draft a PR description from the diff in Copilot ChatGitHub Copilot Chat on a pull request writes a description from the diff: summary, test plan, and residual risk.GitHub Copilot/Coding/15 min
• Gate a risky refactor with a characterization-test skillClaude Code writes a SKILL.md that locks behavior with characterization tests before an agent refactors production paths.Claude Code, Cursor/Coding/40 min
• Share one PR-description skill across Copilot, Cursor, and Claude CodeOne SKILL.md in the repo defines how every coding agent writes PR bodies from a diff, with a short load line per tool.GitHub Copilot, Cursor, Claude Code/Coding/30 min
• Give agents a checked-in design-system SKILL.mdCursor or Claude Code authors a design-system SKILL.md with tokens, component rules, and anti-slop guardrails so agent-built UI matches your product instead of generic AI chrome.Cursor, Claude Code/Coding/35 min
• Keep secrets out of agent chat with env and a SKILL.mdClaude Code or Cursor follows a checked-in skill that forbids pasting DB and API secrets into chat: use .env, a secret manager, op run, or CI secrets, and reference variable names only.Claude Code, Cursor/Coding/30 min
• Publish a portable SKILL.md pack from an MCP serverYou ship a versioned skills folder from an MCP server or agent pack with digest metadata so clients discover verified skills without copying ad-hoc prompts.Cursor, Claude Code/Coding/40 min
• Gate agent work with a checked-in eval harness skillCursor or Claude Code authors a SKILL.md that points at versioned eval cases and a pass/fail rubric so coding agents cannot green a task by vibes alone.Cursor, Claude Code/Coding/40 min
• Require green Playwright before an agent UI rewriteA checked-in SKILL.md tells Cursor or Claude Code to run and extend Playwright coverage before it rewrites screens, with a stop rule if e2e fails mid-diff.Cursor, Claude Code, Playwright/Coding/35 min
• Generate a typed API client from OpenAPI via a repo skillClaude Code or Cursor follows a SKILL.md that regenerates a typed SDK from your OpenAPI spec, with usage examples and a diff checklist agents run every time the spec changes.Claude Code, Cursor/Coding/35 min
• Review a Dependabot PR with a checked-in merge skillCursor or Claude Code follows a SKILL.md that reads the changelog, runs your real test commands, and blocks merge until breaking bumps get a migration note — not a blind approve.Cursor, Claude Code, GitHub/Coding/30 min
• Fix a failing GitHub Actions job with an agent CI skillClaude Code or Cursor uses a SKILL.md that reproduces the failing workflow locally, edits YAML and scripts without disabling checks, and documents what broke and why.Cursor, Claude Code, GitHub/Coding/35 min
• Gate database migrations with a review SKILL.mdCursor or Claude Code applies a SKILL.md before merging SQL or ORM migrations: expand-contract checks, lock risk, rollback path, and a dry-run against staging schema.Cursor, Claude Code/Coding/40 min
• Review a Terraform plan with a blast-radius SKILL.mdCursor or Claude Code follows a SKILL.md before terraform apply: destroy/replace counts, state drift, IAM expansion, and a merge-blocking summary for whoever holds the apply key.Cursor, Claude Code, Terraform/Coding/35 min
• Block insecure Dockerfiles with an agent security SKILL.mdClaude Code or Cursor applies a SKILL.md to Dockerfile and Compose diffs: non-root users, secret leakage in layers, pinned bases, and healthchecks — with merge-blocking findings.Cursor, Claude Code/Coding/30 min
• Triage a Sentry issue into a minimal fix briefCursor or Claude Code follows a SKILL.md from a Sentry issue link: stack, breadcrumbs, and release — then writes a minimal repro and first-fix PR brief without catch-all error swallowing.Cursor, Claude Code, Sentry/Coding/35 min
• Block insecure Kubernetes manifests with a security SKILL.mdCursor or Claude Code applies a SKILL.md to k8s manifests and Helm values: privileged containers, hostPath mounts, capability grants, secrets in env, missing resource limits, and NetworkPolicy gaps.Cursor, Claude Code/Coding/35 min
• Quarantine flaky tests with a triage SKILL.mdCursor or Claude Code follows a SKILL.md from CI flake reports: isolate the flaky test, quarantine it with owner and ticket, propose root-cause checks for timing/state/order issues, and provide a re-enable checklist.Cursor, Claude Code/Coding/30 min
• Find and remove stale feature flags with a cleanup SKILL.mdCursor or Claude Code uses a SKILL.md to discover unused feature flags after launch: dead code paths, config drift, references in tests only, and a safe removal PR checklist.Cursor, Claude Code/Coding/30 min
• Review npm dependencies for supply-chain risk with an audit SKILL.mdCursor or Claude Code applies a SKILL.md to dependency PRs: new maintainers, suspicious postinstall scripts, lockfile-only changes without version bumps, typosquat package names, and a merge gate checklist.Cursor, Claude Code/Coding/35 min
• Audit agent skill folders for SKILL.md casing on Linux CICursor and Claude Code only load a skill when the file is exactly SKILL.md. An agent skill audits skill directories on Linux runners and fixes silent Unknown skill failures from skill.md or Skill.md.Cursor, Claude Code/Coding/25 min
• Threat-model a third-party agent skill before you install itBefore copying a community SKILL.md into your repo, Claude Code or Cursor walks an install-review skill: open source repo, pin version, read SKILL.md and bundled scripts, and produce a go/no-go checklist.Cursor, Claude Code/Coding/40 min
• Route agent work across cheap, mid, and max models with SKILL.mdCursor or Claude Code loads a SKILL.md that assigns read-only and test tasks to a fast tier, refactors to a mid tier, and merge-gate or architecture work to max — cutting spend without hiding quality gaps.Cursor, Claude Code/Coding/30 min
• Scan GitHub Actions workflows for secret exfil before mergeCursor or Claude Code applies a SKILL.md on workflow PRs: hunt secret exfiltration, pull_request_target misuse, unpinned actions, and overbroad permissions — with a merge gate comment.Cursor, Claude Code, GitHub/Coding/35 min
• Review Next.js middleware auth before mergeCursor or Claude Code applies a SKILL.md on middleware/proxy PRs: public path allowlists, matcher gaps, header spoofing, redirect loops, and missing session checks — with merge-blocking findings.Cursor, Claude Code/Coding/40 min
• Review Stripe webhook handlers for idempotency before mergeCursor or Claude Code applies a SKILL.md on webhook PRs: signature verification, idempotency keys, replay windows, and dual-write races — with merge-blocking findings.Cursor, Claude Code/Coding/35 min
• Review outbound URL fetchers for SSRF before mergeCursor or Claude Code applies a SKILL.md on PRs that fetch a caller-supplied URL: private-network targets, redirect hops to metadata endpoints, and DNS rebinding — with merge-blocking findings.Cursor, Claude Code/Coding/40 min
• Review file upload handlers for traversal and content sniffingCursor or Claude Code applies a SKILL.md on upload PRs: path traversal, trusted Content-Type headers, polyglot files, and public object ACLs — with merge-blocking findings.Cursor, Claude Code/Coding/35 min
• Review Content-Security-Policy and security headers before mergeCursor or Claude Code applies a SKILL.md on header diffs: script-src relaxations, unsafe-inline, missing frame-ancestors, and report-only policies that never enforce — with merge-blocking findings.Cursor, Claude Code/Coding/30 min