Skill Claude CodeCodex
Keep the workspace tidy while the agent works: no orphan scratch docs/scripts, confine temp to .agent-scratch/ or tmp/agent-, clean before declaring done. Use during implementation, multi-file edits, shell/write batches, or when marking work done — continuous hygiene, not post-hoc /cleanup.
Skill Claude CodeCodex
KeePassXC cursor.kdbx — natywny keyring per OS, keepass-db.path bez fallbacków, agent instaluje brakujące narzędzia.
Skill Claude CodeCodex
Audit and maintain project rules in .cursor/rules/. Use when auditing project rules, checking prefix convention, syncing doc/rules.md, or when the user asks about .cursor/rules or prefix convention.
Skill Claude CodeCodex
Use Apify Actors for scraping/data acquisition pipelines. Use when data collection from websites is required and needs repeatable runs.
Skill Claude CodeCodex
Use browser automation MCP (Playwright/Browser/Browser-Use) to validate UI flows, capture screenshots, and reproduce issues. Use when visual verification or web flow testing is needed.
Skill Claude CodeCodex
Drive BrowserClaw (BrowserOS agent browser) via MCP: logged-in local Chromium for agents, cockpit/audit/replay, snapshot→act refs, tab ownership. Use when a task needs the web, real logins/cookies, parallel agent tabs, or the user mentions BrowserClaw / agent browser. Prefer over Playwright, Claude-in-Chrome, or the…
Skill Claude CodeCodex
Use BrowserOS MCP to automate the user's visible Chromium browser (sessions, cookies, manual CAPTCHA/2FA). Use when anti-bot protection, user intervention, OAuth in existing session, or Klavis Strata app integrations are needed.
Skill Claude CodeCodex
Fetch version-specific library and framework documentation via Context7 MCP. Use when implementing against third-party APIs/SDKs where model knowledge may be stale, or when the user says "use context7" / asks for current docs for a named library.
Skill Claude CodeCodex
Use GitHub MCP for issue/PR context, diffs, reviews, and automations. Use when the task references PR/issue numbers, review requests, or requires repo metadata beyond local git.
Skill Claude CodeCodex
Query dashboards/logs/alerts to support incident analysis and regressions. Use when troubleshooting involves observability, incidents, latency, error rates.
Skill Claude CodeCodex
Recall and reuse prior decisions, constraints, and artifacts using MCP memory (e.g., Neo4j). Use when the user references past work (“jak ostatnio”, “kontynuuj”), when resuming a project thread, or when a repeated topic suggests existing decisions.
Skill Claude CodeCodex
Use Neo4j memory MCP for creating/updating linked memories (entities, relations), de-duplication (DRY), and retrieval queries for project continuity. Use when saving global learnings or querying graph relationships.
Skill Claude CodeCodex
Automate browser flows and capture evidence (screenshots, console/network errors). Use for UI verification, repro steps, and end-to-end smoke tests.
Skill Claude CodeCodex
Use Postman MCP to inspect/maintain collections, environments, and API workflows; generate or validate requests and tests. Use when API verification or collections are the source of truth.
Skill Claude CodeCodex
Execute Shrimp tasks in order: load state, respect dependencies, implement, verifytask, update status. Use after task-planning-shrimp or when resuming inprogress/pending tasks (/next). Not for same-session-only Plan Mode work.
Skill Claude CodeCodex
Execute end-to-end migrations and consolidate docs/scripts (remove dead files, keep canonical runbooks). Use when changing runtime model, reorganizing repo, or doing “repo cleanup”.
Skill Claude CodeCodex
Next.js App Router frontend stack workflow: Server Components-first, Prisma server-only (Node runtime), Tailwind + shadcn/ui, TanStack Query, React Hook Form + Zod, and conventions for work under frontend/. Use when implementing or refactoring UI, routes, data fetching, mutations, or forms in this stack.
Skill Claude CodeCodex
Produce a reviewable, file-referenced implementation plan that acts as a contract before execution. Use for risky ops, architecture changes, migrations, multi-file edits.
Skill Claude CodeCodex
On-demand over-engineering review/audit using the "laziness ladder" (DietrichGebert/ponytail) — the always-on rung is already in USERRULES.txt STATIC PRINCIPLES; this skill is for deep diff/repo audits and debt tracking. Use when the user asks to review a diff or repo for over-engineering, unnecessary abstractions…
Skill Claude CodeCodex
FastAPI + Pydantic v2 backend workflow: implement/modify API endpoints with thin handlers + service layer, add pytest tests, manage idempotent Alembic migrations, and implement streaming ETL/parsers with invalid-row CSV logging. Use this skill when working on Python backend APIs, schema changes, or ingestion/parsing…
Skill Claude CodeCodex
Enforce consistent Python typing (type hints + return types), concise Google-style docstrings, PEP 8/Black formatting, and unit tests when creating or editing Python code. Use when working on .py files, Python APIs, refactors, or bug fixes where maintainability and correctness matter.
Skill Claude CodeCodex
Ground answers in the repository by reading relevant files, configs, and code paths. Use when the user asks to modify/debug code, configuration, CI/CD, or wants repo-specific reasoning.
Skill Claude CodeCodex
Enforce SOLID design principles during code generation, refactors, and code review (SRP/OCP/LSP/ISP/DIP). Use when changing architecture, introducing new abstractions, reducing coupling, eliminating type-switches, or reviewing PRs for maintainability.
Skill Claude CodeCodex
Provide structured outputs (plan/report/checklist/table) optimized for readability and reuse. Use when user requests a plan, report, checklist, template, or when high-risk requires explicit verification steps.