Claude Skills by Kastalien-Research

Before writing every response, read the shared conversation log for this session.

When writing responses to the user or to the orchestrator, be concise and direct.

You have a team. Use it.

Operate autonomously unless a situation meets one of these thresholds. When escalating, present the situation, options, and tradeoffs. Ask the user to *decide* — not *diagnose*.

- Work is NOT complete until `git push` succeeds - Never force push, `reset --hard`, or `clean -f` without explicit approval - Always `git pull --rebase` before pushing - Commit messages describe the *why*, not just the *what* - Never commit directly to `main` — all work goes through feature branches

You maintain a persistent expertise file that grows over sessions. This is your long-term memory.

Every agent operation — whether debugging, researching, coordinating, or verifying — follows the same fundamental cycle.

The failure mode of autonomous agents is not bad reasoning — it is *structurally unconstrained* reasoning. An agent can produce confident, fluent, plausible-sounding forward progress while operating on a corrupted model of the world, re-visiting ruled-out ideas in new costumes, and never noticing it was wrong because it never committed to what "right" would look like. Operational epistemics is the practice of building error-catching into the structure of the workflow itself — not trusting the...

Self-monitor for implementation spirals. When detected, stop iterating and escalate or accept partial completion.

You are a leader. You think, coordinate, and delegate. You do not execute raw work yourself.

**Status**: Draft **Priority**: P2 - Required for DGM Loop **Complexity**: Medium **Dependencies**: None (prerequisite for other specs) **Target Codebase**: `letta-code-thoughtbox/.letta/skills/`

Next.js best practices - file conventions, RSC boundaries, data patterns, async APIs, metadata, error handling, route handlers, image/font optimization, bundling

Expert integration of Supabase Auth with Next.js App Router Use when: supabase auth next, authentication next.js, login supabase, auth middleware, protected route.

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

Convert Docker Compose files to Coolify templates. Use when creating Coolify services, converting docker-compose.yml for Coolify deployment, working with SERVICE_URL/SERVICE_PASSWORD magic variables, or troubleshooting Coolify compose errors.

Use when writing or improving README files. Not all READMEs are the same — provides templates and guidance matched to your audience and project type.

Structure, classify, and write documentation using the Diátaxis framework. Use when writing docs, README files, guides, tutorials, how-to guides, API references, or organizing documentation architecture. Also use when asked to improve documentation, restructure docs, decide what type of doc to write, or classify existing content. Covers tutorials, how-to guides, reference, and explanation.

Create polished, intentional frontend interfaces. Use this skill when building any UI — dashboards, admin panels, landing pages, marketing sites, or web applications. Routes to specialized guidance based on context.

Use when optimizing CLAUDE.md, AGENTS.md, custom commands, or skill files for Claude 4.5 models - applies documented Anthropic best practices systematically instead of inventing improvements

Use when evaluating designs, reviewing code, or refactoring - measures success by total code in the final codebase, not effort to get there. Bias toward deletion.

Use when answering complex questions about a codebase that require exploring multiple areas or understanding how components connect - coordinates parallel sub-agents to locate, analyze, and synthesize findings

Use when writing prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text. Applies Strunk's timeless rules for clearer, stronger, more professional writing.

Guide for writing skills that wrap CLI tools. Use when creating a new CLI skill. For review, run through the Checklist section.

Execute a research task using compositional workflow planning. Characterizes the task, selects an approach from a library of research strategies, executes it, and self-evaluates output quality.