Read The Docs First
Use when implementing, integrating, upgrading, debugging, or answering anything involving third-party APIs, libraries, frameworks, CLIs, cloud services, model/provider SDKs, fast-moving product behavior, user requests for latest/current/official behavior, unfamiliar repo docs/specs, errors that may indicate API drift, or high-stakes auth, security, billing, data, migration, deployment, compliance…
Code Simplification
Use when code works but is harder to read, maintain, or extend than it should be — after a feature lands, when review flags complexity, or when you hit deep nesting, long functions, duplicated logic, dead code, or unclear names — and you want the complexity reduced without changing behavior.
Effective Communicator
Use when writing any message a person will read — answers, status updates, findings from a review, scan, audit, or debug, plans, recaps, or summaries — especially when the reader may not be able to see the code, files, or systems you are describing, or when another skill (adversarial-review, improve, a code review, a scanning pass) has produced results full of file names, function names, and vari…
Mcp Kubernetes Ro
A read-only Kubernetes MCP server: list resources, get resource details, retrieve pod logs, discover API resources, and perform base64 encoding/decoding operations - all while maintaining security through read-only access.
Use Claude Limits Efficiently
Use when long-running or parallel agent work must respect 5-hour and weekly usage limits by checking usage between waves, pausing near the cap, and resuming only when the window is clear.
Visual Recap
Use when the user wants a visual summary of work that was done — "visual recap", "recap this PR/branch/commit visually", "show me what changed in the browser" — for a PR, branch, commit range, or uncommitted changes. Generates a markdown recap grounded in the real diff and serves it locally (bundled zero-dependency server) with Mermaid diagrams, annotated rich diffs, DB migration cards, API call…
Adversarial Review
Use when you want a hostile, bias-free review of a code change — a PR, the last commit, or local/uncommitted work — that attacks it from many independent angles (concurrency, failure injection, input and auth attacks, data integrity, resource exhaustion, observability, API contract, maintainability, simplicity and scope creep, root-cause/incomplete-fix consistency, rollback, tests, AI-slop, fact-…
Use Premium Models Efficiently
Use when running a premium model (Claude Fable, Claude Opus, GPT-5.6 Sol, or similar) on codebase-heavy or token-heavy work and the user wants it to orchestrate research, coding, and testing while cheaper subagents (Sonnet, Haiku, Terra, Luna, or similar) do bounded heavy lifting.
Visual Plan
Use when the user wants to review an implementation plan visually — "visual plan", "show me the plan in the browser", "render this plan" — or when a plan involves architecture, schema, or API changes worth reviewing before code is written. Writes the plan as markdown and serves it locally (bundled zero-dependency server) with Mermaid diagrams, rich diffs, DB migration cards, API call cards, live…