Agent skills

Use when creating or configuring Claude Code agents and their frontmatter.

Autonomous research review loop using any OpenAI-compatible LLM API.

Audit and rewrite content to remove AI writing patterns ("AI-isms").

This skill should be used when the user asks to "debug this", "fix this error", "investigate this bug", "troubleshoot this issue", "find…

This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command…

Document a recently solved research problem to compound methodological knowledge

Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens.

Full research pipeline: Workflow 1 (idea discovery) → implementation → Workflow 2 (auto review loop).

This skill should be used when the user asks to "review paper quality", "check paper completeness", "validate paper structure"…

This skill should be used when the user asks to "remove AI writing patterns", "humanize this text", "make this sound more natural"…

Automate Bubble tasks via Rube MCP (Composio).

Reviews BubbleTea TUI code for proper Elm architecture, model/update/view patterns, and Lipgloss styling.

Budget allocation and bidding strategy review across all ad platforms.

Plan and review paid-media budgets, bidding, pacing, marginal return, forecasts, CPA, ROAS, MER, LTV:CAC, constraints, and allocation…

Produce a structured budget variance analysis from actual vs budget figures.

Bug bounty program management and security disclosure expertise for smart contracts.

Framework for backlog bug cleanup sessions.

Generates a structured Bug Fix Brief (BFB) to document issue corrections.

Automate Bugherd tasks via Rube MCP (Composio).

Build a redacted, evidence-backed continuation brief from a Claude Code JSONL transcript.

Take a PRD and build a dark factory around it - a repository that takes work in as an issue and ships validated code out with nobody at…