Agent skills for Claude Code

Review a medium- or high-impact decision through multiple specialist perspectives and produce one practical recommendation.

Structure a choice between concrete options: elicit the real criteria and their weights, score each option honestly, run a sensitivity…

Capture context, drivers, options, decision, consequences and revisit triggers in a durable engineering decision record.

Evidence-bound multi-agent council for high-stakes decisions.

Generate modern presentation decks (PDF) from markdown content.

Discrete MCP tools that back the deck-builder agent — theme listing, image generation (gpt-image-2), stock search (Pexels), and Marp…

For declarations of intent — elements of the offense are found in paragraphs 116 et seq.

X/Twitter via xurl CLI: post, search, DM, media, v2 API.

Ask a question about an existing Decodie learning entry and get a deeper explanation using the entry content and live source code as…

Explain a selected piece of code — what it does, how it works, potential issues, and improvement suggestions.

Fast CI-friendly check for entries whose source files have changed since last verification.

Generate a high-level overview of a file, directory, or project — answering "what is this and how is it organized." Produces a single…

Verify that learning entries still match the source code they reference.

Set up the Decodo Codex plugin, environment variables, MCP policy, and safe first-run checks without exposing credentials.

Reverse-engineer why a finished piece of work succeeds and extract what transfers to your own — rules, a checklist, and a first exercise.

Create all AWS resources for AI automation agents — DynamoDB tables, SQS queue, S3 bucket, SNS topic, IAM role, Lambda functions, and API…

Guides architectural decisions for Deep Agents applications.

Inspect and explain conversations in the local Deep Agents Code SQLite session store.

Deep analysis and investigation

Deep consistency audit of the entire repository — launches 4 parallel specialist agents to find factual errors, code bugs, broken…

Extended vault cleanup: full audit PLUS stale content scan, outdated references, content quality review, redundant tags, broken external…