Turn talk scripts, slides, and concept notes into reference sheets with section navigation, definitions, shareable links, a glossary, and six to ten anticipated questions with short answers for live Q&A and attendee follow-up.
Check whether a guide and its landing site show matching versions, template counts, and quiz totals. Get a structured status report that identifies mismatches, points to affected files, and suggests specific corrections.
Review code changes for concrete defects. Use it to examine modified code when you want to check whether a change contains a bug, with the review focused on specific problems in the changes.
Diagnose failures in an application or while it is running. Use it to investigate an application problem or a runtime error, meaning an error that occurs during execution.
Turn CHANGELOG.md entries into English and French announcement drafts for LinkedIn, Twitter/X, newsletters, and Slack. Select a release or week, highlight useful changes, and optionally choose the audience, format, and language.
Find third-party mentions of Claude Code Ultimate Guide or its author's public projects. Verify evidence, remove duplicate sources, and report mentions by type, then update the relevant tracking catalog after explicit approval.
Review a feature request before coding to clarify the user’s real goal and challenge assumptions. Choose whether to expand, hold, or reduce scope, then receive a recommendation to proceed, reframe the brief, or reject the direction.
Fetch official documentation from Anthropic and save local snapshots through an MCP tool. Initialize both baseline and current copies, then report the section count and storage path so later refreshes can be compared against the baseline.
Suggests running verbose shell commands through RTK, a tool that condenses command output, and executes them after confirmation. It helps reduce the text an AI agent processes when reviewing Git history, tests, builds, and files.
Check a Proofpack release candidate before packaging by running tests, validating the candidate, and inspecting the package locally. Compare the source state and command results with the evidence log, then report passed, failed, or unknown checks.
Audit French and English whitepapers and recap cards for outdated versions, missing language counterparts, and metadata problems. Receive document scores, an overall health report, and prioritized update suggestions, with optional proposed patches.
Turn articles, notes, or code history into talk preparation materials, including angles, titles, scripts, slide drafts, and revision sheets. Coordinate the stages with user checkpoints, or run an individual stage again.
Check release readiness by reviewing tests, type checks, linting, builds, security findings, documentation, and environment settings. Get a report separating deployment blockers from warnings, plus action items and checks for post-deployment health and rollback preparation.
Inspect platform support and configured restrictions for the Claude Code sandbox, which limits command access. Review writable paths, protected credential files, allowed network domains, and excluded commands. Recent violation log inspection is not yet implemented.
Audit a project and its Claude Code configuration for exposed credentials, vulnerable dependencies, malicious instructions, and hook security. Receive a scored report with evidence, severity levels, and a prioritized plan for addressing the findings.
Turn Git commits and pull request details into release notes in three formats: a changelog section, a release PR description, and a user announcement. Group changes, explain user impact, and flag database migrations.
Prepare evidence for a talk about project experience by comparing git history, release notes, and a source summary. Produce commit and contributor metrics, release analysis, and a factual timeline that flags conflicting or unverified information.
Compare a saved baseline of Anthropic documentation with the current local snapshot, showing added, removed, and modified sections, line changes, and unchanged counts without making a network request.
Check Claude Code configuration against a supplied threat database. Review installed skills, MCP servers that connect external tools, hooks, permissions, and exposed credentials, then receive findings grouped by severity with prioritized actions.
Review a pull request for code quality, correctness, security, tests, and documentation. Receive structured findings ranked by severity, with file references, approval status, positive highlights, and questions that need clarification.
Create a custom Claude Code skill with a structured SKILL.md file and optional scripts, reference documents, and templates. Follow checks for metadata and usage examples, test a real task, and package the skill for distribution.
Validate an implementation plan before execution through structural checks and specialist agent reviews. Check dependencies, files, tests, and architectural decisions, then update the plan to resolve findings, requesting human decisions when existing guidance is insufficient.
Analyze a project's code, existing automation, and connected services to suggest Routines, cloud-based Claude Code sessions triggered by schedules, API calls, or GitHub events. Receive prioritized proposals with inputs, outputs, expected value, and setup blockers.
Generate tests for a specified file or module using the project’s testing conventions. Cover expected behavior, unusual inputs, boundaries, failures, and external interactions, with independent tests and mock substitutes for external dependencies.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)