264 skills · sorted by relevance
Turn a vague feature idea into clear requirements through dialogue. Define what to build, its scope, and success criteria, then capture the result in a short chat summary or a requirements document ready for implementation planning.
Draft announcements for a shipped feature, explaining what users can now do and why it matters. Produce copy-ready text tailored to channels such as X, LinkedIn, email, release notes, blogs, or demo scripts.
Review code changes or a pull request for bugs, effects on existing behavior, test gaps, and project standards. Receive findings supported by the code and a clear account of review coverage, with local fixes available when explicitly requested.
Review and simplify code while preserving its behavior. Check readability, reuse, and efficiency, assess whether tests and comments add value, and verify applied changes with the project's configured checks before review.
Explain a confusing message, file, link, or passage in everyday language. It highlights the main point, what it means for the reader, and any decisions or actions needed, while preserving caveats and uncertainty.
Save working changes as local Git commits with messages that explain the outcome. Follow the project's commit style, select files explicitly, and split clearly separate changes into a few logical commits when appropriate.
Turn a plan, specification, or concrete development request into implemented changes with local verification. Run it independently for a review and delivery handoff, or return implementation results to a calling workflow.
Evaluate a technology adoption question, a document, or proposed approaches against project evidence and constraints. Receive a supported position with tradeoffs and uncertainty, with an optional panel that consults other models and reconciles their views.
Draft, edit, or check prose for formulaic wording and readability problems while preserving source facts and the writer’s voice. Use it to produce plain text or receive specific findings without a full rewrite.
Test the pages affected by a branch or pull request in a browser. The skill checks rendered pages and key interactions, then reports passes, failures, skipped checks with reasons, and steps to reproduce problems.
Create or update STRATEGY.md through guided questions about a product’s purpose, users, success metrics, and investment areas. Capture a shared basis for product decisions, with draft review and focused updates to existing documents.
Share Markdown specs, plans, and drafts through Proof, a collaborative document editor. Read shared documents, add comments or tracked suggestions, edit text, and pull documents into local files, with confirmation of each requested operation.
Build a disposable prototype to test how a product should work, feel, or look before committing to an approach. Let the user experience it, record their choices, and carry those decisions into requirements or further planning.
Set up a separate Git working directory for a new task or an existing branch, pull request, or commit. Detect and reuse existing isolation, prefer the agent environment's worktree tools, and report the working path and branch.
Create a handoff that captures work context and relevant references for another agent or session. Read an existing continuity document to explain the current situation and recommend next steps for the user to confirm.
Build and exercise an iOS app in a simulator using XcodeBuildMCP. Collect screenshots, logs, and human verification results, then report which checks passed, failed, or were skipped, alongside the overall outcome and remaining failures.
Generate improvement ideas grounded in the project or topic, critique every candidate, and rank the survivors with explanations. Produce a document that helps users choose which ideas deserve further exploration before defining requirements.
Improve a measurable target in a working system by tracing workload costs or scoring alternative implementations. Compare results against a baseline, keep confirmed improvements on a dedicated branch, and record experiments for review or resumption.
Retune a collection of skills for a new model using archived runs and controlled comparisons. Establish normal measurement variation, register success criteria before editing, and make targeted changes until measured behavior meets the criteria or a specific limitation is reported.
Create, edit, and review agent skills against a shared authoring standard. Clarify goals, completion conditions, and responsibilities, remove unsupported instructions, and validate changes according to their risk, with a report explaining what changed and why.
Address existing feedback on a GitHub pull request, a proposed code change. Evaluate comments against the code, apply valid fixes, and verify replies and thread resolution, with options for local handoff or resuming saved work.
Collect new feedback from configured Slack and GitHub Issues sources, acknowledge receipt, analyze recordings, and verify claimed fixes against the default branch. Combine unresolved items into a rolling plan ready for the lfg workflow.
Refine a working feature through browser feedback from the user. Collect observations through typed comments or live speech and drawing, apply focused usability fixes, and save the changes in local commits.
Review an existing requirements document, plan, or specification from several role-based perspectives. Identify inconsistencies and obstacles to carrying out the work, verify their consequences, apply authorized corrections, and present improvements or decisions that still need attention.