All Skills

Experiment with code changes in an isolated worktree. Changes can be reviewed and merged or discarded.

5-stage quality pipeline for Agent Teams — Plan, PRD, Execute, Verify, Fix

Daily curated news digest. Use when user asks about news, trends, what's new, or at session start if a fresh digest is available.

Validate completed work against defined acceptance criteria. Use after completing a task that has specific success criteria defined in issues, specs, or task descriptions.

Enforce tiered test coverage standards — critical paths >=90%, business logic >=80%, general code >=70%. Use before claiming code is complete.

Challenge recommendations, designs, or synthesis by adversarial review across 5 dimensions. Use before shipping any significant recommendation or design document.

End-of-iteration review with quality grading, metrics, and trend analysis. Use at the end of each development iteration or sprint.

Scan staged changes for secrets, debug statements, TODOs without references, and other common commit mistakes. Use before creating any commit.

Enforce the Implement→Review→Test→Fix→Loop cycle until work is clean. Use after any non-trivial implementation to prevent "good enough" exits.

Add new Agent Skill templates to the meta-agent-skills framework.

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

JavaScript essentials for vibecoders. Activated when Claude works with .js/.mjs/.jsx/.ts files. Covers the language concepts most commonly encountered during vibecoding.

Brainstorm with structured debate process. Use when weighing tradeoffs, debating approaches, or making architectural decisions.

Full implementation with testing. Use when building features, adding functionality, or implementing changes that need coding, tests, and review.

Implements file upload, storage, and retrieval using AWS S3 or Cloudflare R2, including pre-signed URLs, image resizing with Pillow/sharp, CDN delivery, and secure MIME validation. Use when users need to upload files — profile pictures, document attachments, product images, or any user-generated media. Trigger when user mentions "file upload", "image upload", "S3", "R2", "Cloudflare", "CDN", "pre-signed URL", "avatar", "attachments", or "store files". Never stores uploaded files on the local filesystem in production.

Gather facts and context from codebase, docs, and web. Use when exploring patterns, finding implementations, looking up documentation, or researching before decisions.

Use when the user wants to check which Tandem features are installed, verify hooks are configured correctly, or see profile and memory stats.

Follow the standards of SynthKernel, a type-safe and highly modular architecture for modular monolith development in TypeScript.

Set up and run unit tests for Python uv projects and uv workspaces with pytest. Use when creating or updating pytest configuration in pyproject.toml, installing pytest dev dependencies with uv, running tests in a workspace member package via `uv run --package`, customizing pytest workflow defaults through layered YAML profiles, organizing tests with fixtures/markers/parametrize, or troubleshooting test discovery and import failures.

Draft a Conventional Commit message from current repo changes. Use when user asks for commit message help based on staged/unstaged git diff.

Systematic technical investigation—evidence gathering, option comparison, and actionable recommendations. Use when the user asks to "research X", "investigate Y", "look into Z", "compare X vs Y", "how does X work", or needs analysis of libraries, APIs, frameworks, or architectural approaches.

Use when user input needs restructuring for clarity, grammar, formatting, or intent. Also use when the user explicitly invokes this skill. Triggers include dictated text without formatting, messy brain dumps, run-on sentences, poor grammar or typos, pasted blocks of unorganised thoughts, or any input where intent is buried in noise.

Simple task management using a shared TASKS.md file. Reference this when the user asks about their tasks, wants to add/complete tasks, or needs help tracking commitments.

Set up the development environment for the project. Use when starting work on the project, when dependencies are out of sync, or to fix environment setup failures.