Reviews a pull request, branch, or worktree against its claim, repository standards, reproducible behavior, and churn-backed architectural risks. It can delegate evidence gathering by review axis, limit findings to exact files, revalidate prior review or audit JSON, and optionally fix selected findings or all in-scope findings. Use when the user runs /code-review or asks for an evidence-backed review of a bounded change.
Investigates and creates a project-aligned GitHub issue from a tagline or short description, using the repository's template, evidence, and labels. Use when the user runs /create-issue or asks to file a GitHub issue.
Publishes a completed change as a templated draft pull request, reconciles PR-only metadata and readiness state, waits for CI, and marks it ready. Use when the user runs /create-pr.
Provides deterministic, resumable GitHub transition waits used internally by delivery workflows. Use when another workflow must await CI, merge, tag, or release state without model heartbeats.
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
Turns an unfiled idea into a confirmed mini-spec, implements the selected approach, repeats code review and black-box testing, runs the project gate, and opens a draft pull request. Use when the user runs /implement-idea or asks to build something without an existing issue.
Validates and implements a GitHub issue against current repository evidence, repeats code review and black-box testing, runs the project's completion gate, and opens a draft pull request. Use when the user runs /implement-issue with an issue number.
Applies the user's language-agnostic repository layout, documentation, governance, hook, test, agent-file, and changelog conventions. Use when scaffolding or restructuring a repo, writing AGENTS.md or docs, or laying out folders.
Reviews a roadmap from fresh project evidence and produces a verified, throughput-anchored version plan, with execution gated on confirmation. Use when reviewing a roadmap, planning releases, or sequencing a backlog.
Applies the user's ambient engineering bar: objective retention, current evidence, complete in-scope solutions, reuse, real validation, maintainability-governed performance, and fast developer feedback. Use when planning, orchestrating, implementing, debugging, reviewing, refactoring, architecture, release delivery, or substantial technical investigation.
Commits relevant changes, merges the remote default when needed, pushes the current pull-request branch, and refreshes stale PR metadata. Use when the user runs /update-pr or asks to update a pull request.
Resolves review feedback on one pull request or native GitHub stack. Use when asked to address, fix, or respond to review comments on a PR or stack, or when the user runs /address-feedback.
Audits agent execution records for instruction compliance, outcome quality, and wasted work using source-backed evidence. Use when asked to audit or analyze how an agent behaved in past sessions, transcripts, or logs.
Writes clear, concise agent replies and engineering artifacts while preserving evidence, decisions, and required detail. Use when drafting a final response or report for engineering work, PR or issue text, or documentation.
Biases technology choices toward the newest viable option while preserving maintainability, live verification, reversibility, and decided constraints. Use when selecting or upgrading a dependency, runtime, tool, language feature, or AI model.
Audits a repository or subsystem for systemic engineering risks and actionable improvements; assessment only unless follow-up fixes are selected. Use when asked to audit a codebase, assess its health or technical debt, or find systemic risks.
Reviews a PR, branch, or worktree for evidence-backed findings, with scoped revalidation and explicitly requested fixes. Use when asked to review code changes, a diff, a branch, or a PR, or to recheck earlier review findings.
Applies the user's Convex backend conventions while deferring mechanics to upstream Convex skills and current APIs to the live Convex docs. Use when scaffolding, reviewing, or refactoring Convex functions, schemas, or auth.
Investigates and creates a project-aligned GitHub issue from a tagline or short description, using the repository's template, evidence, and labels; shows a draft first only when asked. Use when asked to file, open, or create a GitHub issue, or when the user runs /create-issue.
A folder with a SKILL.md file: a name, a description of when to use it, and instructions. Claude loads a skill only when the task matches its description.
How do I use one I find here?
Copy the folder into your project's .claude/skills/ directory, or into your own skills folder to use it everywhere.
What do the warnings mean?
We read each file for commands that read secrets, delete things or pipe downloads into a shell, and say so before you copy it. No warning is not a promise that a file is safe.
Which skills worked for people?
Open a skill to see its discussion. Reports from people and their agents are coming.
frostneySkill