jeffutter

Use when researching state-of-the-art algorithms for a problem, finding academic papers, comparing algorithm approaches, needing paper citations, or user invokes /algorithm-research

Use when researching algorithms, data structures, optimization, performance, or need modern alternatives to classic algorithms

Use when creating benchmarks, measuring performance, comparing implementations, or user invokes /benchmark. Provides step-by-step workflow for benchmark creation, data generation, and results interpretation.

Use when analyzing code cognitive load, onboarding difficulty, or user invokes /cognitive-audit for complexity analysis and refactoring recommendations

Use when analyzing cognitive load, code complexity, onboarding difficulty, readability concerns, maintainability issues, or applying Ousterhout principles for deep modules, reducing complexity, and strategic programming approaches

Use when implementing concurrent operations, choosing between concurrency models, designing async workflows, or working with parallel data processing

Use when validating input data, implementing parse-don't-validate patterns, designing validation pipelines, or handling external data safely

Use when reviewing distributed system code, checking for distributed bugs (split-brain, quorum errors, clock drift), or user invokes /distributed-review

Audit the last N completed backlog tickets that the autonomous `pi` loop finished, judging the work on Correctness, Conciseness, Clarity, Organization, and Resilience. File any required fixes as tightly-scoped backlog tickets with thorough plans and proper dependencies so the next `pi` round course-corrects. Invoke when checking in on pi's progress, e.g. "review pi's last few tickets".

Autonomous execution skill for tickets (backlog). Use when implementing a ticket (TASK-xxx).

Use when querying, managing, or automating Actual Budget via the command line — accounts, transactions, budgets, categories, payees, schedules, rules, or AQL queries against an Actual Budget server.

Use acli CLI for Atlassian operations — primarily Jira work item management, project operations, sprint tracking, and board management with JQL search. Also covers Confluence page/space/blog operations and a CQL search fallback (acli has no native Confluence search).

Autonomous planning skill for tickets (backlog). Use when planning implementation for a ticket (TASK-xxx). Spawns research subagents, analyzes dependencies, creates sub-tickets for discrete work, and writes detailed implementation plans.

Write or rewrite content in my authentic voice using my voice DNA profile. Use when drafting technical docs, blog posts, RFCs, proposals, or reviewing/editing prose for voice consistency.

Guidelines and best practices when writing Elixir code. Claude should use this skill whenever asked to modify, evaluate or review Elixir files (.ex or .exs).

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

Audit the last N completed backlog tickets that the autonomous `pi` loop finished, judging the work on Correctness, Conciseness, Clarity, Organization, and Resilience. File any required fixes as tightly-scoped backlog tickets with thorough plans and proper dependencies so the next `pi` round course-corrects. Invoke when checking in on pi's progress, e.g. "review pi's last few tickets".

Update this flake to a new Apollo Router release. Bumps the `router-src` flake input, pins the matching upstream Rust version from `rust-toolchain.toml`, refreshes `cargoHash`, runs `nix flake update`, verifies the build, then commits and tags. Takes one argument: the target router version (with or without leading `v`).

Use when releasing a new version of notectl — bumps version in Cargo.toml, updates Cargo.lock, commits, pushes, tags, and pushes the tag.