ai-skills

Creates and maintains CHANGELOG.md in Keep a Changelog format, including adding entries and cutting releases. Use when the user asks to update the changelog, add a changelog entry, or record a release.

Writes brief conventional-commit messages, runs pre-commit checks, stages changes, commits them, and proposes splitting when the diff mixes concerns. Use when the user asks to commit, stage and commit, write a commit message, or split a change into atomic commits.

Technical documentation expert for creating clear, comprehensive documentation including API docs (OpenAPI), ADRs, system architecture docs, developer guides, and runbooks. Use when creating or improving technical documentation.

Step-by-step procedure for producing ONE advisory COMMENT review on a Forgejo pull request — clone at the head sha, fetch the diff, apply general and language review criteria, post a single Reviews-API review with inline comments, recover from 422s, then verify and close the kanban card. Use when a kanban card assigns an advisory PR review on git.home.claydon.co.

Generates and verifies eval scenarios for a repository plugin — covering its skills, commands, and hooks — using the tessl-compatible evals/ layout (task.md, criteria.json, scenario.json) so they run under `tessl eval run` and grade offline with any judge. Authors self-gradable scenarios, runs the offline verification ladder, and commits. This skill never restructures plugins. Use when the user asks to build evals for a plugin, generate eval scenarios, or verify that a skill actually works.

Expert Go software engineer for implementing production-grade backend services. Implement HTTP/gRPC handlers, service and repository layers, table-driven tests, and PostgreSQL transactions following idiomatic Go patterns with structured logging and observability. Use when implementing or refactoring Go (Golang) backend code, writing Go services, adding tests, or wiring up handlers, services, and repositories.

Senior Go engineer and technical advisor — use for any Go question, design decision, or implementation task. Covers idiomatic patterns, concurrency, error handling, project structure, performance optimisation, observability, and testing. Invoke whenever the user is writing, reviewing, debugging, or designing Go code, asking about goroutines, channels, interfaces, generics, modules, or benchmarks, or wants a second opinion on a Go architecture. Triggers on: Go, Golang, goroutine, channel, interface, gRPC, go.mod, go test, pprof, golangci-lint.

Senior Go code reviewer for comprehensive code reviews focused on correctness, security, performance, and maintainability. Use when reviewing Go code for bugs, best practices, and production readiness.

Engineering manager agent for orchestrating complex software development tasks by coordinating specialized sub-agents and managing parallel work streams. Use for large initiatives requiring coordination across multiple specialists.

Senior Staff Engineer mentor for architecture, design decisions, technical mentorship, and career guidance. Use when seeking senior-level perspective on system design, code review, technical strategy, or career growth.

Expert guidance on Nix, NixOS, home-manager, flakes, and Nix packaging. Use when writing or debugging Nix expressions, configuring NixOS or home-manager, authoring derivations, managing flake inputs, encrypting secrets with agenix or sops-nix, or hardening a NixOS host. Also use when committing or reviewing a flake.lock or `nix flake update` result, pinning or overriding a flake input, and when reviewing or deploying a NixOS config change (especially to a remote host) before it is applied. Triggers on Nix, NixOS, nixpkgs, home-manager, flake.nix, flake.lock, nix flake update, nixos-rebuild, nix build, nix develop, devShell, derivation, overlay, agenix, and on Nix errors such as hash mismatches, infinite recursion, or evaluation failures. Advisory rather than generative: it explains, reviews, and debugs. If the repository provides its own skill for authoring host configurations, prefer that for writing config.

Creates a draft GitHub pull request with a plain-text conventional-commit title and a succinct description of the branch. Use when the user asks to open, raise, or create a pull request or PR.

Reviews eval scenarios and skills with judgement, covering what a deterministic gate cannot - whether a scenario discriminates, whether a rubric is fair to the unit it tests, whether a recording shim is faithful, and whether a skill's description and body guide an agent. Also grades the criteria an eval run left pending. Use when asked to review a pull request that touches a skill or an eval scenario, to judge an eval run, or to check that a set of evals actually proves what it claims.

Reviews Bash, Zsh, and Fish shell scripts for bugs, security vulnerabilities, portability issues, and style violations against the Google Shell Style Guide, ShellCheck, BashPitfalls, and shell-specific idiom conventions. Use when the user asks to review, audit, lint, or improve a .sh/.bash/.zsh/.fish file, or pastes shell script content for feedback.

Software specification expert for transforming high-level designs into detailed, implementable technical specifications. Use when converting requirements or designs into precise specs that developers can implement directly.

Task decomposition expert for breaking technical specifications into atomic, implementable tasks with dependencies and priorities. Use when converting specs into actionable task lists for development teams.

Triage PR review comments by classifying feedback, accepting actionable suggestions, rejecting non-applicable ones with explanations, and creating tracked follow-up tasks. Use when processing code review feedback on pull requests.