Coding & Refactoring Agent Skill

Find, triage, and deep-evaluate GitHub repos for a given need. Use when the user says /repo-eval, asks to find a tool or library, wants to vet a specific repo, or needs to compare alternatives before adopting one.

Use this skill to control Spotify playback, search music, manage playlists, and queue tracks via the spotify_player CLI.

Generates, validates, and refactors production-ready Ansible playbooks, roles, task files, and inventory configurations following current best practices. Use when the user asks to create, build, or generate Ansible automation, YAML playbooks, infrastructure as code, configuration management files, DevOps roles, or .yml files for Ansible — including requests like "create a playbook to...", "build a role for...", "generate an inventory for...", or "set up Ansible to automate...". Automatically validates all output using the devops-skills:ansible-validator skill.

Expert assistant for chezmoi dotfiles management. Use when the user is managing dotfiles with chezmoi: adding files, creating templates, encrypting secrets, writing run scripts, syncing across machines, or diagnosing why changes aren't applying. Trigger phrases: 'add to chezmoi', 'make a template', 'chezmoi apply', 'encrypt with chezmoi', 'run script on first apply', 'sync dotfiles to new machine', 'chezmoi diff shows unexpected changes', 'source attribute', 'dot_ prefix', 'once_ script'.

Validates syntax, checks pipeline tag connections, detects security misconfigurations, audits best practices, and performs dry-run testing for Fluent Bit configurations. Use this skill when working with Fluent Bit config files, validating syntax, checking for best practices, identifying security issues, performing dry-run testing, or troubleshooting configuration-related errors.

Fetches and analyzes GitLab merge request (MR) comments, metadata, and review feedback using authenticated API calls. Capabilities include fetching comment threads, retrieving reviewer feedback, filtering unresolved discussions, and generating MR activity reports. Use when the user asks about GitLab MR comments, code review discussions, review feedback, approval status, troubleshooting review delays, or needs to fetch merge request metadata via the GitLab API.

Comprehensive toolkit for validating, linting, and optimizing Makefiles. Use when working with Makefiles (Makefile, makefile, *.mk files), validating build configurations, checking for best practices, identifying security issues, or debugging Makefile problems. Concrete capabilities include detecting missing .PHONY declarations, validating tab indentation in recipes, checking variable expansion safety, identifying hardcoded credentials, and flagging missing prerequisites or syntax errors.

Search and analyze biomedical literature from PubMed using the free E-utilities API. Use when researching medical topics, discovering clinical papers, fetching article metadata by PMID, performing deep paper analysis, or downloading open-access PDFs from PubMed Central. Triggers: pubmed search, search biomedical literature, find medical papers, PMID lookup, pubmed metadata, clinical literature search, biomedical research, life sciences papers, PMC download, ncbi search.

Comprehensive toolkit for validating, linting, testing, and automating Terragrunt configurations, HCL files, and Stacks. Use this skill when working with Terragrunt files (.hcl, terragrunt.hcl, terragrunt.stack.hcl), validating infrastructure-as-code, debugging Terragrunt configurations, performing dry-run testing with terragrunt plan, working with Terragrunt Stacks, or working with custom providers and modules.

Search Semantic Scholar for academic papers, fetch paper details by ID or DOI, retrieve author profiles, and analyse citation graphs. Preferred over google-scholar-search — uses the official API with no scraping. Triggers: search papers, find papers, semantic scholar, paper details, paper by DOI, paper by ID, author profile, citation analysis, references, literature search, paper discovery.

Design code for testability using boundary isolation, dependency injection, and testable architecture patterns. Use when designing test strategies, writing unit tests, improving test coverage, refactoring untestable or hard-to-test code, working with mocking or test doubles, or applying TDD practices.

Held-out fixture with a mismatched directory name.

Comprehensive toolkit for validating, linting, testing, and automating Ansible playbooks, roles, and collections. Use this skill when working with Ansible files (.yml, .yaml playbooks, roles, inventories), validating automation code, debugging playbook execution, performing dry-run testing with check mode, or working with custom modules and collections.

Generate GNU Make build systems that define build targets, configure dependencies, set up phony targets, and implement parallel builds. Use when creating make/Makefile/.mk files, implementing compile rules, or building production-ready build automation for C/C++, Go, Python, and Java projects.

Debug a running PostgreSQL backend with lldb / gdb — covers attaching to the right forked backend via pg_backend_pid, single-user mode for postmaster / InitPostgres startup paths, breakpoints in ExecInitNode / heap_update / LWLockAcquire, elog(LOG, ...) printf-debugging, macOS / Linux core-dump configuration, and SQL-level inspection via pg_buffercache / pageinspect / pg_visibility. Use whenever the user wants to step through backend C code, attach lldb / gdb to a specific dev-cluster backend, chase a SIGSEGV / hang / loop / assertion-failure in PG, instrument with elog, inspect shmem / buffer / lock state at runtime, or read a PG core dump. Skip for app-level debugging in Node.js / Python / Ruby / Go / Rust (use language-specific debuggers), JVM hprof / jstack, browser DevTools, Chrome Tracing, application performance profiling, and production PG tuning (autovacuum / shared_buffers — that's DBA work).

Use this skill whenever an agent needs to call, integrate, debug, or write code against the Bila UiTM Cuti API (api.bilauitmcuti.com) — UiTM academic calendar data (sessions, calendar activities, today's status, lecture weeks 1-14) and Malaysia public holiday data. Trigger this any time the user mentions "Bila UiTM Cuti", "bilauitmcuti", "bilacuti.my", UiTM academic calendar/session/semester data, UiTM lecture weeks, Group A / Group B UiTM schedules, or Malaysia public holiday lookups by state/year, even if they don't give the exact endpoint URL. Also use this before writing any fetch/axios/requests call, API client, cron job, Discord/Telegram bot command, or Cloudflare Worker route that talks to api.bilauitmcuti.com, to make sure the correct base URL, query params, and response shape are used.

Runs repeatable AI work as checked, budgeted workflow files.

Invoke when a solo developer asks an agent to cut a release of a library or CLI — bumping the version, tagging, pushing, publishing to a registry (npm or PyPI), and creating a GitHub release. Trigger phrases include "ship it", "cut a release", "publish to npm/PyPI", "tag and release", "bump the version", or "make a GitHub release". Use it whenever the task is turning committed code into a published, versioned artifact. Do NOT invoke for routine commits, opening a normal PR, CI config changes, deploying a running service (that is deployment, not package release), or pre-release exploratory coding. If no publishable package manifest (package.json, pyproject.toml, setup.py) exists, stop and say so instead of guessing.