rails-app
claudeRails applications (Phlex, DaisyUI, phlex-reactive, ActionPolicy, RSpec): the layer specialists, AppSignal debugging and triage.
14 skills
Every repository: /flow:lfg (issue to merge-ready PR), /flow:follow-through (epic to merged, unattended), /flow:finish-prs, /flow:plan (incl. upstream fixes carried to a release), /flow:effort, /flow:github-review-*, /flow:tdd, /flow:review-pr, /flow:debug-flaky, flow:fable-validator.
Plugin flow from marketplace zoolutions in zoolutions/claude-plugins. Commands read from the repo's manifest — 8 days ago.
debug-flakyRoot-cause an intermittent test failure from a failed CI run, a PR or a test path — evidence, a forced reproduction, the mechanism in one sentence, a fix proven in both directions. Use when a test fails only sometimes; never masks it with a retry, sleep, skip or loosened assertion.
effortWhat a pull request cost and how far it strayed from its estimate — time (wall clock, active, before and after the PR opened), tokens per role and model (the session, each agent type, the advisor), validation passes and verdicts, review rounds and threads, commits and the diff — measured from this m
finish-prsDrive open PRs to merge-ready, one at a time, in a given order — merge main in, then rounds of /flow:github-review-pr (conflicts, CI failures, every review thread) until CI is green, no thread is open and the review bot has nothing new; then wait for the user to merge. With `automerge`, merge each P
follow-throughDrive an epic (or any issues) from plan to merged, unattended — dependency waves, /flow:lfg per issue in its own worktree through one Opus agent each, /flow:finish-prs automerge on every PR, and upstream library fixes carried through to a release and an adoption issue. Parks what it cannot settle an
github-review-commentsAnswer every unresolved review thread on a PR — human or bot (cubic, CodeRabbit) — by fixing what is right and pushing back, with reasons from the code, on what is wrong; then resolve every thread. Use when a PR has open review comments; /flow:github-review-pr runs it as its Phase B.
github-review-failuresFix every failing CI check on a PR — fetch the failed job logs (and a merge-queue eviction report), diagnose the root cause, fix, verify locally, push. Use when a PR's checks are red; /flow:github-review-pr runs it as its Phase A.
github-review-prOne full review pass on a PR, strictly in order — merge conflicts with the base, then CI failures (/flow:github-review-failures), then every review thread (/flow:github-review-comments). Use when a PR needs to get to green and thread-free; /flow:finish-prs runs it once per round.
lfgThe full engineering workflow for one issue or description, from a fresh branch to a merge-ready PR — understand, explore, plan, TDD, verify, Fable validation by rigor tier, PR, then /flow:finish-prs until CI is green and every review thread is answered. Never merges. Use for any non-trivial feature
planInvestigate, design and write a self-contained plan — a GitHub issue (default) or docs/plans/ markdown — that /flow:lfg executes without guessing, with the effort estimate its PR is measured against. `upstream <owner/repo> <limitation>` plans a public issue for a library limitation and, for a librar
review-prReview a pull request for bugs and breaches of the repository's written rules — five parallel reviewers, then an independent confidence score per finding; only findings scoring 80 or more are reported. Read-only; with `post` it posts the review as one PR comment.
tddImplement a behaviour or fix a bug test-first — RED (a failing test, seen failing for the right reason), GREEN (the least code that passes), REFACTOR (still green), then the repository's checks. Use for any feature or bug fix, alone or as /flow:lfg's implementation step.
fable-validatorFinal validation of a finished implementation on Fable, before its pull request opens or merges. Use at the end of /lfg and of any change to a public API, a schema or migration, security, payments, a release, or anything irreversible. Read-only: it reads the issue, the acceptance criteria and the di
Rails applications (Phlex, DaisyUI, phlex-reactive, ActionPolicy, RSpec): the layer specialists, AppSignal debugging and triage.
14 skills
Ruby libraries: an unattended release (version, changelog, frozen lockfiles), branch-versus-main benchmarks.
2 skills
Every machine agents run on: /machine:reap reports and reaps leftover agent processes (orphans, stale wait loops, runners in removed worktrees, headless or idle claude sessions) and keeps test runs at background priority. Enabled per machine at user scope; its schedule and SessionStart line are wired from its README.
1 skill
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.