Catalog
All AI skills
23 skills. Every one is readable here; downloads and live use need a subscription.
ai-loop
Runs a bounded spec-build-review development loop with explicit scope, stop conditions, and human approval gates for risky or ambiguous work.
closed-loop-delivery
Use when a coding task must be completed against explicit acceptance criteria with minimal user re-intervention across implementation, review feedback, deployment, and runtime verification.
loop-library
Find, compare, adapt, and design bounded AI-agent feedback loops with explicit checks, stop rules, guardrails, and handoffs.
ux-feedback
Add appropriate user feedback states (loading, success, error, empty) to a component or page
goal-loop
Draft and explain persistent goal-loop prompts for long-running agent work with clear stop conditions.
spec-driven-loop
Freeze PRD, technical design, and acceptance criteria before medium-to-large Codex work; coordinate agents with explicit ownership, then judge delivery from diffs, tests, and evidence.
stitch-loop
Teaches agents to iteratively build websites using Stitch with an autonomous baton-passing loop pattern
brooks-test
Review test-suite quality using established testing literature; identify brittleness, mock abuse, unclear fixtures, weak assertions, slow feedback, and maintenance risks.
code-review-excellence
Transform code reviews from gatekeeping to knowledge sharing through constructive feedback, systematic analysis, and collaborative improvement.
crossframe-org
Use when CrossFrame Suite routes explicit Chinese analysis of teams, projects, organizations, responsibility chains, feedback write-back, repair, or retrospectives.
dx-optimizer
Developer Experience specialist. Improves tooling, setup, and workflows. Use PROACTIVELY when setting up new projects, after team feedback, or when development friction is noticed.
iterate-pr
Iterate on a PR until CI passes. Use when you need to fix CI failures, address review feedback, or continuously push fixes until all checks are green. Automates the feedback-fix-push-wait cycle.
progressive-estimation
Estimate AI-assisted and hybrid human+agent development work with research-backed PERT statistics and calibration feedback loops
shopify-review-triage
Turn public 1-3-star Shopify App Store review rows into a P0-P3 triage brief: incident risk, repeated friction, pricing confusion, feature requests, and an explicit needs-human-read bucket.
vibers-code-review
Human review workflow for AI-generated GitHub projects with spec-based feedback, security review, and follow-up PRs from the Vibers service.
accesslint-audit
Find and fix WCAG 2.2 accessibility issues. Two modes — report (sweep a codebase or page, produce a prioritized written report, no edits) and fix (audit→edit→verify loop on a target). Prefers direct-CDP live-DOM auditing; falls back to a browser-MCP composition or HTML-string audits.
accint-solve
Route a goal through acc's scored-memory loop via acc_act(runtime="solve"); deliberate any returned brain_frame and submit via continue.
diagnosing-bugs
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
invariant-guard
Correctness-first: forces writing the function contract, loop invariant, termination argument, and edge cases BEFORE code. Catches Boyer-Moore, leftmost binary search, QuickSelect traps.
langgraph
Expert in LangGraph - the production-grade framework for building stateful, multi-actor AI applications. Covers graph construction, state management, cycles and branches, persistence with checkpointers, human-in-the-loop patterns, and the ReAct agent pattern.
lookdev
Human-in-the-loop web studio to tune AI-generated output by eye. Stand up a local interactive studio (sliders, pickers, drag handles) or an inline edit/highlight/comment annotation studio for prose & media, instead of guessing values or shipping a static comparison grid.
lookdev-auto
Automated visual tuning: a vision or video model rates rendered variants in a loop. Render several labeled variants into one artifact, ask the model to rate them and suggest better values, render the suggestions, ask it to pick the best, repeat until good — the model is the eye, you run the loop.