cobusgreyling/loop-engineering: 15 Agent Skills
Practical patterns, starters & CLI tools for loop engineering with AI coding agents. Design systems that prompt and orchestrate agents (inspired by Addy Osmani and Boris Cherny). Includes loop-audit, loop-init, loop-cost.
| Repository | cobusgreyling/loop-engineering · website |
|---|---|
| GitHub stars | 11,614 |
| Skills | 15 |
| Category | Design and frontend |
| License | MIT |
| Last updated | Oct 23, 2026 |
| Install counts | cobusgreyling/loop-engineering on skills.sh, Vercel's skills directory, which shows installs and security audits per skill |
Install cobusgreyling/loop-engineering
| All skills, any agent | npx skills add cobusgreyling/loop-engineering |
|---|---|
| One skill | npx skills add cobusgreyling/loop-engineering --skill budget-negotiator |
| Only for Claude Code | npx skills add cobusgreyling/loop-engineering -a claude-code, or copy a skill folder to ~/.claude/skills/ (all projects) or .claude/skills/ (one project) |
npx skills is the open-source skills CLI; it asks which agents to install for. Skills can include scripts that your agent will run: read a skill before installing it, as you would any code.
Skills in cobusgreyling/loop-engineering
| Skill | What it does |
|---|---|
| budget-negotiator | An advanced skill for L3 autonomous loops. When the token budget nears exhaustion, the agent analyzes its ROI and autonomously drafts a negotiation request for a budget increase rather than silently failing.npx skills add cobusgreyling/loop-engineering --skill budget-negotiator |
| install-loop | Install Loop Engineering into a project via the unified CLI front door (@cobusgreyling/loop). Prefer this over invoking loop-init / loop-audit separately. Week-one is report-only; never enable auto-merge or unattended fixes unless the human explicitly asks and doctor is healthy.npx skills add cobusgreyling/loop-engineering --skill install-loop |
| loop-budget | Check token budget and run-log spend before and after a loop run. Enforces early exit when over budget or when there is no actionable work.npx skills add cobusgreyling/loop-engineering --skill loop-budget |
| loop-constraints | Read loop-constraints.md at the start of every run and enforce every rule. This skill runs BEFORE triage or any action skill. Constraints are binding.npx skills add cobusgreyling/loop-engineering --skill loop-constraints |
| loop-triage | Triage recent changes, CI failures, issues, and conversations. Produces a concise, actionable findings report suitable for a loop to consume. Writes structured output to a state file or Linear board.npx skills add cobusgreyling/loop-engineering --skill loop-triage |
| loop-verifier | Independent verification agent for loop-produced changes. Finds reasons to reject. Runs tests. Confirms diff scope. Use after minimal-fix or any implementer sub-agent — never in the same role as the implementer.npx skills add cobusgreyling/loop-engineering --skill loop-verifier |
| minimal-fix | Produce the smallest possible code change that fixes a specific, well-scoped issue (CI failure, reviewer comment, typo). Use only when the fix target is explicit. Never refactor unrelated code.npx skills add cobusgreyling/loop-engineering --skill minimal-fix |
| changelog-scan | Scan merged PRs and commits since a given reference, extract titles, labels, types, and signals. Produces structured input for release notes drafting.npx skills add cobusgreyling/loop-engineering --skill changelog-scan |
| draft-release-notes | Turn changelog-scan output into polished, categorized release notes draft. Propose only.npx skills add cobusgreyling/loop-engineering --skill draft-release-notes |
| ci-triage | Classify CI failures — distinguish clear regressions from infra flakes and security-test failures. Produces structured failure reports.npx skills add cobusgreyling/loop-engineering --skill ci-triage |
| dependency-triage | Scan package manifests and lockfiles for outdated and vulnerable dependencies. Classify by severity and update type.npx skills add cobusgreyling/loop-engineering --skill dependency-triage |
| issue-triage | Scan open issues and discussions, deduplicate, prioritize, and propose labels. Provides a clean actionable queue.npx skills add cobusgreyling/loop-engineering --skill issue-triage |
| post-merge-scan | Scan recent merges to main for tech debt, TODOs, debug code, and small cleanup opportunities. Produces a prioritized fix list.npx skills add cobusgreyling/loop-engineering --skill post-merge-scan |
| pr-review-triage | Watch open PRs, check CI status, review staleness, merge conflicts, and unanswered review comments. Produces a prioritized watchlist.npx skills add cobusgreyling/loop-engineering --skill pr-review-triage |
| goal-verifier | Verify goal completion.npx skills add cobusgreyling/loop-engineering --skill goal-verifier |
Names and descriptions come from each skill's SKILL.md and are written by the pack's authors.
More design and frontend skill packs
| # | Skill pack | Skills | GitHub stars | Updated |
|---|---|---|---|---|
| 1 |
nextlevelbuilder/ui-ux-pro-max-skill An AI skill that provides design intelligence for building professional UI/UX across multiple platforms.
|
7 | 139K | 2026-10-23 |
| 2 |
Leonxlnx/taste-skill Agent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
|
1 | 101K | 2026-10-20 |
| 3 |
tt-a1i/archify Turn any idea, plan, or codebase into a beautiful interactive diagram. An agent skill for Claude Code, Codex, and more.
|
5 | 88K | 2026-10-23 |
| 4 |
pbakaus/impeccable The design language that makes your AI harness better at design.
|
2 | 85.2K | 2026-10-23 |
| 5 |
cathrynlavery/diagram-design Editorial diagram design for Claude Code, Codex, GitHub Copilot, Cursor, Factory Droid, Qoder, and Pi. 45 diagram types. Self-con…
|
1 | 60.2K | 2026-10-21 |
| 6 |
openai/skills Skills Catalog for Codex
|
43 | 28.3K | 2026-09-08 |