Repository
cobusgreyling/loop-engineering agent skills
- skills
- 21
- GitHub stars
- 11k
GitHub description: “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.”
- Stars
- 11,429 (1,532 forks)
- Licence
- MIT
- Last push
- Oct 2026
- Created
- Jun 2026
- agentic-ai
- ai-agents
- claude-code
- codex
- devops-automation
- github-actions
- grok
- llm
- mcp
- ai-coding
- automation
- loop-engineering
- prompt-engineering
- anthropic
- claude
- coding-agents
Install all skills
npx skills add cobusgreyling/loop-engineeringAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in cobusgreyling/loop-engineering, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Installs Loop Engineering into a project through the single @cobusgreyling/loop CLI, scaffolding a report-only loop and a readiness score. | cobusgreyling/ | 11k | 1 repo | ~648 | Automated safety check: Pass | MIT | today |
| 2 | Loads a project's loop-constraints.md before any other action and blocks pushes, edits or merges that violate the rules it defines. | cobusgreyling/ | 11k | 1 repo | ~475 | Automated safety check: Notes | MIT | today |
| 3 | Turns a structured list of changes from changelog-scan into a categorized, user-facing release notes draft file, and never publishes anything. | cobusgreyling/ | 11k | — | ~555 | Automated safety check: Pass | MIT | today |
| 4 | Scans open GitHub issues and discussions, flags duplicates, scores priority and proposes labels into issue-triage-state.md without ever labeling or closing. | cobusgreyling/ | 11k | — | ~522 | Automated safety check: Pass | MIT | today |
| 5 | Turns CI failures, open issues, recent commits and chat threads into a prioritized markdown report that an automation loop can act on without inventing architecture work. | cobusgreyling/ | 11k | — | ~500 | Automated safety check: Pass | MIT | today |
| 6 | 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. | cobusgreyling/ | 11k | 1 repo | ~376 | Automated safety check: Pass | MIT | today |
| 7 | Tracks open pull requests and records CI state, staleness, merge conflicts and unanswered review comments in a state file, then lists the top three actions for a human. | cobusgreyling/ | 11k | — | ~480 | Automated safety check: Pass | MIT | today |
| 8 | Acts as a skeptical checker for changes an implementer sub-agent made, running the tests, confirming the diff scope and returning approve, reject or escalate to a human. | cobusgreyling/ | 11k | 1 repo | ~383 | Automated safety check: Pass | MIT | today |
| 9 | Makes the smallest code change that fixes one well-scoped problem, such as a CI failure, review comment or typo, without refactoring anything unrelated. | cobusgreyling/ | 11k | 1 repo | ~345 | Automated safety check: Notes | MIT | today |
| 10 | Scans merges to main since the last tag or date, extracting titles, labels and breaking-change or security signals as structured input for a release notes drafter. | cobusgreyling/ | 11k | — | ~453 | Automated safety check: Pass | MIT | today |
| 11 | Scans package manifests and lockfiles for outdated packages and known CVEs, then classifies each possible update as patch, minor, major or escalate-human for a dependency sweeper loop. | cobusgreyling/ | 11k | — | ~300 | Automated safety check: Pass | MIT | today |
| 12 | An advanced skill for L3 autonomous loops. An agent skill from cobusgreyling/loop-engineering. | cobusgreyling/ | 11k | 1 repo | ~864 | Automated safety check: Pass | MIT | today |
| 13 | 13.Loop Triage Triage recent changes, CI failures, issues, and conversations. | cobusgreyling/ | 11k | 1 repo | ~538 | Automated safety check: Pass | MIT | today |
| 14 | Acts as an independent checker for drafted release notes, comparing them with the scan data and returning an APPROVE, REVISE or ESCALATE_HUMAN verdict with evidence. | cobusgreyling/ | 11k | — | ~319 | Automated safety check: Pass | MIT | today |
| 15 | Scan recent merges to main for follow-up cleanup: TODOs, deprecations, broken doc links, stale flags. | cobusgreyling/ | 11k | — | ~229 | Automated safety check: Pass | MIT | today |
| 16 | Triage open pull requests for CI status, review comments, and merge readiness. | cobusgreyling/ | 11k | — | ~425 | Automated safety check: Pass | MIT | today |
| 17 | Scan merged PRs and commits since a given reference, extract titles, labels, types, and signals. | cobusgreyling/ | 11k | — | ~206 | Automated safety check: Pass | MIT | today |
| 18 | 18.CI Triage Parse CI failures, identify failing job/step, classify as flake, regression, env, or config. | cobusgreyling/ | 11k | — | ~192 | Automated safety check: Pass | MIT | today |
| 19 | Scan package manifests and lockfiles for outdated and vulnerable dependencies. | cobusgreyling/ | 11k | — | ~206 | Automated safety check: Pass | MIT | today |
| 20 | 20.Issue Triage Scan open issues and discussions, deduplicate, prioritize, and propose labels. | cobusgreyling/ | 11k | — | ~212 | Automated safety check: Pass | MIT | today |
| 21 | Scan recent merges to main for tech debt, TODOs, debug code, and small cleanup opportunities. | cobusgreyling/ | 11k | — | ~208 | Automated safety check: Pass | MIT | today |
Questions, answered from the data.
What is the best skill in cobusgreyling/loop-engineering?
Install Loop Engineering from cobusgreyling/loop-engineering ranks first of the 21 skills in cobusgreyling/loop-engineering listed here, with the highest score: its repository has 11k GitHub stars, 1 other GitHub owner carry a copy, its SKILL.md loads about 648 tokens and it passes the automated safety check with no findings. Next come Loop Constraints Enforcer and Release Notes Drafter.
Are the skills in cobusgreyling/loop-engineering official?
None yet. All 21 skills in cobusgreyling/loop-engineering listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How do I install all skills from cobusgreyling/loop-engineering?
Run npx skills add cobusgreyling/loop-engineering in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.