GitHub user
Agent skills by zereight
- skills
- 24
- repository
- 1
Repositories by zereight
Skills by zereight, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Detects which autonomous OMG mode is currently active - Autopilot, Ralph, Ultrawork, UltraQA, Team or Self-Improve - and shuts it down cleanly. | zereight/ | 2k | 1 repo | ~690 | Automated safety check: Pass | MIT | yesterday |
| 2 | Runs a task through Codex and Gemini CLIs in parallel alongside Claude, then synthesizes the three outputs into one answer with agreements and conflicts called out. | zereight/ | 2k | 1 repo | ~657 | Automated safety check: Pass | MIT | yesterday |
| 3 | Shared reference for naming, function size, complexity and error handling rules that reviewer agents apply across TypeScript, Python, Go, Rust, Java, C# and Swift. | zereight/ | 2k | 1 repo | ~1.4k | Automated safety check: Pass | MIT | yesterday |
| 4 | Sorts what you learned in a session into the right memory surface, filtering out ephemeral notes and duplicates before anything is stored. | zereight/ | 2k | 1 repo | ~846 | Automated safety check: Pass | MIT | yesterday |
| 5 | Runs a fast security sweep of recent code changes before a commit or PR, checking for leaked secrets, vulnerable dependencies, unsafe input handling and auth gaps. | zereight/ | 2k | 1 repo | ~859 | Automated safety check: Notes | MIT | yesterday |
| 6 | Audits a project's skill directories for broken frontmatter, missing template sync and quality gaps, then produces a health report of what needs fixing. | zereight/ | 2k | 1 repo | ~1k | Automated safety check: Pass | MIT | yesterday |
| 7 | Reports which OMG modes are active, such as autopilot, ralph, team, ultraqa and self-improve, with phase, story or cycle progress read from their state files. | zereight/ | 2k | 1 repo | ~441 | Automated safety check: Pass | MIT | yesterday |
| 8 | Enforces strict red-green-refactor, with a failing test first, the minimum code to pass it, then cleanup, and a quick reference for common test runners. | zereight/ | 2k | 1 repo | ~904 | Automated safety check: Pass | MIT | yesterday |
| 9 | Runs an autonomous evolutionary loop that improves a codebase against a measurable benchmark, using agent roles, tournament selection and recorded history until a stop condition. | zereight/ | 2k | 1 repo | ~1.8k | Automated safety check: Warn | MIT | yesterday |
| 10 | Spawns a chosen number of coordinated agents on a shared task list and runs them through plan, requirements, execution, verification and fix stages. | zereight/ | 2k | 1 repo | ~1.5k | Automated safety check: Pass | MIT | yesterday |
| 11 | 11.Trace Evidence-driven tracing with competing hypotheses in parallel. | zereight/ | 2k | 1 repo | ~412 | Automated safety check: Pass | MIT | yesterday |
| 12 | Authenticates and runs zereight-mcp-gitlab as a plain command line tool to read GitLab merge requests, diffs, discussions, issues and pipelines when no MCP client is set up. | zereight/ | 2k | — | ~787 | Automated safety check: Pass | MIT | yesterday |
| 13 | 13.Ultraqa QA cycling workflow - test, verify, fix, repeat until goal met. | zereight/ | 2k | 1 repo | ~379 | Automated safety check: Pass | MIT | yesterday |
| 14 | 14.Ultrawork Parallel execution engine for high-throughput task completion. | zereight/ | 2k | 1 repo | ~369 | Automated safety check: Pass | MIT | yesterday |
| 15 | 15.Deep Dive 2-stage pipeline: trace (causal investigation) then deep-interview (requirements). | zereight/ | 2k | 1 repo | ~536 | Automated safety check: Pass | MIT | yesterday |
| 16 | Socratic deep interview with mathematical ambiguity gating. An agent skill from zereight/gitlab-mcp. | zereight/ | 2k | 1 repo | ~725 | Automated safety check: Pass | MIT | yesterday |
| 17 | Full autonomous execution from idea to working code. An agent skill from zereight/gitlab-mcp. | zereight/ | 2k | 1 repo | ~713 | Automated safety check: Pass | MIT | yesterday |
| 18 | 18.Plan Strategic planning with optional interview workflow. An agent skill from zereight/gitlab-mcp. | zereight/ | 2k | 1 repo | ~509 | Automated safety check: Pass | MIT | yesterday |
| 19 | 19.Ralph PRD-driven persistence loop until task completion with verification. | zereight/ | 2k | 1 repo | ~711 | Automated safety check: Pass | MIT | yesterday |
| 20 | Clean AI-generated code slop with regression-safe workflow. An agent skill from zereight/gitlab-mcp. | zereight/ | 2k | 1 repo | ~361 | Automated safety check: Pass | MIT | yesterday |
| 21 | 21.Ralplan Consensus planning with Planner/Architect/Critic iterative loop. | zereight/ | 2k | 1 repo | ~365 | Automated safety check: Pass | MIT | yesterday |
| 22 | 22.Review Code review with spec compliance and quality checks. An agent skill from zereight/gitlab-mcp. | zereight/ | 2k | 1 repo | ~226 | Automated safety check: Pass | MIT | yesterday |
| 23 | 23.Verify Verify that a change really works before claiming completion. | zereight/ | 2k | 1 repo | ~256 | Automated safety check: Pass | MIT | yesterday |
| 24 | A skill your agent uses when working with the GitLab MCP server tools for merge requests, issues, repositories, pipelines, work items, variables, dependency proxy, vulnerabilities, webhooks, search… | zereight/ | 2k | — | ~2k | Automated safety check: Pass | MIT | yesterday |
Questions, answered from the data.
What is the best skill by zereight?
OMG Mode Canceller from zereight/gitlab-mcp ranks first of the 24 skills by zereight listed here, with the highest score: its repository has 2k GitHub stars, 1 other GitHub owner carry a copy, its SKILL.md loads about 690 tokens and it passes the automated safety check with no findings. Next come CCG Tri-Model Orchestration and Cross-Language Coding Standards.
Are zereight's skills official?
None yet. All 24 skills by zereight listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
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.