Repository
catlog22/maestro-flow agent skills
- skills
- 30
- GitHub stars
- 563
GitHub description: “Intent-driven workflow orchestration for multi-agent AI development — adaptive lifecycle engine, self-reinforcing knowledge graph, and visual dashboard for Claude Code, Gemini, Codex & more”
- Stars
- 563 (68 forks)
- Licence
- No licence
- Last push
- Oct 2026
- Created
- Mar 2026
- Homepage
- catlog22.github.io/maestro-flow
- ai-agents
- claude-code
- cli
- codex
- gemini
- knowledge-graph
- mcp
- multi-agent
- typescript
- workflow-orchestration
Install all skills
npx skills add catlog22/maestro-flowAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in catlog22/maestro-flow, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Create, revise, and format thesis or dissertation Word documents with strict academic formatting control. | catlog22/ | 563 | 1 repo | ~2.5k | Automated safety check: Pass | MIT | today |
| 2 | Swarm intelligence team skill — ACO-driven multi-agent exploration with hybrid LLM coordinator + Python optimization controller. | catlog22/ | 563 | — | ~2k | Automated safety check: Notes | No licence | today |
| 3 | Remove AI writing patterns from academic prose. An agent skill from catlog22/maestro-flow. | catlog22/ | 563 | — | ~1.7k | Automated safety check: Notes | No licence | today |
| 4 | Four-layer citation verification for academic papers. An agent skill from catlog22/maestro-flow. | catlog22/ | 563 | — | ~1.6k | Automated safety check: Notes | No licence | today |
| 5 | Maestro Flow 命令帮助系统。搜索命令、浏览技能、工作流推荐、新手引导。Triggers on "maestro-help", "帮助", "命令", "怎么用", "skill", "workflow", "maestro 怎么用". | catlog22/ | 563 | — | ~2.4k | Automated safety check: Pass | No licence | today |
| 6 | A skill your agent uses when designing, reviewing, refining, fixing, or codifying frontend UI with Maestro's self-contained Impeccable core | catlog22/ | 563 | — | ~4.8k | Automated safety check: Notes | No licence | today |
| 7 | Systematic experimental results analysis workflow for ML/AI research papers. | catlog22/ | 563 | — | ~3.4k | Automated safety check: Notes | No licence | today |
| 8 | Research ideation workflow from literature search to research planning. | catlog22/ | 563 | — | ~2.8k | Automated safety check: Notes | No licence | today |
| 9 | Organize messy conference LaTeX template .zip files into clean Overleaf-ready structure. | catlog22/ | 563 | — | ~1.8k | Automated safety check: Notes | No licence | today |
| 10 | Post-acceptance conference preparation workflow covering presentation slides, academic posters, and promotion content. | catlog22/ | 563 | — | ~2.1k | Automated safety check: Notes | No licence | today |
| 11 | Enhanced academic paper review response workflow with Agy/CLI collaborative analysis and multi-perspective discussion. | catlog22/ | 563 | — | ~4.8k | Automated safety check: Notes | No licence | today |
| 12 | Systematic academic paper review workflow covering self-review before submission and rebuttal writing after receiving reviewer feedback. | catlog22/ | 563 | — | ~2.3k | Automated safety check: Notes | No licence | today |
| 13 | End-to-end academic paper writing workflow. An agent skill from catlog22/maestro-flow. | catlog22/ | 563 | — | ~3.3k | Automated safety check: Notes | No licence | today |
| 14 | 14.Maestro Intent-to-chain planner over the canonical Session/Run lifecycle | catlog22/ | 563 | — | ~2.7k | Automated safety check: Notes | No licence | today |
| 15 | 15.Maestro Init Initialize project with auto state detection. An agent skill from catlog22/maestro-flow. | catlog22/ | 563 | — | ~2.1k | Automated safety check: Notes | No licence | today |
| 16 | Merge session worktree branch back to main. An agent skill from catlog22/maestro-flow. | catlog22/ | 563 | — | ~1.3k | Automated safety check: Notes | No licence | today |
| 17 | Create or edit command overlays from natural language, or auto-generate them from workflow deficiency signals | catlog22/ | 563 | — | ~4.2k | Automated safety check: Notes | No licence | today |
| 18 | Closed-loop policy over the canonical Session/Run chain. An agent skill from catlog22/maestro-flow. | catlog22/ | 563 | — | ~4.3k | Automated safety check: Notes | No licence | today |
| 19 | Manage a v3 Session — inspect status/resume-view, review knowledge candidates, complete, archive/unarchive | catlog22/ | 563 | — | ~3.2k | Automated safety check: Notes | No licence | today |
| 20 | Detect version, preview changes, apply workflow upgrades. An agent skill from catlog22/maestro-flow. | catlog22/ | 563 | — | ~1.7k | Automated safety check: Notes | No licence | today |
| 21 | Intent-driven knowhow precipitation — describe what you want to capture (记一个关于X的决策 / 保存这段代码模板 / 写个部署配方 / 存个调试技巧) and the workflow infers the type and records it into .workflow/knowhow/. | catlog22/ | 563 | — | ~589 | Automated safety check: Notes | No licence | today |
| 22 | User-invoked learning toolkit — guided reading, investigation, pattern extraction, or second opinions. | catlog22/ | 563 | — | ~7.1k | Automated safety check: Notes | No licence | today |
| 23 | 23.Maestro Next Unified entry for all development intents — classify intent, assess complexity, route to the correct execution channel: /maestro-companion (lightweight), standard single run, or /maestro and… | catlog22/ | 563 | — | ~6k | Automated safety check: Notes | No licence | today |
| 24 | Long-running iterative cycle — one entry, seven modes (debug|improve|planex|review|security|defensive|ui). | catlog22/ | 563 | — | ~4.1k | Automated safety check: Notes | No licence | today |
| 25 | Intent-driven issue lifecycle management — describe what you want in natural language (报告一个 bug / 列出开放 issue / 关掉 ISS-xxx / 关联到 task / 扫描发现问题) and the workflow routes to the right operation. | catlog22/ | 563 | — | ~446 | Automated safety check: Notes | No licence | today |
| 26 | 26.Maestro Spec Intent-driven spec precipitation — state a constraint in natural language (加一条规范：禁止用 any / 记录架构约束：服务间走 gRPC / 质量规则：覆盖率≥80%) and the workflow infers the category and records a <spec-entry. | catlog22/ | 563 | — | ~417 | Automated safety check: Notes | No licence | today |
| 27 | 27.Maestro Fork Create or sync session worktree for parallel dev. An agent skill from catlog22/maestro-flow. | catlog22/ | 563 | — | ~1.3k | Automated safety check: Notes | No licence | today |
| 28 | Intent-driven knowledge-store and Run knowledge lifecycle management — read-only audit/prune reports, stage candidates (with signal recording), review/resolve/promote candidates, harvest artifacts… | catlog22/ | 563 | — | ~1.9k | Automated safety check: Notes | No licence | today |
| 29 | Quick execution for small tasks — minimal run lifecycle (start + done) with evidence recording. | catlog22/ | 563 | — | ~1.6k | Automated safety check: Warn | No licence | today |
| 30 | Manage editing boundary restrictions | catlog22/ | 563 | — | ~1.3k | Automated safety check: Notes | No licence | today |
Questions, answered from the data.
What is the best skill in catlog22/maestro-flow?
Thesis DOCX from catlog22/maestro-flow ranks first of the 30 skills in catlog22/maestro-flow listed here, with the highest score: its repository has 563 GitHub stars, 1 other GitHub owner carry a copy, its SKILL.md loads about 2.5k tokens and it passes the automated safety check with no findings. Next come Team Swarm and Scholar Anti AI Writing.
Are the skills in catlog22/maestro-flow official?
None yet. All 30 skills in catlog22/maestro-flow 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 catlog22/maestro-flow?
Run npx skills add catlog22/maestro-flow 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.