Repository
overmind-core/overmind agent skills
- skills
- 20
- GitHub stars
- 544
GitHub description: “The platform for continuously improving AI agents.”
- Stars
- 544 (54 forks)
- Licence
- AGPL-3.0
- Last push
- Oct 2026
- Created
- Mar 2026
- Homepage
- overmindlab.ai
- ai-agents
- evals
- fine-tuning
- llm
- llm-evaluation
- llmops
- lora
- mcp
- observability
- python
Install all skills
npx skills add overmind-core/overmindAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in overmind-core/overmind, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | End-to-end workflow for adding or changing a backend API endpoint — which module the serializer and view belong in, URL registration, OpenAPI client regeneration, and typed consumption from the… | overmind-core/ | 544 | — | ~830 | Automated safety check: Notes | AGPL-3.0 | today |
| 2 | Rules for adding a new model or model family to the finetuning pipeline, or changing finetuning behavior for an existing one — engine-agnostic customization via family hooks instead of if/else in… | overmind-core/ | 544 | — | ~3.1k | Automated safety check: Pass | AGPL-3.0 | today |
| 3 | Overmind Console design system — semantic tokens, shared primitives, geometry and icons, the border-contrast floor, the duplicated table implementations, and the verification scripts. | overmind-core/ | 544 | — | ~1.8k | Automated safety check: Pass | AGPL-3.0 | today |
| 4 | 4.MCP End-to-end workflow for adding or changing Overmind MCP tools, resources, prompts, authentication, or result contracts — server layers, catalog registration, MCP-impact classification, and required… | overmind-core/ | 544 | — | ~4.3k | Automated safety check: Pass | AGPL-3.0 | today |
| 5 | How to open a complete pull request on overmind-core/overmind — the CI gates, the cross-cutting surfaces a change must carry with it (MCP, blast radius, the docs repo), gh pr edit being broken here… | overmind-core/ | 544 | — | ~1.5k | Automated safety check: Pass | AGPL-3.0 | today |
| 6 | Run or modify the seeddemo management command (the one-project Support Copilot demo) without breaking the beat-safety invariants that keep celery workers from re-driving seeded rows. | overmind-core/ | 544 | — | ~973 | Automated safety check: Pass | AGPL-3.0 | today |
| 7 | Inspect an Overmind project's agent map, capabilities, behaviour contracts, repository provenance and evaluation coverage. | overmind-core/ | 544 | — | ~797 | Automated safety check: Pass | AGPL-3.0 | today |
| 8 | Build, inspect, prepare, generate and export Overmind datasets in Data Workshop. | overmind-core/ | 544 | — | ~875 | Automated safety check: Pass | AGPL-3.0 | today |
| 9 | Prepare and run Overmind evaluations, author evaluators and eval sets, compare runs, and inspect sample-level failures. | overmind-core/ | 544 | — | ~779 | Automated safety check: Pass | AGPL-3.0 | today |
| 10 | Inspect Overmind model deployments, serving metrics, worker state and live routing; test inference and activate an approved model. | overmind-core/ | 544 | — | ~753 | Automated safety check: Pass | AGPL-3.0 | today |
| 11 | Connect external tracing providers to Overmind, inspect connector health, review capability-boundary mappings and verify imported traces. | overmind-core/ | 544 | — | ~772 | Automated safety check: Pass | AGPL-3.0 | today |
| 12 | Investigate Overmind traces, sessions, task executions, quality regressions, errors, latency and instrumentation gaps. | overmind-core/ | 544 | — | ~757 | Automated safety check: Pass | AGPL-3.0 | today |
| 13 | Set up, inspect and complete Overmind Optimiser experiments for prompt/code changes or model comparisons. | overmind-core/ | 544 | — | ~771 | Automated safety check: Pass | AGPL-3.0 | today |
| 14 | Select models, prepare exact training inputs, estimate costs, launch and inspect Overmind fine-tuning jobs. | overmind-core/ | 544 | — | ~837 | Automated safety check: Pass | AGPL-3.0 | today |
| 15 | Full comment and docstring policy for this repo — what to delete, what to keep compressed, what to never touch, and the two local traps. | overmind-core/ | 544 | — | ~1.1k | Automated safety check: Pass | AGPL-3.0 | today |
| 16 | The engineering bar for this repo — rebuild from first principles rather than patching, the simplicity ladder, what must never be simplified away, and the one-runnable-check rule. | overmind-core/ | 544 | — | ~810 | Automated safety check: Pass | AGPL-3.0 | today |
| 17 | 17.Run Tests How to run the platform test suites without wasting minutes — log-to-file pattern, when to skip tests entirely. | overmind-core/ | 544 | — | ~914 | Automated safety check: Pass | AGPL-3.0 | today |
| 18 | Deeper backend map of overbae — module layout, celery queue topology, the span-only tracing model and its API surface, capabilities and toml sync, behaviour-keyed scoring, auth and guests, model… | overmind-core/ | 544 | — | ~10k | Automated safety check: Pass | AGPL-3.0 | today |
| 19 | 19.Overmind Connect and set up Overmind, discover capabilities from a local repository, or coordinate work across product surfaces. | overmind-core/ | 544 | — | ~6.7k | Automated safety check: Pass | AGPL-3.0 | today |
| 20 | Data Workshop internals — Dataset and Cell, derived versions and the use gate, Parquet identity, the sandboxed runner, agent engines and tools, reviewed preparation, synthetic examples, shared… | overmind-core/ | 544 | — | ~7.1k | Automated safety check: Warn | AGPL-3.0 | today |
Questions, answered from the data.
What is the best skill in overmind-core/overmind?
API Endpoints from overmind-core/overmind ranks first of the 20 skills in overmind-core/overmind listed here, with the highest score: its repository has 544 GitHub stars, its SKILL.md loads about 830 tokens and it has informational notes only in the automated safety check. Next come Finetuning Model Onboarding and Frontend Design.
Are the skills in overmind-core/overmind official?
None yet. All 20 skills in overmind-core/overmind 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 overmind-core/overmind?
Run npx skills add overmind-core/overmind 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.