Skip to content
Agentmart
Submit a tool

repo-skills-router

Routes substantive ML, AI, data, scientific-computing, and software-engineering requests to the smallest useful set of managed repository skills.

Skill by VectorSpaceLab

IndexedApache-2.0★ 341
Write a review

Chalk Labs

Need help deploying repo-skills-router?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/vectorspacelab-repo-skills-router

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Routes substantive ML, AI, data, scientific-computing, and software-engineering requests to the smallest useful set of managed repository skills. Invoke proactively when a request names or implies a package, framework, model family, dataset, modality, workflow, backend, deployment target, evaluation method, or implementation approach that may benefit from repository guidance, even if no repository is named. Narrow progressively from area to family to repository root: inspect only the one or two most likely area pages; compare candidates by capability, task surface, model/data format, training versus inference versus evaluation intent, runtime constraints, and root-skill description; then open only the selected root and relevant sub-skills, references, or scripts. Select multiple repositories only when each adds a distinct capability. Do not load the whole collection, treat dependencies or incidental integrations as capabilities, choose by name alone, or force a match when no exact taxonomy family applies.

Use cases: backend, data, ml, research

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/repo-skills-router

What's inside

Skill name
repo-skills-router
Description
Routes substantive ML, AI, data, scientific-computing, and software-engineering requests to the smallest useful set of managed repository skills. Invoke proactively when a request names or implies a package, framework, model family, dataset, modality, workflow, backend, deployment target, evaluation method, or implementation approach that may benefit from repository guidance, even if no repository is named. Narrow progressively from area to family to repository root: inspect only the one or two most likely area pages; compare candidates by capability, task surface, model/data format, training versus inference versus evaluation intent, runtime constraints, and root-skill description; then open only the selected root and relevant sub-skills, references, or scripts. Select multiple repositories only when each adds a distinct capability. Do not load the whole collection, treat dependencies or incidental integrations as capabilities, choose by name alone, or force a match when no exact taxonomy family applies.
License
Apache-2.0
Metadata
disco-role: operating
Instructions
43 lines in SKILL.md · view on GitHub

Files (200)

  • SKILL.md
  • autonomous-driving.md · references/areas/
  • biomedical-ai.md · references/areas/
  • computer-vision.md · references/areas/
  • data-science.md · references/areas/
  • generative-media.md · references/areas/
  • graph-learning.md · references/areas/
  • information-retrieval.md · references/areas/
  • llm-applications.md · references/areas/
  • llm-models-training-and-alignment.md · references/areas/
  • mlops.md · references/areas/
  • model-deployment-and-optimization.md · references/areas/
  • natural-language-processing.md · references/areas/
  • probabilistic-and-causal-modeling.md · references/areas/
  • reinforcement-learning.md · references/areas/
  • responsible-ai.md · references/areas/
  • robotics-and-embodied-ai.md · references/areas/
  • scientific-computing.md · references/areas/
  • speech-and-audio.md · references/areas/
  • time-series-analysis.md · references/areas/
  • training-infrastructure.md · references/areas/
  • driving-perception.md · references/families/autonomous-driving/
  • driving-simulation-and-evaluation.md · references/families/autonomous-driving/
  • motion-planning-and-control.md · references/families/autonomous-driving/
  • clinical-prediction-from-health-records.md · references/families/biomedical-ai/
  • digital-pathology.md · references/families/biomedical-ai/
  • medical-image-classification.md · references/families/biomedical-ai/
  • medical-image-reconstruction.md · references/families/biomedical-ai/
  • medical-image-registration.md · references/families/biomedical-ai/
  • medical-imaging-toolkits.md · references/families/biomedical-ai/
  • medical-object-detection.md · references/families/biomedical-ai/
  • medical-segmentation.md · references/families/biomedical-ai/
  • microscopy-image-analysis.md · references/families/biomedical-ai/
  • neuroimaging.md · references/families/biomedical-ai/
  • physiological-signal-analysis.md · references/families/biomedical-ai/
  • 3d-reconstruction.md · references/families/computer-vision/
  • 3d-scene-understanding.md · references/families/computer-vision/
  • backbone-model-libraries.md · references/families/computer-vision/
  • detection-utilities.md · references/families/computer-vision/
  • document-vision.md · references/families/computer-vision/
  • image-classification.md · references/families/computer-vision/
  • image-processing.md · references/families/computer-vision/
  • image-restoration.md · references/families/computer-vision/
  • image-segmentation.md · references/families/computer-vision/
  • object-detection-models.md · references/families/computer-vision/
  • object-detection-toolkits.md · references/families/computer-vision/
  • object-tracking.md · references/families/computer-vision/
  • open-vocabulary-detection.md · references/families/computer-vision/
  • panorama-stitching.md · references/families/computer-vision/
  • pose-estimation.md · references/families/computer-vision/
  • synthetic-vision-data.md · references/families/computer-vision/
  • video-understanding.md · references/families/computer-vision/
  • vision-language-understanding.md · references/families/computer-vision/
  • visual-anomaly-detection.md · references/families/computer-vision/
  • visual-correspondence-and-localization.md · references/families/computer-vision/
  • visual-identity-analysis.md · references/families/computer-vision/
  • data-integration.md · references/families/data-science/
  • data-profiling.md · references/families/data-science/
  • data-visualization.md · references/families/data-science/
  • dataset-discovery.md · references/families/data-science/
  • …and 140 more

SKILL.md (first lines)

# Repo Skills Router

Use this router for substantive requests where a managed repository skill may provide implementation guidance. It is a progressive-disclosure index, not a replacement for the selected repository skill.

## Routing procedure

1. Identify the user's dominant capability, workflow, data/model format, and runtime intent.
2. Read only the one or two most likely area pages below.
3. Compare the relevant family pages, especially when training, inference, evaluation, deployment, or similarly named repositories overlap.
4. Open the selected repository root at `../repo-skills/<skill-id>/SKILL.md`, then read only its relevant sub-skills, references, and scripts.
5. If no exact family fits, do not force a repository match; continue with the general task context or report that the managed collection has no exact route.

A repository may appear in several families. Choose the smallest set of repository roots that directly covers the request, and do not load every candidate listed on a family page.

## Area quick map

| Area | Populated families | Repository memberships | Area page |
| --- | ---: | ---: | --- |
| [Computer Vision](references/areas/computer-vision.md) | 21 | 312 |
| [Biomedical AI](references/areas/biomedical-ai.md) | 11 | 50 |
| [Generative Media](references/areas/generative-media.md) | 13 | 194 |
| [Speech and Audio](references/areas/speech-and-audio.md) | 5 | 56 |
| [Natural Language Processing](references/areas/natural-language-processing.md) | 9 | 78 |
| [LLM Applications](references/areas/llm-applications.md) | 16 | 325 |
| [LLM Models, Training, and Alignment](references/areas/llm-models-training-and-alignment.md) | 6 | 149 |
| [Information Retrieval](references/areas/information-retrieval.md) | 4 | 67 |
| [MLOps](references/areas/mlops.md) | 15 | 116 |
| [Model Deployment and Optimization](references/areas/model-deployment-and-optimization.md) | 4 | 114 |
| [Training Infrastructure](references/areas/training-infrastructure.md) | 12 | 135 |
| [Reinforcement Learning](references/areas/reinforcement-learning.md) | 5 | 82 |
| [Robotics and Embodied AI](references/areas/robotics-and-embodied-ai.md) | 7 | 81 |
| [Autonomous Driving](references/areas/autonomous-driving.md) | 3 | 38 |
| [Graph Learning](references/areas/graph-learning.md) | 4 | 42 |
| [Scientific Computing](references/areas/scientific-computing.md) | 16 | 124 |
| [Data Science](references/areas/data-science.md) | 12 | 152 |
| [Time Series Analysis](references/areas/time-series-analysis.md) | 7 | 53 |
| [Probabilistic and Causal Modeling](references/areas/probabilistic-and-causal-modeling.md) | 4 | 20 |
| [Responsible AI](references/areas/responsible-ai.md) | 4 | 21 |

## Maintenance

The machine-readable files under `references/index/` are the generated routing source of truth. Do not hand-edit area or family pages. For import, refresh, extension, or taxonomy changes, read [references/maintenance.md](references/maintenance.md) and use the verified importer/updater transaction.

From VectorSpaceLab/AREX-Skill, Apache-2.0.

More from VectorSpaceLab/AREX-Skill

Signals

Stars
341
Forks
26
Open issues
0
Last commit (this folder)
Aug 28, 2026 (2 months ago)
Last release
Sep 2, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from VectorSpaceLab

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get repo-skills-router running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying repo-skills-router?

CallGet help
Cite this page

repo-skills-router. Agent Mart. https://agentmart.dev/skills/vectorspacelab-repo-skills-router (last updated 2026-10-24)