contribute-skills-via-pr
Skill39 starsChanged 9 months agoMITView on GitHub
Step-by-step guidance for contributing a new skill to the NeuroAIHub/awesome_cognitive_and_neuroscience_skills repository via GitHub Pull Request, including SKILL.md format requirements, quality rules, and PR checklist
- Commits and pushes
In this repository49 other files it gives its agents.
- act-r-model-builderSkill
- alternative-uses-task-designerSkill
- bayesian-cognitive-model-builderSkill
- brain-connectivity-modelerSkill
- calcium-imaging-analysis-guideSkill
- cognitive-paradigm-designSkill
- cogsci-power-analysisSkill
- cogsci-statisticsSkill
- cogsci-visualizationSkill
- contribute-skillSkill
- creativity-self-efficacy-mediationSkill
- deeplabcutSkill
- divergent-thinking-scoringSkill
- drift-diffusion-modelSkill
- eeg-paradigm-designerSkill
- eeg-preprocessing-pipeline-guideSkill
- erp-analysisSkill
- evidence-accumulation-selectorSkill
- fmri-glm-analysis-guideSkill
- fmri-preprocessing-pipeline-guideSkill
- fmriprepSkill
- fmri-task-design-guideSkill
- infant-looking-time-designerSkill
- lesion-symptom-mapping-guideSkill
- markdown-report-writingSkill
- mne-python-guideSkill
- netneurotools-guideSkill
- neural-decoding-analysisSkill
- neural-population-analysis-guideSkill
- neuroimaging-power-guideSkill
- neuroimaging-sample-size-calculatorSkill
- neuropsych-battery-selectorSkill
- optogenetics-protocol-designerSkill
- paper-to-skillSkill
- parameter-recovery-checkerSkill
- pycortex-guideSkill
- reading-time-analysisSkill
- repo-to-skillSkill
- research-literacySkill
- self-paced-reading-designerSkill
- sentence-stimulus-normingSkill
- share-caseSkill
- share-usageSkill
- signal-detection-analysisSkill
- spikeinterface-skillSkill
- spiking-network-model-builderSkill
- tom-task-selectorSkill
- verify-skillSkill
- visual-search-array-generatorSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 31
Present the plan and WAIT for user confirmation: before writing the SKILL.md.
- Distinctive: line 39
Before writing, verify your skill does not duplicate an existing one.
- Distinctive: line 135
When opening the PR, all items must be checked:
- Very specific: line 148
If you prefer not to use Git, use the contribute-skill meta-skill inside Claude Code:
- Very specific: line 163
Use the verify-skill meta-skill to self-review your SKILL.md before submitting to catch common issues early.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Contribute Skills via PR
Purpose
This skill encodes the complete workflow for contributing a new skill to the NeuroAIHub/awesome_cognitive_and_neuroscience_skills repository via GitHub Pull Request. It covers SKILL.md format requirements, quality rules enforced by maintainers, the PR submission process, and the no-Git alternative.
When to Use This Skill
Activate when the user:
- Wants to contribute a skill to the NeuroAIHub community repository
- Asks how to submit a PR to
awesome_cognitive_and_neuroscience_skills - Wants to know the SKILL.md format or quality requirements for this repository
- Asks about the review process or PR checklist for this repo
Research Planning Protocol
- State the contribution goal — What domain knowledge does the new skill encode? Is it a new skill, an improvement, or a verification?
- Check for overlap — Confirm the skill does not duplicate an existing one (see overlap checklist below).
- Declare the skill structure — Outline the sections and key parameters before writing.
- Note quality constraints — All numerical parameters need citations; no page numbers; under 500 lines.
- Present the plan and WAIT for user confirmation before writing the SKILL.md.
Verification Notice
This skill was generated by AI from direct inspection of the NeuroAIHub/awesome_cognitive_and_neuroscience_skills repository (April 2026). Repository requirements may change — always check the current CONTRIBUTING.md before submitting. If you find errors, please open an issue.
Step 1: Check for Overlap
Before writing, verify your skill does not duplicate an existing one. Current skills include (41 total):
eeg-preprocessing-pipeline-guide, erp-analysis, mne-python-guide, fmri-preprocessing-pipeline-guide, fmri-glm-analysis-guide, fmri-task-design-guide, brain-connectivity-modeler, neural-decoding-analysis, neural-population-analysis-guide, calcium-imaging-analysis-guide, lesion-symptom-mapping-guide, optogenetics-protocol-designer, spiking-network-model-builder, drift-diffusion-model, bayesian-cognitive-model-builder, act-r-model-builder, evidence-accumulation-selector, parameter-recovery-checker, signal-detection-analysis, cogsci-statistics, cogsci-power-analysis, cogsci-visualization, neuroimaging-power-guide, neuroimaging-sample-size-calculator, cognitive-paradigm-design, eeg-paradigm-designer, divergent-thinking-scoring, alternative-uses-task-designer, creativity-self-efficacy-mediation, reading-time-analysis, self-paced-reading-designer, sentence-stimulus-norming, infant-looking-time-designer, tom-task-selector, neuropsych-battery-selector, visual-search-array-generator, research-literacy, paper-to-skill, contribute-skill, verify-skill, share-case
Step 2: Write the SKILL.md
Required YAML Frontmatter
Skill name may only contain lowercase letters, numbers, and hyphens. The name must match the folder name.
---
name: "my-skill-name"
description: "One-sentence summary of the domain knowledge encoded"
domain: "your-domain"
version: "1.0.0"
authors:
- "Your Name"
papers:
- "Author et al., Year"
dependencies:
required:
- research-literacy
review_status: "ai-generated"
---Mandatory fields: name, description, review_status. All others are recommended.
Required Sections (in this order)
- Purpose — What domain knowledge this skill encodes and why it is useful
- When to Use — Trigger conditions that activate this skill
- Research Planning Protocol — The standard 5-step preamble (copy template below)
- Verification Notice — The standard AI disclaimer (copy template below)
- Domain-specific content — The actual skill logic with cited parameters
Research Planning Protocol Template
## Research Planning Protocol
1. **State the research question** — ...
2. **Justify the method choice** — ...
3. **Declare expected outcomes** — ...
4. **Note assumptions and limitations** — ...
5. **Present the plan to the user and WAIT for confirmation** before proceeding.Verification Notice Template
## Verification Notice
> This skill was generated by AI from academic literature. All parameters,
> thresholds, and citations require independent verification before use in
> research. If you find errors, please open an issue at
> https://github.com/NeuroAIHub/awesome_cognitive_and_neuroscience_skills/issues.Quality Rules
| Rule | Requirement |
| Skill name | Lowercase letters, numbers, and hyphens only. Must match the folder name. e.g., my-new-skill |
| Citations | All numerical parameters must have (Author, Year) |
| No page numbers | Use (Luck, 2014) NOT (Luck, 2014, p. 187) |
| Line limit | SKILL.md must be under 500 lines |
| Directory name | kebab-case, must match the name field in YAML frontmatter |
| Commit prefix | feat:, fix:, docs:, or refactor: |
Step 3: Submit via Git PR
# 1. Fork on GitHub, then clone your fork
git clone https://github.com/<your-username>/awesome_cognitive_and_neuroscience_skills.git
cd awesome_cognitive_and_neuroscience_skills
# 2. Create a feature branch
git checkout -b feat/<skill-name>
# 3. Create skill directory and add files
mkdir -p skills/<skill-name>
# copy your SKILL.md into skills/<skill-name>/SKILL.md
# optionally: mkdir skills/<skill-name>/references
# 4. Commit and push
git add skills/<skill-name>/
git commit -m "feat: add <skill-name> skill for <one-line description>"
git push origin feat/<skill-name>
# 5. Open PR on GitHub against the master branchPR Template Checklist
When opening the PR, all items must be checked:
- SKILL.md has required YAML frontmatter (
name,description,review_status) - Includes Research Planning Protocol section
- Includes Verification Notice section
- All numerical parameters have
(Author, Year)citations - Citations do not contain specific page numbers
- SKILL.md is under 500 lines
- Directory name uses kebab-case
- Commit messages use conventional prefixes (
feat:,fix:,docs:, etc.)
Alternative: No-Git Contribution
If you prefer not to use Git, use the contribute-skill meta-skill inside Claude Code:
- Say "contribute a skill" in Claude Code
- The meta-skill generates a SKILL.md interactively
- It submits the skill as a GitHub Issue with the
community-skilllabel - Maintainers review and merge on your behalf
After Submission
Maintainers may request changes such as:
- Adding missing
(Author, Year)citations - Removing page numbers from citations
- Reducing line count if over 500
- Clarifying the Research Planning Protocol or Verification Notice
Use the verify-skill meta-skill to self-review your SKILL.md before submitting to catch common issues early.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

