contribute-skill
Skill39 starsChanged 9 months agoMITView on GitHub
One-command skill contribution — generate a SKILL.md from your domain expertise and submit to GitHub Issues for maintainer review
1 other project uses a version of this.
Adopted by
Most recently taken up by
- TBSten/skillstheir own version, first seen Sep 29, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- TBSten/skills★ 2same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
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-skills-via-prSkill
- 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
11 rules. About 0 are common, 5 are distinctive, and 6 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 32
Before starting the contribution process, you MUST:
- Very specific: line 54
Run gh auth status to check
- Very specific: line 140
Every numerical parameter must have a citation (Author, Year)
- Distinctive: line 141
No page numbers in citations (high hallucination risk)
- Very specific: line 144
If content exceeds 500 lines, split into SKILL.md + references/ subdirectory
- Very specific: line 158
If gh is available:
- Very specific: line 165
If gh is NOT available:
- Very specific: line 179
Create a GitHub Issue with the community-skill label:
- Distinctive: line 270
Before generating the skill, verify each piece of content against the litmus test:
- Distinctive: line 274
If YES → Include it (this is domain knowledge)
- Distinctive: line 275
If NO → Exclude it (this is general knowledge)
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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 Skill
Purpose
This meta-skill lets researchers contribute new domain knowledge skills to the repository without needing Git expertise. It generates a properly formatted SKILL.md from the user's domain knowledge and submits it as a GitHub Issue for maintainer review.
When to Use This Skill
Activate when the user:
- Says "contribute a skill", "把这个方法做成 skill", "submit a new skill"
- Wants to turn a discussion about methodology into a reusable skill
- Has domain expertise they want to encode as a structured skill
- Wants to contribute a skill from a paper they are reading
Research Planning Protocol
Before starting the contribution process, you MUST:
- Identify the knowledge source — Where does this domain knowledge come from? (paper, personal expertise, current session)
- Confirm domain specificity — Does this knowledge pass the litmus test: "Would a competent programmer who has never taken a cognitive science course get this wrong?"
- Outline the expected skill structure — What sections and parameters will the skill contain?
- Note potential gaps — What information might be missing or need verification?
- Present the contribution plan to the user and WAIT for confirmation before proceeding.
For detailed methodology guidance, see skills/research-literacy/SKILL.md.
⚠️ 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.
Prerequisites
This skill supports two submission methods:
- Direct submission via
ghCLI (Recommended)- Requires
ghCLI installed and authenticated - Run
gh auth statusto check - Install from https://cli.github.com/ and run
gh auth login
- Requires
- Manual submission via web browser
- No
ghCLI required - Opens GitHub Issues page in browser
- User copies and pastes the generated content
- No
The skill will check for gh availability and let the user choose their preferred method.
Interactive Flow
Step 1 — Source Confirmation
Q1: Where does this knowledge come from?
- A specific paper (provide DOI or title)
- Personal research experience
- Current session discussion
- Textbook or guidelines document
- Other (free text)
Q2: What is the skill about? (free text — brief description of the methodology)
Q3: Suggested skill name?
- Auto-suggest a kebab-case name based on the description
- Let the user confirm or modify
If the source is a paper with DOI/title, check whether the paper-to-skill meta-skill would be more appropriate. If the user has the full paper available, suggest: "Since you have the full paper, the paper-to-skill skill can do a more thorough extraction. Would you like to use that instead?"
Step 2 — Content Generation
Generate a SKILL.md following the project conventions. The generated skill MUST include:
YAML Frontmatter:
---
name: "[Human-Readable Skill Name]"
description: "[One-sentence summary]"
domain: "[subdomain]"
version: "1.0.0"
review_status: "ai-generated"
papers:
- "[Author, Year]"
dependencies:
required:
- research-literacy
---Required Sections (in order):
- Purpose — What domain knowledge this skill encodes
- When to Use This Skill — Trigger conditions
Research Planning Protocol — Standard preamble (adapt from template):
## Research Planning Protocol Before executing the domain-specific steps below, you MUST: 1. **State the research question** — What specific question is this analysis/paradigm addressing? 2. **Justify the method choice** — Why is this approach appropriate? What alternatives were considered? 3. **Declare expected outcomes** — What results would support vs. refute the hypothesis? 4. **Note assumptions and limitations** — What does this method assume? Where could it mislead? 5. **Present the plan to the user and WAIT for confirmation** before proceeding. For detailed methodology guidance, see `skills/research-literacy/SKILL.md`.Verification Notice — Standard disclaimer:
## ⚠️ 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](https://github.com/HaoxuanLiTHUAI/awesome_cognitive_and_neuroscience_skills/issues).- Domain-specific content — The actual skill logic with:
- Key parameters (every number cited with Author, Year — no page numbers)
- Decision logic
- Common pitfalls
- Step-by-step methodology
Content Quality Rules:
- Every numerical parameter must have a citation
(Author, Year) - No page numbers in citations (high hallucination risk)
- Skill must pass the litmus test: domain-specific, not general programming advice
- Under 500 lines total
- If content exceeds 500 lines, split into SKILL.md +
references/subdirectory
Step 3 — User Review and Submission Choice
Display the complete generated SKILL.md to the user.
First, check gh CLI availability:
gh auth status 2>&1Then present submission options using AskUserQuestion:
If gh is available:
- Submit via gh CLI (Recommended) — Direct submission to GitHub Issues
- Open in browser — Manual submission via web interface
- Save locally only — Save the file without submitting
- Request modifications — Specify what to change
- Abort — Cancel without saving
If gh is NOT available:
- Open in browser — Manual submission via web interface
- Save locally only — Save the file without submitting
- Request modifications — Specify what to change
- Abort — Cancel without saving
You MUST wait for explicit user confirmation before proceeding to Step 4.
Step 4 — Submit to GitHub
Based on the user's choice in Step 3:
Option A: Submit via gh CLI
Create a GitHub Issue with the community-skill label:
gh issue create \
--repo "HaoxuanLiTHUAI/awesome_cognitive_and_neuroscience_skills" \
--title "[Community Skill] skill-name-here" \
--label "community-skill" \
--body "ISSUE_BODY_HERE"Issue body format:
## Contributed Skill: `skill-name-here`
### Source
- **Knowledge source**: [paper / experience / session / other]
- **Key references**: [papers cited in the skill]
### Contributor Notes
> [Any additional context from the user about this skill]
### Generated SKILL.md
<details>
<summary>Click to expand full SKILL.md</summary>
[Full SKILL.md content here]
</details>
---
*Submitted via the `contribute-skill` meta-skill.*On success, display the Issue URL to the user:
✅ Skill submitted successfully!
🔗 Issue URL: [URL]
The maintainers will review your contribution. Thank you!On failure, fall back to Option B.
Option B: Open in Browser
- Save the SKILL.md locally to the current directory as
skill-name-here.md - Prepare the issue body and save it as
skill-name-here-issue.md - Open the GitHub Issues page:
xdg-open "https://github.com/HaoxuanLiTHUAI/awesome_cognitive_and_neuroscience_skills/issues/new?labels=community-skill&title=%5BCommunity%20Skill%5D%20skill-name-here" 2>/dev/null || \
open "https://github.com/HaoxuanLiTHUAI/awesome_cognitive_and_neuroscience_skills/issues/new?labels=community-skill&title=%5BCommunity%20Skill%5D%20skill-name-here" 2>/dev/null || \
echo "Please open: https://github.com/HaoxuanLiTHUAI/awesome_cognitive_and_neuroscience_skills/issues/new?labels=community-skill"- Inform the user:
✅ Files saved:
- skill-name-here.md (the skill)
- skill-name-here-issue.md (issue body to copy)
🌐 Opening GitHub Issues in your browser...
📋 Next steps:
1. Copy the content from skill-name-here-issue.md
2. Paste it into the issue body
3. Submit the issue
The maintainers will review your contribution. Thank you!Option C: Save Locally Only
Save the SKILL.md to the current directory as skill-name-here.md:
✅ Skill saved to: skill-name-here.md
You can submit it later by:
1. Opening https://github.com/HaoxuanLiTHUAI/awesome_cognitive_and_neuroscience_skills/issues/new
2. Using the label "community-skill"
3. Copying the skill content into the issueLitmus Test Enforcement
Before generating the skill, verify each piece of content against the litmus test:
"Would a competent programmer who has never taken a cognitive science course get this wrong?"
- If YES → Include it (this is domain knowledge)
- If NO → Exclude it (this is general knowledge)
Flag any borderline items to the user for their decision.
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.

