Agent skill

Share Case

by NeuroAIHub in NeuroAIHub/BrainPilot

One-command community case sharing — capture research context from your session and submit to GitHub Discussions

AGPL-3.0Auto-check passed

Install Share Case

skills CLI
$ npx skills add NeuroAIHub/BrainPilot --skill share-case -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install NeuroAIHub/BrainPilot share-case --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/NeuroAIHub/BrainPilot.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/skills/skills/01_Meta-Skills/share-case .claude/skills/share-case && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
share-case
GitHub stars
1.1k
Token cost
~1.9k tokens
SKILL.md length
717 words
Files
1
Skills in repo
59
Repo updated
First seen
Licence
AGPL-3.0

At a glance

One-command community case sharing — capture research context from your session and submit to GitHub Discussions

  • Works in 4 steps: Quick Survey → Context Extraction → User Review and Submission Choice → …
  • SKILL.md covers Purpose, When to Use This Skill, Research Planning Protocol and ⚠️ Verification Notice, plus 4 more sections
  • Calls gh; reaches github.com

What it does

Share Case is an agent skill from NeuroAIHub/BrainPilot. One-command community case sharing — capture research context from your session and submit to GitHub Discussions

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It works with GitHub. The repository describes itself as: BrainPilot: Automating Brain Discovery with Agentic Research. The licence is AGPL-3.0.

Example prompts

  • “/share-case”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Quick Survey
  2. Context Extraction
  3. User Review and Submission Choice
  4. Submit to GitHub

What it can do on your machine

Read from SKILL.md and the folder at commit 93f6855. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • gh

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • github.com

    Also links to:

    • cli.github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Share Case loads about 1.9k tokens when it runs. Until then it costs about 31 tokens; SKILL.md has 717 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~31
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from NeuroAIHub/BrainPilot at commit 93f6855, republished under its AGPL-3.0 licence (© NeuroAIHub). 717 words, ~1,910 tokens.

Download SKILL.mdSave it as .claude/skills/share-case/SKILL.md (or your agent's skills folder).
name
share-case
description
One-command community case sharing — capture research context from your session and submit to GitHub Discussions
domain
meta-skill
version
1.0.0
review_status
ai-generated

Share Case

Purpose

This meta-skill captures a researcher's experience using any skill in this repository and submits it as a structured case to GitHub Discussions. It handles all formatting and submission so users never need to leave their terminal or know Git.

When to Use This Skill

Activate when the user:

  • Says "share this case", "share my experience", "分享这个案例"
  • Wants to document how they used a skill in their research
  • Asks how to contribute a usage example

Research Planning Protocol

Before starting the case sharing process, you MUST:

  1. Identify the skill used — Which skill(s) from this repository were used in the current session?
  2. Clarify sharing scope — What aspects of the experience does the user want to share?
  3. Declare what will be extracted — List the specific conversation elements that will be included
  4. Note privacy considerations — Are there dataset names, lab identifiers, or participant details that should be anonymized?
  5. Present the extraction 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:

  1. Direct submission via gh CLI (Recommended)

    • Requires gh CLI installed and authenticated
    • Run gh auth status to check
    • Install from https://cli.github.com/ and run gh auth login
  2. Manual submission via web browser

    • No gh CLI required
    • Opens GitHub Discussions page in browser
    • User copies and pastes the generated case

The skill will check for gh availability and let the user choose their preferred method.

GitHub Discussions must be enabled on the repository. The skill submits to the "Show & Tell" category.


Interactive Flow

Step 1 — Quick Survey

Present these questions using multiple-choice format:

Q1: Which skill did you use?

  • Auto-detect from the current session context (list skills that were activated)
  • Let the user confirm or select manually from the full skill list

Q2: What was your research scenario?

  • Formal experiment
  • Coursework or teaching
  • Method exploration
  • Paper reproduction
  • Other (free text)

Q3: How helpful was the skill? (1-5)

  • 1 = Not helpful
  • 2 = Slightly helpful
  • 3 = Moderately helpful
  • 4 = Very helpful
  • 5 = Extremely helpful

Q4: What was most valuable? (select all that apply)

  • Correct methodology guidance
  • Validated parameters and thresholds
  • Pitfall warnings
  • Complete pipeline coverage
  • Literature references
  • Other (free text)
Show full SKILL.md (320 more words)Show less
Step 2 — Context Extraction

Extract the following from the current conversation:

  1. Research context — The user's original research question and experimental setup
  2. Key recommendations — The main suggestions the skill provided (parameters, methods, warnings)
  3. Follow-up adjustments — Any modifications made during the conversation
  4. Outcome summary — What the user ultimately decided to do

Format each as a concise paragraph. Do NOT include raw conversation transcripts — synthesize into readable summaries.

Step 3 — User Review and Submission Choice

Display the complete case preview using the format below.

First, check gh CLI availability:

bash
gh auth status 2>&1

Then present submission options using AskUserQuestion:

If gh is available:

  • Submit via gh CLI (Recommended) — Direct submission to GitHub Discussions
  • Open in browser — Manual submission via web interface
  • Delete sections — Remove specific paragraphs before submitting
  • Anonymize — Replace specific names (datasets, labs, participants)
  • Abort — Cancel without submitting

If gh is NOT available:

  • Open in browser — Manual submission via web interface
  • Delete sections — Remove specific paragraphs before submitting
  • Anonymize — Replace specific names (datasets, labs, participants)
  • Abort — Cancel without submitting

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 Discussion in the "Show & Tell" category.

First, get repository and category IDs:

bash
gh api graphql -f query='
{
  repository(owner: "HaoxuanLiTHUAI", name: "awesome_cognitive_and_neuroscience_skills") {
    id
    discussionCategories(first: 10) {
      nodes {
        id
        name
      }
    }
  }
}'

Then create the discussion:

bash
gh api graphql -f query='
mutation {
  createDiscussion(input: {
    repositoryId: "REPO_ID",
    categoryId: "SHOW_AND_TELL_CATEGORY_ID",
    title: "Community Case: SKILL_NAME",
    body: "CASE_BODY_HERE"
  }) {
    discussion {
      url
    }
  }
}'

On success, display the Discussion URL:

✅ Case shared successfully!
🔗 Discussion URL: [URL]

Thank you for contributing to the community!

On failure, fall back to Option B.

Option B: Open in Browser
  1. Save the case locally to the current directory as case-skill-name-YYYYMMDD.md

  2. Open the GitHub Discussions page:

bash
xdg-open "https://github.com/HaoxuanLiTHUAI/awesome_cognitive_and_neuroscience_skills/discussions/new?category=show-and-tell" 2>/dev/null || \
open "https://github.com/HaoxuanLiTHUAI/awesome_cognitive_and_neuroscience_skills/discussions/new?category=show-and-tell" 2>/dev/null || \
echo "Please open: https://github.com/HaoxuanLiTHUAI/awesome_cognitive_and_neuroscience_skills/discussions/new?category=show-and-tell"
  1. Inform the user:
✅ Case saved to: case-skill-name-YYYYMMDD.md

🌐 Opening GitHub Discussions in your browser...

📋 Next steps:
1. Title: "Community Case: [Skill Name]"
2. Copy the content from case-skill-name-YYYYMMDD.md
3. Paste it into the discussion body
4. Click "Start discussion"

Thank you for contributing to the community!

Case Format Template

The submitted Discussion body uses this format:

markdown
## Community Case: [skill-name]

### Quick Info
- **Skill used**: `[skill-name]`
- **Scenario**: [selected option from Q2]
- **Rating**: [stars from Q3, e.g., ⭐⭐⭐⭐]
- **Most valuable**: [selected options from Q4]

### Research Context
> [User's research question and experimental setup — synthesized from conversation]

### What the Skill Suggested
- [Key recommendation 1]
- [Key recommendation 2]
- [Key recommendation 3]

### What I Actually Did & Result
> [User's experience applying the recommendations and the outcome]

### User's Tips
> [Optional: Additional insights the user wants to share with the community]

---
*Submitted via the `share-case` meta-skill.*

Privacy Principles

  • Nothing is submitted without explicit user confirmation after full preview
  • Users can remove any section or paragraph before submission
  • Users can anonymize dataset names, lab names, and participant identifiers
  • Users can choose to submit anonymously (no GitHub username attribution in the case body)
  • The skill never auto-submits — the user must explicitly approve

© NeuroAIHub, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in packages/skills/skills/01_Meta-Skills/share-case of NeuroAIHub/BrainPilot.

Open the folder on GitHubat commit 93f6855

Compare with similar skills

Share Case next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Share Case compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Share Case this skillNeuroAIHub/BrainPilot1.1k—~1.9kAutomated safety check: PassAGPL-3.0
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Greplooponyx-dot-app/onyx32k4 repos~3.3kAutomated safety check: PassMIT
GitHub Deep Researchbytedance/deer-flow84k4 repos~1.3kAutomated safety check: PassMIT
Diagnosing Superpowers Sessionsobra/superpowers297k3 repos~1.7kAutomated safety check: PassMIT
Update V8 Versionopeninterpreter/openinterpreter69k2 repos~845Automated safety check: PassApache-2.0

Similar skills

  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed
  • Greploop

    onyx-dot-app/onyx

    Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.

    32k GitHub starsUsed in 4 repos~3.3k tokens
    DevelopmentAuto-check passed
  • GitHub Deep Research

    bytedance/deer-flow

    Researches a GitHub repository over four rounds using the GitHub API and web search, then writes a structured markdown report with timeline, metrics and Mermaid diagrams.

    84k GitHub starsUsed in 4 repos~1.3k tokens
    Research & ScienceAuto-check passed
  • Investigates a session where Superpowers went wrong, reads the transcripts on disk and produces an evidence-cited report, optionally prepared as a bug report for the maintainers.

    297k GitHub starsUsed in 3 repos~1.7k tokens
    Agent WorkflowsAuto-check passed
  • Update V8 Version

    openinterpreter/openinterpreter

    Bumps the pinned v8 and rusty_v8 versions in Codex, validates the release-candidate path with the v8-canary check, and traces failures to upstream build changes.

    69k GitHub starsUsed in 2 repos~845 tokens
    DevOps & CloudAuto-check passed
  • Last30days

    mvanhorn/last30days-skill

    Research what people actually say about any topic in the last 30 days.

    64k GitHub stars~7.9k tokensUpdated yesterday
    Research & ScienceAuto-check: notes

More from NeuroAIHub/BrainPilot

All 59 skills in this repo
  • Deeplabcut

    NeuroAIHub/BrainPilot

    Toolbox for markerless animal pose estimation with DeepLabCut.

    1.1k GitHub stars~1.7k tokensUpdated 8 days ago
    Auto-check passed
  • Fmriprep

    NeuroAIHub/BrainPilot

    Preprocess task-based or resting-state fMRI data with fMRIPrep — a robust, BIDS-App preprocessing pipeline built on FSL, ANTs, FreeSurfer, AFNI, and Nilearn.

    1.1k GitHub stars~4.1k tokensUpdated 8 days ago
    Auto-check passed
  • Mne Python Guide

    NeuroAIHub/BrainPilot

    Domain-validated pipeline guidance for EEG/MEG data analysis using MNE-Python: data loading, preprocessing (filtering, ICA, re-referencing), epoching, ERP/ERF computation, time-frequency…

    1.1k GitHub stars~2.3k tokensUpdated 8 days ago
    Auto-check passed
  • Netneurotools Guide

    NeuroAIHub/BrainPilot

    Domain-validated guidance for network neuroscience analysis using netneurotools: datasets, brain network metrics, connectivity consensus, modularity, spatial statistics, null models, and cortical…

    1.1k GitHub stars~2.6k tokensUpdated 8 days ago
    Auto-check passed
  • Nature Figure

    NeuroAIHub/BrainPilot

    Submission-grade Nature/high-impact journal figure workflow for Python or R.

    1.1k GitHub starsUsed in 1 repo~1.3k tokens
    Auto-check passed
  • Pycortex Guide

    NeuroAIHub/BrainPilot

    Domain-validated guidance for cortical surface visualization and brain surface rendering of fMRI data using pycortex: data types (Volume, Vertex, Dataset), 2D cortical flatmaps, 3D WebGL brain…

    1.1k GitHub stars~1.6k tokensUpdated 8 days ago
    Auto-check passed

Works with

Questions about Share Case

What does Share Case do?

One-command community case sharing — capture research context from your session and submit to GitHub Discussions. Share Case is an agent skill from NeuroAIHub/BrainPilot.

How do I install Share Case in Claude Code?

Run `npx skills add NeuroAIHub/BrainPilot --skill share-case -a claude-code`. Or copy the skill folder (packages/skills/skills/01_Meta-Skills/share-case in NeuroAIHub/BrainPilot) into .claude/skills/share-case in your project. Claude Code loads it when a task matches its description.

How do I install Share Case in Codex?

Run `npx skills add NeuroAIHub/BrainPilot --skill share-case -a codex`. Or copy the skill folder (packages/skills/skills/01_Meta-Skills/share-case in NeuroAIHub/BrainPilot) into .agents/skills/share-case in your project. Codex loads it when a task matches its description.

Can I use Share Case in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add NeuroAIHub/BrainPilot --skill share-case -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/share-case, .gemini/skills/share-case, .github/skills/share-case and .opencode/skills/share-case in your project.

What does Share Case need to run?

Going by SKILL.md and its folder, Share Case needs the command-line tools its instructions call (gh).

Does Share Case access the network?

SKILL.md names 2 domains. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. As links in the text: cli.github.com. This is read from the text; nothing was executed.

Is Share Case safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Share Case use?

Share Case is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Share Case use?

About 1.9k tokens (SKILL.md is roughly 7.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Share Case?

Skills that share tags, products or a category with Share Case: PR Babysitter (openinterpreter/openinterpreter, 69k stars), Greploop (onyx-dot-app/onyx, 32k stars), GitHub Deep Research (bytedance/deer-flow, 84k stars) and Diagnosing Superpowers Sessions (obra/superpowers, 297k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Share Case?

NeuroAIHub (a GitHub organization) maintains it in NeuroAIHub/BrainPilot, which has 1,062 GitHub stars. The repository holds 59 skills in this directory. The repository was last updated on October 2, 2026.

Source: NeuroAIHub/BrainPilot on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.