Not in the top 1,000 by GitHub stars
GAN-Thinking/gan-skill
A Claude Code skill that makes AI argue with itself to stress-test your ideas.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 38878cc8991c
No earlier version was observed for comparison.
View on GitHubAdd to my skills
Verified commit 38878cc8991c606b190ff278c0adaab0cde9bb51
git clone --filter=blob:none --no-checkout https://github.com/GAN-Thinking/gan-skill.git .hotskills/gan-thinking-gan-skill && git -C .hotskills/gan-thinking-gan-skill checkout --detach 38878cc8991c606b190ff278c0adaab0cde9bb51
# Copy each selected skill directory from .hotskills/gan-thinking-gan-skill into .claude/skills/<skill-name>/15GitHub stars
0stars in 7 days
1skill in this repository
0commits in 30 days
Heat
0.4- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- gan
/
How it works
gan
When your agent uses it
Adversarial dialectic tool inspired by GAN. Alternates between Generator (creative advocate) and Discriminator (adversarial critic). Supports forced role selection (g/d), intensity modes (hard/soft), and multi-language output. Use for stress-testing ideas, business plans, code, and spec designs.
What it loads into context
Frontmatter
91 tokensAlways available to the agent
SKILL.md
2,882 tokensWhen the skill is activated
Reference documents
3,428 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Argument Parsing (CRITICAL)
- Role Detection (when no g/d override)
- User Input Absorption (CRITICAL)
- Discriminator Role (Adversarial Critic)
- Generator Role (Creative Advocate)
- Scope
- Dialectical Loop
- Conclude Mode
- Output Language
Files
.claude/skills/evolve/SKILL.mddoc8,492 bytes.gitignoreasset85 bytesLICENSEasset1,069 bytesREADME.mddoc4,822 bytesSKILL.mdcore13,048 bytesevolve-benchmark.mddoc598 bytesevolve-results.tsvasset1,275 bytes
Read SKILL.md
# GAN — Adversarial Dialectic Mode
This skill mirrors a Generative Adversarial Network. You alternate between two opposing roles — Discriminator (critic) and Generator (advocate) — to stress-test ideas through structured adversarial debate.
## Argument Parsing (CRITICAL)
Parse `$ARGUMENTS` by scanning for these **optional, order-independent** tokens:
### Conclude Mode: `sum`
- If the **first word** of `$ARGUMENTS` is exactly `sum`, enter **Conclude Mode** (see below). All other tokens are ignored.
- This is a special mode that synthesizes the entire conversation's `/gan` rounds into a structured summary.
### Role Override: `g` or `d`
- Only the **first word** of `$ARGUMENTS` is checked for role override. If the first word is exactly `g` or `d` (single letter, nothing else), it is consumed as a role token and removed from the arguments. Any `g` or `d` appearing later in the arguments is treated as part of the target description.Skills included
- gan
Repository facts
- License
- MIT
- Created
- Mar 29, 2026
- Last pushed
- Mar 30, 2026
- Forks
- 1
- Open issues
- 0
- Project activity
- Slowing
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 6, 2026
- 1 broad permissionin 1 file: .claude/skills/evolve/SKILL.md:1
- No dangerous shell commands
- 3 network referencesin 1 file: README.md:47
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- No access to secrets
- No requests to vote in Hot
Show all 4 signals by file
.claude/skills/evolve/SKILL.md
- Broad permissionsline 1
Agent, Read, Write, Edit, Bash, Glob, Grep
README.md
- Network accessline 47
mkdir -p ~/.claude/skills/gan && curl -o ~/.claude/skills/gan/SKILL.md https://raw.githubusercontent.com/GAN-Thinking/gan-skill/main/SKILL.md - Network accessline 52
git clone https://github.com/GAN-Thinking/gan-skill.git ~/gan-skill - Network accessline 117
Found a bug? Have an idea? [Open an issue](https://github.com/GAN-Thinking/gan-skill/issues) or submit a PR.
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Declared and executed: 1 fact
- Allows Bash without restrictions, though it has no scripts or shell blocksevolve/SKILL.md:5High confidence
Signal confidence: 4 facts
- Broad permissions in the frontmatter of the SKILL.md.claude/skills/evolve/SKILL.md:1High confidence
- Network access in code of documentationREADME.md:47Low confidence
- Network access in code of documentationREADME.md:52Low confidence
- Network access in prose of documentationREADME.md:117Low confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Path .claude/skills/evolve/SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
