New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Bias Detection Design

by Owl-Listener in Owl-Listener/ai-design-skills

Designing review workflows to surface and mitigate bias in AI outputs.

MITAuto-check passedAI & LLM Engineering

Install Bias Detection Design

skills CLI
$ npx skills add Owl-Listener/ai-design-skills --skill bias-detection-design -a claude-code

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

GitHub CLI
$ gh skill install Owl-Listener/ai-design-skills bias-detection-design --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/Owl-Listener/ai-design-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/ai-alignment-reasoning/bias-detection-design .claude/skills/bias-detection-design && 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
bias-detection-design
GitHub stars
185
Token cost
~650 tokens
SKILL.md length
316 words
Files
1
Skills in repo
11
Repo updated
First seen
Licence
MIT

At a glance

Designing review workflows to surface and mitigate bias in AI outputs.

  • Tasks that involve AI interpretability
  • SKILL.md covers Types of Bias in AI Products, Designing Bias Detection…, Detection Methods and From Detection to Mitigation, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Bias Detection Design is an agent skill from Owl-Listener/ai-design-skills. Designing review workflows to surface and mitigate bias in AI outputs.

Its SKILL.md is about 650 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in AI & LLM Engineering, covering AI interpretability. The repository describes itself as: AI Design Skills Collection: agentic skills, commands, and plugins for designing AI products — from interaction patterns to alignment, evaluation, agent orchestration, and prompt… The licence is MIT.

When your agent uses it

  • Tasks that involve AI interpretability

Example prompts

  • “/bias-detection-design”

What it can do on your machine

Read from SKILL.md and the folder at commit f41b650. 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

    No scripts in the folder and no shell commands in SKILL.md.

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

  • Network

    No URLs in SKILL.md.

    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

Bias Detection Design loads about 650 tokens when it runs. Until then it costs about 23 tokens; SKILL.md has 316 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~23
When it runs · the whole SKILL.md, loaded when a task matches
~650

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 Owl-Listener/ai-design-skills at commit f41b650, republished under its MIT licence (© Owl-Listener). 316 words, ~650 tokens.

Download SKILL.mdSave it as .claude/skills/bias-detection-design/SKILL.md (or your agent's skills folder).
name
bias-detection-design
description
Designing review workflows to surface and mitigate bias in AI outputs.

Bias Detection Design

AI systems inherit biases from training data, amplify them through pattern-matching, and embed them in outputs that appear authoritative. Bias detection design creates the workflows, processes, and interfaces that help teams find and fix bias before users encounter it.

Types of Bias in AI Products

  • Representation bias: Some groups are overrepresented or underrepresented in outputs (images, examples, personas)
  • Performance bias: The AI works better for some users than others (languages, accents, cultural contexts)
  • Framing bias: The AI presents information in ways that favour certain perspectives
  • Allocation bias: AI-driven decisions distribute resources or opportunities unevenly
  • Association bias: The AI links concepts in stereotypical ways

Designing Bias Detection Workflows

Bias detection is a team practice, not a one-time audit:

  • Regular review cycles: Schedule periodic reviews of AI outputs for bias patterns
  • Diverse review panels: Include reviewers from different backgrounds, cultures, and perspectives
  • Structured evaluation: Use rubrics and checklists, not intuition
  • Real-world sampling: Test with real user inputs, not just curated test cases
  • Longitudinal monitoring: Bias can emerge over time as usage patterns change

Detection Methods

  • Comparative testing: Give the AI the same task with different demographic variables. Compare outputs.
  • Edge case exploration: Test inputs from underrepresented groups or unusual contexts.
  • Output auditing: Review a sample of real outputs for patterns of bias.
  • User feedback analysis: Look for bias-related complaints or differential satisfaction.
  • Benchmark evaluation: Test against established fairness benchmarks for the domain.

From Detection to Mitigation

Finding bias is step one. Addressing it requires:

  • Root cause analysis: Is the bias in training data, prompt design, model architecture, or product design?
  • Mitigation options: Retraining, prompt adjustment, output filtering, user controls, or design changes
  • Tradeoff analysis: Fixing one bias might introduce another. Document the tradeoffs.
  • Verification: After mitigation, verify the fix worked without creating new problems.

Design Artefacts

  • Bias audit checklists per feature
  • Review panel composition guidelines
  • Comparative testing protocols
  • Bias incident documentation templates
  • Mitigation tracking logs

© Owl-Listener, MIT. 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 skills/ai-alignment-reasoning/bias-detection-design of Owl-Listener/ai-design-skills.

Open the folder on GitHubat commit f41b650

Compare with similar skills

Bias Detection Design 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.

Bias Detection Design compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Bias Detection Design this skillOwl-Listener/ai-design-skills185—~650Automated safety check: PassMIT
Esmfold2JimLiu/science-skills2284 repos~2.5kAutomated safety check: PassApache-2.0
ObliteratusRedWoodOG/Hermes-Desktop1775 repos~3.8kAutomated safety check: PassMIT
Sparse Autoencoder Training with SAELensOrchestra-Research/AI-Research-SKILLs13k5 repos~3.2kAutomated safety check: PassMIT
TransformerLens InterpretabilityOrchestra-Research/AI-Research-SKILLs13k3 repos~3kAutomated safety check: PassMIT
Nnsight Remote InterpretabilityOrchestra-Research/AI-Research-SKILLs13k2 repos~3.3kAutomated safety check: PassMIT

Similar skills

  • Esmfold2

    JimLiu/science-skills

    Biohub ESMFold2 / ESMFold2-Fast all-atom co-folding (Candido et al.

    228 GitHub starsUsed in 4 repos~2.5k tokens
    AI & LLM EngineeringAuto-check passed

  • Obliteratus

    RedWoodOG/Hermes-Desktop

    Remove refusal behaviors from open-weight LLMs using OBLITERATUS — mechanistic interpretability techniques (diff-in-means, SVD, whitened SVD, LEACE, SAE decomposition, etc.) to excise guardrails…

    177 GitHub starsUsed in 5 repos~3.8k tokens
    AI & LLM EngineeringAuto-check passed

  • Sparse Autoencoder Training with SAELens

    Orchestra-Research/AI-Research-SKILLs

    Guides training and analyzing sparse autoencoders with SAELens to break neural network activations into interpretable features, including superposition and monosemanticity studies.

    13k GitHub starsUsed in 5 repos~3.2k tokens
    AI & LLM EngineeringAuto-check passed

  • TransformerLens Interpretability

    Orchestra-Research/AI-Research-SKILLs

    Guides mechanistic interpretability work with TransformerLens: loading models, caching activations, using HookPoints, activation patching and attention-pattern analysis.

    13k GitHub starsUsed in 3 repos~3k tokens
    AI & LLM EngineeringAuto-check passed

  • Nnsight Remote Interpretability

    Orchestra-Research/AI-Research-SKILLs

    Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution.

    13k GitHub starsUsed in 2 repos~3.3k tokens
    AI & LLM EngineeringAuto-check passed

  • pyvene Causal Interventions

    Orchestra-Research/AI-Research-SKILLs

    Guides causal experiments on PyTorch models with pyvene, such as causal tracing, activation patching and interchange intervention training, to test how a model works.

    13k GitHub starsUsed in 2 repos~3.5k tokens
    AI & LLM EngineeringAuto-check passed

More from Owl-Listener/ai-design-skills

All 11 skills in this repo

  • Few Shot Patterns

    Owl-Listener/ai-design-skills

    Crafting examples that steer AI behavior effectively. An agent skill from Owl-Listener/ai-design-skills.

    185 GitHub stars~723 tokensUpdated 4 mo ago
    Auto-check passed

  • State Management

    Owl-Listener/ai-design-skills

    Managing shared context, memory, and state across multiple agents.

    185 GitHub stars~1.5k tokensUpdated 4 mo ago
    Auto-check passed

  • Agent Role Design

    Owl-Listener/ai-design-skills

    Defining what each agent does, knows, and owns in a multi-agent system.

    185 GitHub stars~658 tokensUpdated 4 mo ago
    Auto-check passed

  • Behavioral Consistency

    Owl-Listener/ai-design-skills

    Ensuring the AI behaves predictably across sessions, edge cases, and modalities.

    185 GitHub stars~568 tokensUpdated 4 mo ago
    Auto-check passed

  • Chain Of Thought Design

    Owl-Listener/ai-design-skills

    Designing reasoning chains that produce better outputs. An agent skill from Owl-Listener/ai-design-skills.

    185 GitHub stars~687 tokensUpdated 4 mo ago
    Auto-check passed

  • Comparative Evaluation

    Owl-Listener/ai-design-skills

    A/B testing, side-by-side comparison, and preference ranking for AI outputs.

    185 GitHub stars~614 tokensUpdated 4 mo ago
    Auto-check passed

Categories

Questions about Bias Detection Design

What does Bias Detection Design do?

Designing review workflows to surface and mitigate bias in AI outputs. Bias Detection Design is an agent skill from Owl-Listener/ai-design-skills. Designing review workflows to surface and mitigate bias in AI outputs.

When should I use Bias Detection Design?

Bias Detection Design fits situations like: tasks that involve AI interpretability.

How do I install Bias Detection Design in Claude Code?

Run `npx skills add Owl-Listener/ai-design-skills --skill bias-detection-design -a claude-code`. Or copy the skill folder (skills/ai-alignment-reasoning/bias-detection-design in Owl-Listener/ai-design-skills) into .claude/skills/bias-detection-design in your project. Claude Code loads it when a task matches its description.

How do I install Bias Detection Design in Codex?

Run `npx skills add Owl-Listener/ai-design-skills --skill bias-detection-design -a codex`. Or copy the skill folder (skills/ai-alignment-reasoning/bias-detection-design in Owl-Listener/ai-design-skills) into .agents/skills/bias-detection-design in your project. Codex loads it when a task matches its description.

Can I use Bias Detection Design 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 Owl-Listener/ai-design-skills --skill bias-detection-design -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/bias-detection-design, .gemini/skills/bias-detection-design, .github/skills/bias-detection-design and .opencode/skills/bias-detection-design in your project.

What does Bias Detection Design need to run?

SKILL.md names no scripts, command-line tools or credentials: Bias Detection Design is instructions for the agent only.

Does Bias Detection Design access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Bias Detection Design 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 Bias Detection Design use?

Bias Detection Design is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Bias Detection Design use?

About 650 tokens (SKILL.md is roughly 2.6k 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 Bias Detection Design?

Skills that share tags, products or a category with Bias Detection Design: Esmfold2 (JimLiu/science-skills, 228 stars), Obliteratus (RedWoodOG/Hermes-Desktop, 177 stars), Sparse Autoencoder Training with SAELens (Orchestra-Research/AI-Research-SKILLs, 13k stars) and TransformerLens Interpretability (Orchestra-Research/AI-Research-SKILLs, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Bias Detection Design?

Owl-Listener (a GitHub user) maintains it in Owl-Listener/ai-design-skills, which has 185 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on June 9, 2026.

Source: Owl-Listener/ai-design-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.