bias-assessment

bias-assessment is a skill for Claude Code from obielin/responsible-ai-skills. It costs 38 tokens per session (1,151 once invoked), scanned A, original, MIT.

A required review process for checking whether data or an AI model treats groups of people unevenly. It covers representation in the data and variables that may indirectly reveal protected traits.

In plain words
What is it for?
Use it when loading datasets, training machine-learning models, evaluating performance, or preparing data for an AI system.
Why use it?
Overall accuracy can hide poor results for smaller or protected groups. The assessment helps find these problems before training or evaluating the model.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the responsible-ai-skills plugin — 9 skills shipped together

Good fit Use it when loading datasets, training machine-learning models, evaluating performance, or preparing data for an AI system.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/obielin/responsible-ai-skills/bias-assessment
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add obielin/responsible-ai-skills --skill bias-assessment
Clone the repo
git clone --depth 1 https://github.com/obielin/responsible-ai-skills

Made for: Claude Code.

Or install responsible-ai-skills, the plugin that ships this one along with the rest of its 9 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for bias-assessment

README.md
[![agentmods](https://agentmods.dev/badge/skills/obielin/responsible-ai-skills/bias-assessment/github.svg)](https://agentmods.dev/skills/obielin/responsible-ai-skills/bias-assessment)
Your own site
<a href="https://agentmods.dev/skills/obielin/responsible-ai-skills/bias-assessment"><img src="https://agentmods.dev/badge/skills/obielin/responsible-ai-skills/bias-assessment/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for bias-assessment

Your own site · 80×15
<a href="https://agentmods.dev/skills/obielin/responsible-ai-skills/bias-assessment"><img src="https://agentmods.dev/badge/skills/obielin/responsible-ai-skills/bias-assessment.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,151 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00038 $0.01151
Opus 5 $0.00019 $0.00575
Sonnet 5 $0.00008 $0.00230
Haiku 4.5 $0.00004 $0.00115

Measured 12d ago against content hash 744ac5d52a9f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

bias-assessment scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/check_representation.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/bias-assessment/SKILL.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bias Assessment

Bias in AI systems causes real harm. A model that appears accurate overall can systematically disadvantage specific groups. You MUST complete this assessment before training or evaluating any model.

Phase 1: Data Audit (Before Training)

1.1 Check Representation

Run the representation check script:

python skills/bias-assessment/scripts/check_representation.py --data <your_dataset>

If no script applies, manually verify:

# For each protected attribute in your dataset:
for attr in ['age', 'sex', 'ethnicity', 'disability', 'postcode']:
    if attr in df.columns:
        print(f"\n{attr} distribution:")
        print(df[attr].value_counts(normalize=True))
        
        # Flag underrepresented groups (<5% of dataset)
        underrepresented = df[attr].value_counts(normalize=True)
        flagged = underrepresented[underrepresented < 0.05].index.tolist()
        if flagged:
            print(f"⚠️  UNDERREPRESENTED: {flagged}")

Stop and fix if: Any group that will be affected by predictions has <5% representation.

1.2 Check for Proxy Variables

Proxy variables appear neutral but encode protected characteristics:

Proxy Variable May Encode
Postcode / ZIP code Ethnicity, deprivation
Name Ethnicity, sex
School attended Socioeconomic status, ethnicity
Job title history Sex, disability
Device type Socioeconomic status

Action: For each proxy variable, decide: remove it, transform it, or document the risk explicitly.

1.3 Check Label Quality

Biased labels produce biased models:

  • Were labels assigned by humans? → Check inter-annotator agreement across annotator demographics
  • Were labels derived from historical decisions? → Those decisions may contain historical bias
  • Are labels consistent across demographic groups? → Run: df.groupby(protected_attr)['label'].mean()

Phase 2: Model Evaluation (After Training)

2.1 Disaggregated Performance

Read the full file on GitHub · 151 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 151 lines · 38 tokens per session scan A 744ac5d52a9f

Subscribe to this mod's changes

bias-assessment is a skill published in the GitHub repository obielin/responsible-ai-skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 38 tokens to every session and 1,151 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

embed

Generate, inspect, and use node/text embeddings in Semantica — compute Node2Vec embeddings, find similar nodes, score link predictions, batch similarity, and pairwise similarity. Uses NodeEmbedder, SimilarityCalculator, LinkPredictor, and AgentContext. Sub-commands: compute, similar, similarity, predict-link…

semantica-agi/semantica · 0 tokens

visualize

Visualize the Semantica knowledge graph — topology, centrality, communities, paths, embeddings, decision insights, and temporal evolution. Uses GraphAnalyzer, CentralityCalculator, CommunityDetector, PathFinder, and ContextGraph analytics. Sub-commands: topology, centrality, community, path, decision-graph, insights…

semantica-agi/semantica · 0 tokens

reason

Run reasoning over the Semantica knowledge graph — deductive logic, abductive hypothesis generation, Datalog programs, SPARQL queries, Rete network evaluation. Uses DeductiveReasoner, AbductiveReasoner, DatalogReasoner, SPARQLReasoner, ReteEngine. Sub-commands: deductive, abductive, datalog, sparql, rete, prove…

semantica-agi/semantica · 0 tokens

temporal

Temporal graph operations on Semantica — scoped queries at a point in time, graph snapshots, node change timelines, temporal causal analysis, and graph state reconstruction. Uses AgentContext.findprecedents(asof=), ContextGraph.stateat(), CausalChainAnalyzer.traceattime(), and TemporalQueryRewriter. Sub-commands…

semantica-agi/semantica · 0 tokens

validate

Validate Semantica pipelines, extraction quality, graph schemas, and ontology consistency. Returns structured error/warning checklists. Uses PipelineValidator, PipelineBuilder.validatepipeline(), GraphValidator, and OntologyValidator. Sub-commands: pipeline, step, dependencies, extraction, graph, ontology, performance.

semantica-agi/semantica · 0 tokens

extract

Run the full Semantica semantic extraction pipeline on a file or selected text — NER, relations, events, coreference resolution, triplets, and validation. Clears result cache before each run. Returns Markdown tables with entity/relation/event/triplet results and inline validator warnings.

semantica-agi/semantica · 59 tokens