Anti Hallucination
ALWAYS activate this skill. Apply these rules to every task regardless of domain. This skill governs how Claude Code verifies information, writes code, references documentation, and avoids fabricating functions, arguments, APIs, file paths, data structures, or facts. These rules override any inclination to guess.
Install
npx skills add dariia-m/my_claude_skills --skill anti-hallucinationgit clone --depth 1 https://github.com/dariia-m/my_claude_skills.git /tmp/my_claude_skills
mkdir -p ~/.claude/skills
cp -r /tmp/my_claude_skills/dont-lie ~/.claude/skills/anti-hallucinationPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Anti-Hallucination Protocol This skill exists to prevent Claude from fabricating information. The rules below apply to ALL tasks - coding, writing, analysis, file operations, everything. ## Core Principle **Never guess. Verify or say you don't know.** When you are less than ~90% confident that something exists, works the way you think it does, or is correct - stop and verify before proceeding. Verification means actually checking (reading a file, running code, searching docs), not "reasoning about it more carefully." --- ## Rule 1: Read Before You Write Before writing any code, read the relevant context first: - **Existing project code**: Read the files you'll modify or depend on. Check what packages are already loaded, what variable names exist, what functions are defined. Use `cat`, `head`, `grep`, or your file-reading tools. - **Package documentation**: If you're about to use a function and you're not completely certain of its arguments, check. In R: `?function_name` or `args(function_name)`. In Python: `help(function)` or `inspect.signature()`. - **Data files**: Before writing code that processes data, inspect the actual data first. Check column names, types, dimensions, sample values. In R: `str()`, `head()`, `names()`, `glimpse()`. Never assume column names. - **File structure**: Run `ls`, `find`, or `tree` before referencing paths. Never assume a file or directory exists.
Details
- Skill name
anti-hallucination- Repository
- dariia-m/my_claude_skills
- Path
dont-lie/SKILL.md- License
- MIT
- Repo updated
- 16 November 2026
FAQ
What does the Anti Hallucination skill do?
ALWAYS activate this skill. Apply these rules to every task regardless of domain. This skill governs how Claude Code verifies information, writes code, references documentation, and avoids fabricating functions, arguments, APIs, file paths, data structures, or facts. These rules override any inclination to guess.
How do I install the Anti Hallucination skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add dariia-m/my_claude_skills --skill anti-hallucination. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Anti Hallucination popular?
It lives in dariia-m/my_claude_skills, which has 36 GitHub stars and 11 forks.
Related skills
Academic Paper Verify
36dariia-m/my_claude_skills
Thoroughly verify all code, tables, figures, modeling decisions, and quantitative claims in an academic paper against its source R scripts and output files. Use this skill whenever you need to audit, replicate, or verify an academic research paper - including cross-checking LaTeX tables against R output, validating econometric modeling choices, ensuring sample sizes are consistent, building a verification manifest, and running automated replication tests. Trigger this skill for any mention of: paper verification, replication check, table audit, code-paper consistency, reproducing results, veri
Academic Writing
36dariia-m/my_claude_skills
Activate when the user is drafting any academic economics content from scratch (e.g., outlines, abstracts, introductions, data/methods/identification sections, results narratives, conclusions, referee responses, table/figure captions) and needs economics-specific structure, phrasing options, and quality checks to produce publication-ready prose.
Code Walkthrough
36dariia-m/my_claude_skills
Interactive step-by-step code walkthrough for entire codebases (single or multi-file). Explains each section's logic, assumptions, and data transformations, then RUNS the code and shows actual output - dataframe dimensions, head(), model summaries, plot descriptions, file previews. Pauses after each section for questions. Use whenever the user says "walk through", "explain", "go through", "break down", "review", "understand", "what does this code do", "help me understand this script", "annotate", "explain step by step", or "walk me through the codebase". Also trigger if someone just points at
Brain Write
43inite-ai/inite-brain-service
How to write to the INITE Brain knowledge graph from an agent loop — record_fact (with the conversationId / evidence[] grounding inputs), ingest_document, link_entities, retract_fact, record_feedback, and the detect_contradiction preflight. Covers confidence picking, claim grounding, retract vs forget semantics, identity_of cycle-guards. Use when the user explicitly wants to record, merge, or revise structured knowledge from a conversation (not when they're just asking a question).
Recommender System
40muralidharsoth-tech/andrew-ng-ml-claude-skills
推荐系统(Recommender System)—— 基于内容的推荐 / 协同过滤,纯 NumPy 实现。 当用户提到"推荐系统"、"recommender system"、"协同过滤"、"collaborative filtering"、 "内容推荐"、"content-based filtering"、"推荐算法"、"评分预测"、"帮我推荐"、 "电影推荐"、"商品推荐"、"recommendation system"、"推荐引擎"、"基于内容的推荐"、 "基于协同过滤"、"预测评分"、"推荐电影"、"推荐商品"、"similar items"、"相似物品"、 "找出相似"等类似场景时触发。 适用于任何"有用户-物品评分数据,想预测缺失评分或推荐物品"的需求。 不要手动写代码——必须调用此技能来统一处理。
Diataxis
23keithpatton/diataxis-agent-skill
Classify, validate, generate, and audit documentation using the Diátaxis framework. Enforces quadrant purity across tutorials, how-to guides, reference, and explanation. Use when creating documentation, reviewing docs, auditing doc sets, restructuring existing content, or when the user mentions Diátaxis, documentation structure, or doc quality.
Browse the most popular Claude skills, all writing & content skills, or write your own with the skills generator.