Audit Tambon Hunt
Hunt the three Tambon LLM-failure-mode signatures (Hallucinated Object, Wrong Attribute, Silly Mistake) across an audit scope. Use during the audit pipeline AFTER hard-stops and BEFORE blind-spots. Output: counts per signature, top occurrences, density per 1000 LoC. Findings flow into Domain 13 (Code Integrity).
Install
npx skills add wolverin0/claude-skills --skill audit-tambon-huntgit clone --depth 1 https://github.com/wolverin0/claude-skills.git /tmp/claude-skills
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills/skills/audit/audit-tambon-hunt ~/.claude/skills/audit-tambon-huntPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Skill: Audit Tambon Hunt This skill detects the three LLM-specific bug patterns documented in Tambon et al. 2025 — patterns that are nearly absent from human-written code. Finding them is double signal: each occurrence is a correctness defect AND evidence of unreviewed AI generation. The full taxonomy and detection guidance is in `@.claude/context/audit-tambon-signatures.md`. Load it before starting. ## Process ### Pre-flight ``` Read @.claude/context/audit-rules.md Read @.claude/context/audit-tambon-signatures.md ``` ### Phase 1 — Static type-check (the heavy lifter) The single most effective Tambon detector is a strict type-checker. Run the appropriate one(s): ```bash # Python which mypy &>/dev/null && mypy --strict src/ 2>&1 | tee /tmp/mypy.log which pyright &>/dev/null && pyright src/ 2>&1 | tee /tmp/pyright.log # TypeScript which tsc &>/dev/null && tsc --noEmit --strict 2>&1 | tee /tmp/tsc.log # If nothing is installed, that's a finding in its own right — # "no static type checking configured." Continue with grep-based hunts. ``` Filter the output for the relevant error categories: - **mypy:** `has no attribute`, `Module has no attribute`, `is not defined` - **pyright:** `Cannot access attribute`, `is not a known attribute`, `is not defined` - **tsc:** `Property '...' does not exist`, `Cannot find name`, `has no exported member` Each unique error of those classes is a candidate Tambon finding.
Details
- Skill name
audit-tambon-hunt- Repository
- wolverin0/claude-skills
- Path
skills/audit/audit-tambon-hunt/SKILL.md- Repo updated
- 17 November 2026
FAQ
What does the Audit Tambon Hunt skill do?
Hunt the three Tambon LLM-failure-mode signatures (Hallucinated Object, Wrong Attribute, Silly Mistake) across an audit scope. Use during the audit pipeline AFTER hard-stops and BEFORE blind-spots. Output: counts per signature, top occurrences, density per 1000 LoC. Findings flow into Domain 13 (Code Integrity).
How do I install the Audit Tambon Hunt skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add wolverin0/claude-skills --skill audit-tambon-hunt. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Audit Tambon Hunt popular?
It lives in wolverin0/claude-skills, which has 41 GitHub stars and 1 forks.
Related skills
UI UX Pro Max
41wolverin0/claude-skills
UI/UX design intelligence for web and mobile. Includes 50+ styles, 161 color palettes, 57 font pairings, 161 product types, 99 UX guidelines, and 25 chart types across 10 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, and HTML/CSS). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, and check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, and mobile app. Elements: button, modal, navbar, sidebar, card, table, form, and chart. Styles: glassmorphism,
Audit Blind Spots
41wolverin0/claude-skills
Walk the B1-B19 AI-to-AI blind-spot catalog systematically. Use during the audit pipeline AFTER hard-stops and Tambon hunt and BEFORE the 13 domain audits. Output: PRESENT / NOT PRESENT for each B-class with evidence. Findings flow into the appropriate domains.
Audit Decisions
41wolverin0/claude-skills
Standardize remediation decisions, baseline-policy entries, and legal-review banners for accepted, deferred, or policy-blocked audit findings.
Bootstrap Agent Identity
45pjt222/agent-almanac
Consistent agent behavior after restart — progressive identity loading, working context reconstruction from persistent artifacts, fresh-vs-continuation detection, calibration through centering and attunement, and identity verification for coherence. Addresses the cold-start problem where an agent must reconstruct who it is and what it was doing from evidence rather than memory. Use at the start of every new session, after a session interruption or crash, when agent behavior feels inconsistent with prior sessions, or when persistent memory and current context appear contradictory.
Audit Fix Generator
41wolverin0/claude-skills
Generate a detailed AI fix prompt for a specific audit finding. Use when the user asks for the audit-fix-generator skill with a finding id (e.g. F-X.Y) or "give me the fix prompt for finding N." Produces a complete prompt the user can hand to a fresh AI session (Claude Code, Cursor, ChatGPT) to remediate the finding with verification and rollback steps.
Build Coherence
45pjt222/agent-almanac
AI multi-path reasoning coherence using bee democracy — independent evaluation of competing approaches, waggle dance as reasoning-out-loud, quorum sensing for confidence thresholds, and deadlock resolution. Use when forage-solutions has identified multiple valid approaches and a selection must be made, when oscillating between options without committing, when justifying an architecture or tool choice with structured reasoning, or before an irreversible action where the cost of the wrong choice is high.
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.