CtrlK
BlogDocsLog inGet started
Tessl Logo

meme-coin-audit

Meme coin and token security audit — rug pull detection (honeypot, hidden mint, fee manipulation, LP lock bypass), Solana SPL token analysis (freeze authority, mint authority, metadata mutability), Token-2022 extension risks (transfer hooks, permanent delegate), DEX liquidity pool attacks (sandwich amplification, LP drain, bonding curve exploits), pump.fun/Raydium/Jupiter integration risks, and real exploit examples from 2024-2025. Use for any token audit, rug pull assessment, meme coin security review, or pre-investment due diligence.

64

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/meme-coin-audit/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a comprehensive, largely actionable token-audit playbook with strong grep/CLI primitives and explicit kill criteria, but it is weighed down by narrative prose, an incomplete PoC template, and a monolithic structure with no progressive disclosure into reference files. It is competent across the board without excelling on any dimension.

Suggestions

Tighten narrative prose: remove the 'THE ONE RULE' aphorism block, the Operator Notes meta-intro ('Wisdom from real authorized engagements...'), and condense the repeated 'Workflow primitive:' explanations in Related Skills to one-line pointers.

Complete the Foundry PoC template — replace `// ... buy tokens on Uniswap` / `// Assert token price crashed` placeholders with executable swap and assert calls, or explicitly state the skeleton is intentionally token-agnostic.

Split large inline blocks into reference files (e.g. references/foundry-poc.md, references/operator-notes.md) and link them from SKILL.md so the main file stays a concise overview with one-level-deep navigation.

DimensionReasoningScore

Conciseness

The bulk is high-value specifics (grep commands, CLI checks, pass/fail criteria), but narrative padding is present — the 'THE ONE RULE' aphorism, the Operator Notes intro prose ('Wisdom from real authorized engagements...'), and verbose 'Workflow primitive:' explanations in Related Skills — so it is mostly efficient but could be tightened; not a 3 because of this meta-commentary, not a 1 because it avoids generic concept explanation.

2 / 3

Actionability

The 8 bug-class grep commands and Solana CLI snippets are copy-paste ready (3-level), but the headline Foundry PoC template is incomplete pseudocode with `// ... buy tokens on Uniswap` and `// Assert token price crashed` placeholders and no explicit justification for the skeleton form; the mix lands at the 'some concrete guidance but incomplete' anchor rather than fully executable.

2 / 3

Workflow Clarity

Per-bug-class 'Kill if:' criteria and the 6-question decision filter provide validation checkpoints, but there is no single end-to-end sequenced workflow tying pre-dive → fast sweep → deep dive together with explicit feedback/retry loops, so the sequence is present yet implicit; not a 3 because checkpoints are distributed rather than woven into a linear validated procedure.

2 / 3

Progressive Disclosure

Sections are well organized, but the skill is a ~358-line monolithic SKILL.md with no bundle files and no references to split-out material, so content that could be separate (the Foundry PoC template, Operator Notes) is inline; the under-50-lines exception does not apply, so it does not reach the 'clear overview with one-level-deep references' anchor.

2 / 3

Total

8

/

12

Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, trigger-rich, and clearly states both capabilities and activation conditions in third person. It is dense but not padded with fluff, and the explicit 'Use for' clause anchors when to invoke it.

DimensionReasoningScore

Specificity

Lists multiple concrete actions and sub-domains — 'rug pull detection (honeypot, hidden mint, fee manipulation, LP lock bypass)', 'Solana SPL token analysis', 'DEX liquidity pool attacks' — matching the 'lists multiple specific concrete actions' anchor; not a 2 because coverage is comprehensive rather than partial.

3 / 3

Completeness

Explicitly answers both what ('Meme coin and token security audit — rug pull detection...') and when ('Use for any token audit, rug pull assessment, meme coin security review, or pre-investment due diligence.'), satisfying the explicit-trigger anchor; not a 2 because the 'Use for' clause is present and explicit.

3 / 3

Trigger Term Quality

Natural user phrasing is well covered — 'meme coin', 'token audit', 'rug pull assessment', 'meme coin security review', 'pre-investment due diligence' — matching the good-coverage anchor; technical jargon like 'Token-2022' is balanced by these common terms.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (meme coin / token security audit) with distinct triggers unlikely to fire for unrelated skills; not a 2 because the scope is sharply token-specific rather than overlapping with general audit skills.

3 / 3

Total

12

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
elementalsouls/Claude-BugHunter
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.