Report Writer Skill

SkillDev tools

Generate professional audit reports with structured findings, severity classifications, proof-of-concept code, and actionable recommendations. Use when writing individual findings, composing full audit reports, or formatting results for Code4rena, Sherlock, or client engagements.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the Report Writer Skill skill

What this skill tells your AI

The instructions your AI receives, as published by 0x-shashi/web3-audit-skills in skills/report-writer/SKILL.md and read by ahel’s review.

Generate professional audit reports with structured findings, severity classifications, proof-of-concept code, and actionable recommendations. Based on industry standards from Trail of Bits, OpenZeppelin, Cyfrin, Spearbit, and Code4rena.


Report Components

ComponentPurposeLength
Executive SummaryNon-technical overview for stakeholders1-2 paragraphs
ScopeFiles/contracts reviewed, commit hash, exclusionsTable
MethodologyHow the audit was conducted1 paragraph
Finding SummaryTable of all findings by severityTable
Detailed FindingsFull write-up of each findingPer finding
Centralization RisksAdmin/owner privilege analysisSection
Gas OptimizationsOptional efficiency improvementsList
AppendixTools used, out-of-scope itemsSection

Severity Classification

Based on the industry-standard Likelihood × Impact matrix:

Low ImpactMedium ImpactHigh Impact
High LikelihoodMediumHighCritical
Medium LikelihoodLowMediumHigh
Low LikelihoodInfoLowMedium

Likelihood Assessment

LevelCriteria
HighExploitable by anyone, no special conditions, low cost
MediumRequires specific conditions, timing, or moderate skill
LowRequires unlikely conditions, high cost, or privileged access

Impact Assessment

LevelCriteria
HighDirect loss of funds, protocol takeover, permanent DoS
MediumConditional fund loss, temporary DoS, incorrect state
LowInconvenience, minor gas waste, edge case behavior

Finding ID Convention

PrefixSeverityExample
CCriticalC-01, C-02
HHighH-01, H-02
MMediumM-01, M-02
LLowL-01, L-02
IInformationalI-01, I-02
GGas OptimizationG-01, G-02

Writing Quality Standards

Good Finding Characteristics

  1. Specific title — Describes the vulnerability, not just the location

    • BAD: "Issue in withdraw function"
    • GOOD: "Missing reentrancy guard in withdraw() allows ETH drain via malicious token callback"
  2. Clear description — A reader unfamiliar with the code can understand the issue

  3. Precise location — Contract name, function, line numbers

  4. Demonstrated impact — Concrete scenario showing what an attacker achieves

  5. Working PoC — For Critical/High, a test case that proves exploitability

  6. Actionable fix — Specific code change, not "fix the issue"


Resources

Workflows

Signals

GitHub stars
60
Forks
10
Last commit
Feb 2026
Advanced
Catalog kind
skill
Gateway key
report-writer
Source
github.com/0x-shashi/web3-audit-skills