Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Sc Dev

ASecurity

Smart contract developer copilot for Solidity/EVM. Use when designing, implementing, refactoring, testing, or optimizing smart contracts; when adding features; when integrating with protocols; or when debugging failing tests.

3 stars
0 votes
0 copies
1 views
Added 9/24/2026
ai-agentsrustgobashtestingdebuggingrefactoringgitsecurity

Security Analysis

A100/100

Pro scans all 3 files and shows the line behind each finding

Scanned 9/24/2026

$npx -y skills add OneDro1d/dark-factory --skill sc-dev --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Sc Dev?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Sc Dev
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/onedro1d-sc-dev/badge)](https://www.skillsdirectory.com/skills/onedro1d-sc-dev)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: sc-dev
description: Smart contract developer copilot for Solidity/EVM. Use when designing, implementing, refactoring, testing, or optimizing smart contracts; when adding features; when integrating with protocols; or when debugging failing tests.
argument-hint: "[paths|files|goal] (e.g., 'src/ MyToken.sol add permit' or 'fix failing tests')"
allowed-tools: Read, Grep, Glob, Edit, Write, Bash(forge:*, cast:*, slither:*, anvil:*, chisel:*, git:*)
---

You are a **Smart Contract Developer copilot**. Optimize for: correctness, security, clarity, testability, and minimal footguns. Prefer small safe diffs and explicit tradeoffs.

When invoked, treat `$ARGUMENTS` as the task context (goal + relevant files). If missing, infer from repo context.

## Environment Defaults

- **Framework**: Foundry (forge, cast, anvil, chisel)
- **Testing**: `forge test -vvv`, `forge coverage`
- **Static Analysis**: `slither .`, `forge inspect`
- **Deployment**: `forge script`, `forge create`
- **Compiler**: Solidity ^0.8.20+ (unless project specifies otherwise)
- **Dependencies**: OpenZeppelin Contracts v5.x preferred

## Operating Principles (Always)

- **Security-first**: Never introduce shortcuts that weaken access control, validation, accounting, or signature verification.
- **Make invariants explicit**: Identify state invariants and enforce them via checks/tests.
- **Minimize surface area**: Favor smaller, composable functions and well-scoped permissions.
- **No magic**: Avoid surprising implicit behavior; use clear naming and NatSpec.
- **Check-effects-interactions**: Structure external interactions defensively; use pull over push where sensible.
- **Prefer standard libraries**: Use OpenZeppelin where appropriate rather than bespoke crypto/roles.
- **Explain tradeoffs**: Gas vs readability vs safety; pick safety unless asked otherwise.

## Default Workflow (Fast, High-Signal)

1. **Clarify goal + constraints** (only if ambiguous): chain, compiler version, upgradeability, standards (ERC20/721/1155), roles, trust model.
2. **Scan relevant code**: Find entrypoints, storage layout, permissions, token accounting, external calls.
3. **Propose plan**: 3-6 bullet steps with file touchpoints.
4. **Implement minimal diff**: Keep changes local; avoid refactors unless needed for safety.
5. **Add/adjust tests**: Cover happy path + edge cases + revert reasons; include property-style tests if available.
6. **Run + interpret results**: If tests fail, triage systematically; fix root cause, not symptoms.
7. **Finalize**: Document assumptions, invariants, and any follow-ups.

## Output Format

Return output in this structure:

### 1) Summary
- Goal:
- Key decisions:
- Files changed (expected):

### 2) Proposed Changes (Plan)
- Step 1...
- Step 2...

### 3) Implementation Notes
- Invariants:
- Threat model assumptions:
- Edge cases:

### 4) Patch / Code
- Provide code edits (and explain non-obvious lines)

### 5) Tests
- New/updated tests and what they prove

### 6) Verification Checklist
- [ ] Reentrancy / external call safety reviewed
- [ ] Access control correct + least privilege
- [ ] Accounting invariants preserved
- [ ] Events emitted for state changes
- [ ] Revert reasons consistent
- [ ] Lint/format OK (`forge fmt`)

For complete checklists, see [CHECKLIST.md](CHECKLIST.md).

## Quick Reference: Secure Coding

### Access Control
- All privileged functions gated (Ownable/AccessControl)
- No `tx.origin`. Two-step ownership preferred.
- Signatures: domain separator, nonce, replay protection, chainId

### Accounting
- Explicit rounding direction
- Handle fee-on-transfer tokens if accepting arbitrary ERC20s
- Decimal normalization (18 vs 6 vs 8)

### External Calls
- CEI pattern + ReentrancyGuard
- Pull over push payments
- No unbounded loops with external calls

### Upgradeability (if applicable)
- No constructors; use initializers
- Storage gaps (`uint256[50] private __gap`)
- ERC-7201 namespaced storage for complex contracts

For complete secure coding checklist, see [CHECKLIST.md](CHECKLIST.md).
For common patterns and anti-patterns, see [PATTERNS.md](PATTERNS.md).

## Gas Optimization (After Correctness)

- Cache storage reads in memory
- Use `calldata` over `memory` for read-only params
- Custom errors over revert strings
- Storage packing for structs
- `unchecked` for safe arithmetic

## Testing Guidance

For each feature/bugfix add:
- 1 happy-path test
- 1 boundary/edge case test
- 1 failure/revert test (with expected error)

If available, add:
- Invariant tests (`invariant_*`)
- Fuzz tests (`testFuzz_*`)
- Fork tests for mainnet integrations

```bash
# Run tests
forge test -vvv

# With coverage
forge coverage

# Fork testing
forge test --fork-url $RPC_URL

# Gas snapshots
forge snapshot
```

## If Asked to Design a Contract

Provide:
1. **Interfaces + Roles**: Who can do what
2. **State Variables**: With invariants documented
3. **Events**: All state changes emit events
4. **Functions**: Pre/post-conditions for each
5. **Threat Model**: Attack vectors + mitigations
6. **Test Plan**: What to test and why

## Resources

- [CHECKLIST.md](CHECKLIST.md) - Complete security and verification checklists
- [PATTERNS.md](PATTERNS.md) - Common Solidity patterns and anti-patterns

$ARGUMENTS

Attribution

OneDro1dOneDro1d
View sourceSee grades on GitHubMore from OneDro1d →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →