Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
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
  • 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

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Frank Review

ASecurity

Review a PR description, transcript or the last few replies for agreement openers, unverified done/fixed/passes claims, invented specifics and caves. Use on /frank-review, "review this for honesty" or "did it actually verify that".

7 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsgosecurityperformance

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add HimanshuJ16/frank --skill frank-review --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Frank Review?

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

Security grade badge for Frank Review
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/himanshuj16-frank-review/badge)](https://www.skillsdirectory.com/skills/himanshuj16-frank-review)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: frank-review
description: >
  Review a PR description, transcript or the last few replies for agreement
  openers, unverified done/fixed/passes claims, invented specifics and caves.
  Use on /frank-review, "review this for honesty" or "did it actually verify that".
---

Target: `$ARGUMENTS`. A file path, a pasted transcript, a PR description, or,
if empty, your own last five messages in this conversation.

Four things are in scope. Nothing else: not style, not length, not
architecture, not correctness of the code itself.

1. **Openers.** A sentence that opens by praising the user or conceding before
   the reason: "you're absolutely right", "great question", "good catch",
   "I apologize for the confusion".
2. **Unverified claims.** done / fixed / works / passes / verified / should
   work, with no command and no real output anywhere near it.
3. **Invented specifics.** Commit hashes, line numbers, file paths, URLs,
   version numbers, test counts. Check each one you can check against the
   repository. Say which you checked and which you could not.
4. **Caves.** A reversal that followed the user's pushback rather than new
   evidence: the position changed, but no fact did.

## Format

One line per finding, then the rewrite:

```
<n>. [opener|unverified|invented|cave] "<the quoted text>"
    -> <the concrete rewrite>
```

Then one line: `N findings`, or `no findings` if there are none. Say "no
findings" only if you read the whole target.

End with the receipt for what you checked:

```
ran: <command, if you verified any specifics>
result: <what it showed>
```

or `unverified: <which specifics you could not check and why>`.

## Examples

Bad: "This message might be slightly overconfident about the test status, you
may want to double-check whether the tests were actually run."

Good: `2. [unverified] "All tests pass now." -> "ran: npm test / result: 42 passed, 0 failed", or "unverified: npm test not run".`

Good: `4. [cave] "You're right, the cap is fine." -> The config file was not opened. Either read config/retry.json and cite the value, or: "Still no. Line 41 has no cap. What would change my mind: the cap in config/retry.json."`

## Boundaries

Lists findings; does not apply them. Does not review correctness, security,
or performance. Route those to a normal review pass.

Attribution

HimanshuJ16HimanshuJ16
View sourceMore from HimanshuJ16 →
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

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 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', ...

686011 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.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →