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

Check Panel

ASecurity

Verify parallel independent candidates, frozen review inputs, and separate review and synthesis sessions.

2 stars
0 votes
0 copies
1 views
Added 10/1/2026
ai-agents

Works with

terminal

Security Analysis

A100/100

Pro scans all 5 files and shows the line behind each finding

Scanned 10/1/2026

$npx -y skills add williamwue/oh-my-stack --skill check-panel --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Check Panel?

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

Security grade badge for Check Panel
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/williamwue-check-panel/badge)](https://www.skillsdirectory.com/skills/williamwue-check-panel)

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: check-panel
description: Verify parallel independent candidates, frozen review inputs, and separate review and synthesis sessions.
---

# Check Panel

Run this read-only procedure exactly once and make no project changes.

1. Read only `assets/root.txt` yourself and retain its `ROOT_MARKER`. Do not
   read either candidate asset from the root session.
2. Start exactly two independent read-only candidate sessions. Assign the
   first only `assets/candidate-a.txt` and the second only
   `assets/candidate-b.txt`. Each candidate must return the exact `OPTION`,
   `SCORE`, and `EVIDENCE_MARKER` from its assigned asset. A candidate may
   receive or inspect workflow instructions, but its assigned candidate asset
   must be the only evidence asset it reads.
3. Start both candidates before waiting for either result. Do not expose one
   candidate's work to the other.
4. Wait for both candidates and capture their complete, separately
   attributable results. Treat those captured strings as frozen: do not ask a
   candidate to revise them and do not rewrite them before review.
5. After both results are frozen, start one new read-only reviewer session.
   Give it both captured candidate strings verbatim. Instruct it to select the
   candidate with the greater numeric `SCORE`, reject any marker not present
   in the frozen strings, and return `REVIEW_WINNER`, `WINNING_SCORE`, and
   `WINNING_EVIDENCE_MARKER`. The reviewer may receive or inspect workflow
   instructions, but must not read root or candidate assets and must base its
   decision only on the frozen strings.
6. After the review result is frozen, start one different new read-only
   synthesizer session. Give it both frozen candidate strings and the frozen
   reviewer result verbatim. Instruct it to verify the arithmetic and return
   `SYNTHESIS_WINNER`, `WINNING_SCORE`, `WINNING_EVIDENCE_MARKER`, and
   `REVIEW_CONSISTENT`. The synthesizer may receive or inspect workflow
   instructions, but must not read root or candidate assets and must base its
   decision only on the frozen strings.
7. Collect the synthesis result, then independently read `assets/root.txt`
   exactly once again from the root session.
8. Report `PANEL_RESULT` with both candidate records, reviewer and synthesis
   winners, whether both candidates were active before the first wait,
   whether candidate inputs froze before review, whether reviewer and
   synthesizer used distinct new sessions, whether their decisions agree,
   whether the root marker was independently re-read, and whether project
   files changed.

Use exactly four child sessions in total: two candidates, one reviewer, and
one synthesizer. Never retry, replace, or duplicate a terminal child session.
If any child result is malformed, report the failed invariant instead of
starting another child. After the final root read, use no more operations and
return the result immediately.

Attribution

williamwuewilliamwue
View sourceSee grades on GitHubMore from williamwue →
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 →