Consult Claude
EpicenterHQ/epicenter
Assign Claude Code a read-only investigation, recommendation, or finished text draft.
Deploy a bounded, profile-loaded adversarial review squad at a mission point-cut so independent doctrine lenses converge on findings one reviewer would miss.
Install Adversarial Squad
$ npx skills add spec-kitty/spec-kitty --skill adversarial-squad -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install spec-kitty/spec-kitty adversarial-squad --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/spec-kitty/spec-kitty.git skills-src && mkdir -p .claude/skills && cp -r skills-src/src/charter/offering/skills/adversarial-squad .claude/skills/adversarial-squad && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "adversarial-squad" agent skill from https://github.com/spec-kitty/spec-kitty/tree/main/src/charter/offering/skills/adversarial-squad into .claude/skills/adversarial-squad/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "adversarial-squad", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/spec-kitty/spec-kitty/tree/main/src/charter/offering/skills/adversarial-squadType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add spec-kitty/spec-kitty --skill adversarial-squad -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install spec-kitty/spec-kitty adversarial-squad --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/spec-kitty/spec-kitty.git skills-src && mkdir -p .agents/skills && cp -r skills-src/src/charter/offering/skills/adversarial-squad .agents/skills/adversarial-squad && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "adversarial-squad" agent skill from https://github.com/spec-kitty/spec-kitty/tree/main/src/charter/offering/skills/adversarial-squad into .agents/skills/adversarial-squad/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "adversarial-squad", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add spec-kitty/spec-kitty --skill adversarial-squad -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install spec-kitty/spec-kitty adversarial-squad --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/spec-kitty/spec-kitty.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/src/charter/offering/skills/adversarial-squad .cursor/skills/adversarial-squad && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "adversarial-squad" agent skill from https://github.com/spec-kitty/spec-kitty/tree/main/src/charter/offering/skills/adversarial-squad into .cursor/skills/adversarial-squad/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "adversarial-squad", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/spec-kitty/spec-kitty.git --path src/charter/offering/skills/adversarial-squad--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add spec-kitty/spec-kitty --skill adversarial-squad -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install spec-kitty/spec-kitty adversarial-squad --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/spec-kitty/spec-kitty.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/src/charter/offering/skills/adversarial-squad .gemini/skills/adversarial-squad && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "adversarial-squad" agent skill from https://github.com/spec-kitty/spec-kitty/tree/main/src/charter/offering/skills/adversarial-squad into .gemini/skills/adversarial-squad/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "adversarial-squad", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install spec-kitty/spec-kitty adversarial-squadInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add spec-kitty/spec-kitty --skill adversarial-squad -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/spec-kitty/spec-kitty.git skills-src && mkdir -p .github/skills && cp -r skills-src/src/charter/offering/skills/adversarial-squad .github/skills/adversarial-squad && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "adversarial-squad" agent skill from https://github.com/spec-kitty/spec-kitty/tree/main/src/charter/offering/skills/adversarial-squad into .github/skills/adversarial-squad/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "adversarial-squad", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add spec-kitty/spec-kitty --skill adversarial-squad -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install spec-kitty/spec-kitty adversarial-squad --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/spec-kitty/spec-kitty.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/src/charter/offering/skills/adversarial-squad .opencode/skills/adversarial-squad && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "adversarial-squad" agent skill from https://github.com/spec-kitty/spec-kitty/tree/main/src/charter/offering/skills/adversarial-squad into .opencode/skills/adversarial-squad/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "adversarial-squad", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
adversarial-squad- GitHub stars
- 1.7k
- Token cost
- ~406 tokens
- SKILL.md length
- 108 words
- Files
- 1
- Skills in repo
- 50
- Repo updated
- First seen
- Licence
- MIT
At a glance
Deploy a bounded, profile-loaded adversarial review squad at a mission point-cut so independent doctrine lenses converge on findings one reviewer would miss.
- Tasks that involve Design review and critique
- SKILL.md covers Load the procedure and Invocation
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Adversarial Squad is an agent skill from spec-kitty/spec-kitty. Deploy a bounded, profile-loaded adversarial review squad at a mission point-cut so independent doctrine lenses converge on findings one reviewer would miss. Triggers: "deploy a squad", "adversarial squad", "post-tasks anti-laziness pass", "pre-spec investigation squad", "brownfield check", "second opinion on this design", "review squad", "run a multi-lens review". Does NOT handle: the implement-review loop (use spec-kitty-implement-review), spec/plan/tasks generation, or direct code editing by the orchestrator…
Its SKILL.md is about 410 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Media & Creative, covering Design review and critique. The repository describes itself as: Spec-Driven Development with organizational governance. Specs tell AI agents what to build; Charter governs how they build it. Git-native missions, enforceable workflows, and… The licence is MIT.
When your agent uses it
- Tasks that involve Design review and critique
Example prompts
- “deploy a squad”
- “adversarial squad”
- “post-tasks anti-laziness pass”
- “/adversarial-squad”
What it can do on your machine
Read from SKILL.md and the folder at commit 4cabb90. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Adversarial Squad loads about 406 tokens when it runs. Until then it costs about 155 tokens; SKILL.md has 108 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from spec-kitty/spec-kitty at commit 4cabb90, republished under its MIT licence (© spec-kitty). 108 words, ~406 tokens.
Download SKILL.mdSave it as
.claude/skills/adversarial-squad/SKILL.md (or your agent's skills folder).- name
- adversarial-squad
- description
- Deploy a bounded, profile-loaded adversarial review squad at a mission point-cut so independent doctrine lenses converge on findings one reviewer would miss. Triggers: "deploy a squad", "adversarial squad", "post-tasks anti-laziness pass", "pre-spec investigation squad", "brownfield check", "second opinion on this design", "review squad", "run a multi-lens review". Does NOT handle: the implement-review loop (use spec-kitty-implement-review), spec/plan/tasks generation, or direct code editing by the orchestrator. It is an optional, charter/memory-activated enrichment — it never gates a mission.
Adversarial Squad Deployment (harness)
The operational alias for the doctrine procedure adversarial-squad-deployment
(packs/built-in/procedures/adversarial-squad-deployment.procedure.yaml), which is
the single owner of when, who, and how to run a squad. This skill changes no
mission type or guard; it is a technique the orchestrator opts into.
Load the procedure
Before dispatching, load the procedure's full playbook:
spec-kitty charter context --include procedure:adversarial-squad-deploymentApply its point-cut list, casting rule, dispatch discipline, model-tier routing, synthesis step, and findings-disposition contract as written there — this skill does not restate them.
Invocation
Invoke by name (adversarial-squad) with the point-cut + question, e.g.
"adversarial-squad: post-tasks anti-laziness on WP01–WP08." This skill is the alias
surface; the doctrine procedure is the canonical record of the technique.
© spec-kitty, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in src/charter/offering/skills/adversarial-squad of spec-kitty/spec-kitty.
Open the folder on GitHubat commit 4cabb90
Compare with similar skills
Adversarial Squad next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Adversarial Squad this skillspec-kitty/spec-kitty | 1.7k | — | ~406 | Automated safety check: Pass | MIT | |
| Consult ClaudeEpicenterHQ/epicenter | 4.8k | — | ~2k | Automated safety check: Pass | Custom licence | |
| System Atlasinkboard/system-atlas | 429 | — | ~2.3k | Automated safety check: Pass | MIT | |
| Design Image Studiokangarooking/design-image-studio | 102 | — | ~1.5k | Automated safety check: Pass | MIT | |
| Kicad Reviewmixelpixx/Konnect | 905 | — | ~3.2k | Automated safety check: Pass | AGPL-3.0 | |
| Reimagine It AuditKayforkind/reimagine-it | 203 | 1 repos | ~756 | Automated safety check: Pass | MIT |
Similar skills
System Atlas
inkboard/system-atlas
Build and maintain an explorable, progressively-disclosed isometric "atlas" of a system's architecture — an interactive page (hover to read, click to pin, go inside for steps, moving data packets…
Design Image Studio
kangarooking/design-image-studio
Directly generate design-oriented AI images with strong creative direction and prompt engineering.
Kicad Review
mixelpixx/Konnect
Design review and validation workflow for KiCAD projects via MCP tools.
Reimagine It Audit
Kayforkind/reimagine-it
Design Health — runs 19 deterministic quality checks on HTML output.
Design Audit
UniClipboard/UniClipboard
定期审计代码库的工程设计问题（高心智复杂度、单一真相源被破坏、catch-all 胖接口、死代码、散落魔法字面量、泄漏抽象、资源生命周期靠环形缓冲）与可优化点，范围限定为自上次审计以来的 git churn，每条发现都落到 file:line 并对照本项目自己的 VISION.md / 各级 AGENTS.md / memory…
More from spec-kitty/spec-kitty
All 50 skills in this repoSpec Kitty Setup Doctor
spec-kitty/spec-kitty
Install, verify, and recover the modern Spec Kitty 2.0.11+ operating surface.
Spk Doctrine Show Me
spec-kitty/spec-kitty
Explain Spec Kitty work with compact, checkable visuals. An agent skill from spec-kitty/spec-kitty.
Spec Kitty Git Workflow
spec-kitty/spec-kitty
Understand how Spec Kitty manages git: what git operations Python handles automatically, what agents must do manually, worktree lifecycle, auto-commit behavior, merge execution, and the safe-commit…
Spec Kitty Glossary Context
spec-kitty/spec-kitty
Curate and apply canonical terminology across Spec Kitty missions.
Spec Kitty Mission System
spec-kitty/spec-kitty
Understand how Spec Kitty missions work: the 4 built-in mission types, how they define workflows via step contracts and action indices, how missions and work packages relate, how templates are…
Spec Kitty Orchestrator API Operator
spec-kitty/spec-kitty
Teach agents and external systems how to use spec-kitty orchestrator-api to drive workflows from outside the host CLI.
Related
Categories
Questions about Adversarial Squad
What does Adversarial Squad do?
Deploy a bounded, profile-loaded adversarial review squad at a mission point-cut so independent doctrine lenses converge on findings one reviewer would miss. Adversarial Squad is an agent skill from spec-kitty/spec-kitty. Deploy a bounded, profile-loaded adversarial review squad at a mission point-cut so independent doctrine lenses converge on findings one reviewer would miss.
When should I use Adversarial Squad?
Adversarial Squad fits situations like: tasks that involve Design review and critique.
How do I install Adversarial Squad in Claude Code?
Run `npx skills add spec-kitty/spec-kitty --skill adversarial-squad -a claude-code`. Or copy the skill folder (src/charter/offering/skills/adversarial-squad in spec-kitty/spec-kitty) into .claude/skills/adversarial-squad in your project. Claude Code loads it when a task matches its description.
How do I install Adversarial Squad in Codex?
Run `npx skills add spec-kitty/spec-kitty --skill adversarial-squad -a codex`. Or copy the skill folder (src/charter/offering/skills/adversarial-squad in spec-kitty/spec-kitty) into .agents/skills/adversarial-squad in your project. Codex loads it when a task matches its description.
Can I use Adversarial Squad in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add spec-kitty/spec-kitty --skill adversarial-squad -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/adversarial-squad, .gemini/skills/adversarial-squad, .github/skills/adversarial-squad and .opencode/skills/adversarial-squad in your project.
What does Adversarial Squad need to run?
SKILL.md names no scripts, command-line tools or credentials: Adversarial Squad is instructions for the agent only.
Does Adversarial Squad access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Adversarial Squad safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Adversarial Squad use?
Adversarial Squad is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Adversarial Squad use?
About 406 tokens (SKILL.md is roughly 1.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Adversarial Squad?
Skills that share tags, products or a category with Adversarial Squad: Consult Claude (EpicenterHQ/epicenter, 4.8k stars), System Atlas (inkboard/system-atlas, 429 stars), Design Image Studio (kangarooking/design-image-studio, 102 stars) and Kicad Review (mixelpixx/Konnect, 905 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Adversarial Squad?
spec-kitty (a GitHub organization) maintains it in spec-kitty/spec-kitty, which has 1,677 GitHub stars. The repository holds 50 skills in this directory. The repository was last updated on October 8, 2026.
Source: spec-kitty/spec-kitty on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.