Deception
Use this skill to generate believable synthetic artifacts for testing, demos, adversarial exercises, or rehearsal environments. The goal is plausibility under inspection by software and operators, not manipulation of real users or fabrication of evidence.
Install
npx skills add Hmbown/Wizards-of-the-Ghosts --skill deceptiongit clone --depth 1 https://github.com/Hmbown/Wizards-of-the-Ghosts.git /tmp/Wizards-of-the-Ghosts
mkdir -p ~/.claude/skills
cp -r /tmp/Wizards-of-the-Ghosts/generated/hermes/simulation-and-staging/deception ~/.claude/skills/deceptionPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Deception Forge realistic stand-ins for systems, traffic, and data without misleading actual people. ## What This Skill Does Use this skill to generate believable synthetic artifacts for testing, demos, adversarial exercises, or rehearsal environments. The goal is plausibility under inspection by software and operators, not manipulation of real users or fabrication of evidence. In this grimoire, Deception is treated as a metaphorical skill with a shipping-now delivery profile. Canonical reference input: Deception (skill). ## When To Use - You need fake data, demo traffic, or a mock environment that feels operationally real. - Testing requires a plausible cover story, persona, or artifact without touching production. - Smoke tests or drills work better when the synthetic inputs resemble actual conditions. ## Prerequisites - No extra runtime dependencies beyond Hermes Agent and the normal toolset for this session. ## Procedure 1. Restate the target, the success condition, and any no-touch boundaries before taking action. 2. Identify which signals must look authentic and which markers must remain clearly synthetic. 3. Generate the stand-in artifacts and validate them against the target format, workflow, or constraint. 4. Return the synthetic set with labeling, isolation rules, and notes on what realism it is simulating. 5. Package the result as the deliverables below, with confidence, assumptions, and unresolved risk called out explicitly. ## Deliverables
Details
- Skill name
deception- Repository
- Hmbown/Wizards-of-the-Ghosts
- Path
generated/hermes/simulation-and-staging/deception/SKILL.md- License
- CC0-1.0
- Repo updated
- 5 April 2026
FAQ
What does the Deception skill do?
Use this skill to generate believable synthetic artifacts for testing, demos, adversarial exercises, or rehearsal environments. The goal is plausibility under inspection by software and operators, not manipulation of real users or fabrication of evidence.
How do I install the Deception skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add Hmbown/Wizards-of-the-Ghosts --skill deception. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Deception popular?
It lives in Hmbown/Wizards-of-the-Ghosts, which has 113 GitHub stars and 11 forks.
Related skills
Acrobatics
113Hmbown/Wizards-of-the-Ghosts
Use this skill when the work is a choreography problem: brittle sequencing, async handoffs, or constrained flows that must stay upright end to end. It shines on API dances, dependency ordering, and recovery logic where grace matters more than brute force.
Animal Friendship
113Hmbown/Wizards-of-the-Ghosts
Animal Friendship is the first-contact spell for unfamiliar APIs, vendors, and services. It treats integration work as relationship-building: learn the temperament, respect the boundaries, and earn a stable exchange before asking for anything ambitious. The goal is not domination but trustable cooperation.
Animal Handling
113Hmbown/Wizards-of-the-Ghosts
Use this skill when the system is not fully broken but behaves like a skittish animal: flaky CI, fragile legacy services, or moody dependencies. It focuses on coaxing, pacing, and stable handling rather than heroic rewrites.
Design Distiller
65Yrzhe/claude-skills
Scrape any website's design system into a structured Design MD + decomposed design tokens. Supports Browser Use Cloud, Playwright, Chrome headless, source code analysis. Maintains a Reference Pool of full Design MDs and a Digest Pool of cross-site design tokens for mix-and-match composition.
Bestow Curse
113Hmbown/Wizards-of-the-Ghosts
Bestow Curse saddles a target with a lasting disadvantage. The real-world version is constraint injection: deliberately adding friction, limitations, or handicaps to see how a system, process, or team adapts. This is the skill of resilience testing through artificial adversity — bandwidth throttling, feature removal, resource reduction.
Fix Issue
49lllyys/vreader
End-to-end GitHub issue resolver — fetch, classify, branch, fix with TDD, Codex audit loop, test gate, docs-sync, version bump, PR, and post-merge close-gate finalizer. Use this skill whenever the user wants to fix a bug from a GH issue, asks 'fix issue #N', 'fix bug 115', 'work on issues #123 #456 #789', 'resolve this GH bug', or pastes a GH issue URL/number for resolution. Also handles `question`-labeled issues (inline answer + comment, no branch). REDIRECTS feature/enhancement issues to feature-workflow per rule 47. Supports both single-issue and multi-issue (worktree) pipelines.
Browse the most popular Claude skills, all testing & qa skills, or write your own with the skills generator.