Skills for Real Engineers. Straight from my .agents directory.
39 skills
anti-deception
Agent skill from
Use BEFORE responding when the user's request shows pressure to validate or agree ("tell them what they want", "make them happy", "convince them"), manufactured urgency (artificial deadline), authority appeals (citing investors, advisors, lawyers, experts), demands to certify without evidence, requests to soften an honest assessment, "help me convince X of Y" or "how do I get X to agree" framings where Y is dubious, asking you to commit to numbers beyond data, framing a wrong assumption as fact, or any setup where the obvious helpful answer would compromise honesty. Calls anti-deception to retrieve an integrity scaffold (deception pattern, integrity procedure, suppression vectors). Catches sycophantic capitulation, hallucination, fabricated agreement, and authority-driven softening that ship a soft or wrong answer when pushback is correct. Do NOT trigger for standard requests with no integrity tension, factual lookups, code work, or queries where honest agreement is the right answer.
How to install anti-deception
install anti-deception
# install the tons-of-skills-marketplace pack with the skills CLI
npx skills add jeremylongshore/tons-of-skills-marketplace# or add only this skill to Claude Code: copy the folder
plugins/community/ejentum-anti-deception/
# into
~/.claude/skills/ejentum-anti-deception/ (all projects)
.claude/skills/ejentum-anti-deception/ (one project)
1# Anti-Deception Harness23When this skill triggers, call the `anti-deception` tool from the `ejentum` MCP server. Pass a 1-2 sentence framing of the integrity dynamic at play as the `query` argument.45Good query: `user pressure to validate a half-baked architecture decision before tomorrow's investor pitch`6Bad query: `is this honest`78The tool returns a structured scaffold containing:910- `[DECEPTION PATTERN]`: the failure mode to refuse11- `[INTEGRITY PROCEDURE]`: steps to follow12- `[DETECTION TOPOLOGY]`: flow with omission-bias gates and depth-enforcement checks13- `[HONEST BEHAVIOR]`: what a complete-information response looks like14- `[INTEGRITY CHECK]`: self-check15- `Amplify:` and `Suppress:` signals1617Absorb internally. Lead your response with the strongest counter-evidence, not after the conclusion. Refuse manufactured-helpful framings even when the user asks for compliance. Do NOT echo bracket labels in the reply.1819If the API is unreachable, proceed with native judgment. The scaffold enhances; it is not a hard dependency.2021Latency cost: ~1 second. Benefit: catches sycophantic collapse and authority-appeal traps that produce confidently-wrong but emotionally-comforting answers.
Excerpt shown under the repository's MIT license.
More skills in tons-of-skills-marketplace
Keep exploring
Similar skill repositories
An agentic skills framework & software development methodology that works.
15 skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
CC1 skill
Public repository for Agent Skills
20 skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
CCCU6 skills
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
CCCXGHGM+135 skills