byhoodini· 40 skills
Detect installed AI coding agents and append honest-feedback rules to their instruction files. Scans for config files (CLAUDE.md, copilot-instructions.md, .cursorrules, etc.), adapts output format per agent, and appends directives that disable sycophancy and enable constructive pushback. Use when setting up honest feedback, disabling people-pleasing, or enabling objective criticism. Triggers on honest agent, objective feedback, no sycophancy, honest criticism, contradict me, challenge assumptions, honest mode, brutal honesty.
$npx -y skills add hoodini/ai-agents-skills --skill honest-agentInstalls into the current project.
Run `npx skills use "https://github.com/hoodini/ai-agents-skills" --skill "hoodini/ai-agents-skills/honest-agent"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/hoodini/ai-agents-skills" that are relevant to the current task. Run `npx skills add "https://github.com/hoodini/ai-agents-skills"` and select the relevant skills, then follow their instructions.