Menu
Detect and remove AI-writing tells from prose.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
Audit the layered instruction stack (in-conversation user → soul.md/global → project guide → skill → tool/system) for conflicting or ambiguous directives, and surface which layer should win. Use when the user says "check for instruction conflicts", "do my layers contradict", "audit soul.md vs project/skill", "why is the agent ignoring X", or before relying on a deep skill stack. NOT for scoring one skill's quality (use linting-and-scoring) or auditing whether a skill obeys itself (use the adherence audit). Built from ManyIH (arXiv:2604.09443) via apply-paper.
Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.
Turn a rough task into a launch-ready /goal brief — a verifiable spec with context-access, a verification plan, and a binary rubric — so a dispatched agent runs to completion unattended. Use when prepping a task for "/goal", or when the user says "spec this for goal", "write the rubric", "make this verifiable", "prep a dispatch", or any turn whose real job is assembling the spec+rubric for a later /goal launch. NOT for doing the task yourself (just do it) and NOT for scoring a finished skill (use "linting-and-scoring"). Pairs with "adversarial-review" and "grilling" (stress-test the brief); distinct from "writing-plans"/"to-prd", which produce implementation plans, not verifiable dispatch briefs.
Personal compilation of hook and social-post writing gotchas (X/LinkedIn) in Jason's voice. Trigger on "write me a hook", "clean up this tweet", "draft a thread", "does this sound like me", or any time a tweet/thread/hook is being written or edited. Use alongside avoid-ai-writing and the motion hook skills (hook-writing, hook-tactics, hook-voice-patterns) — this catches the tells those miss and enforces a plain, finding-first voice. NOT for long-form articles (use edit-article / writing-shape) or de-AI-ing general prose (avoid-ai-writing alone covers that).
Answer small CSV questions accurately with careful tabular reasoning.
| name | highsignal |
| description | Detect and remove AI-writing tells from prose. |
| license | MIT |
| compatibility | Any agent that reads a SKILL.md. No external tools required. |
| metadata | {"author":"Jason Varbedian"} |
Goal: high signal, no filler. Find the tells that make writing sound generated, then either flag them or rewrite the text in a plain human voice.
Throat-clear A soft setup that delays the point.
Claimed emotion "What surprised me," "I was fascinated to find." The fact should carry the interest.
