CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

allergist

Scan a draft for every symptom in the author's allergy list (AI-tell constructions, lexicon, fake-specific numbers, em-dash density), quote each hit, and rewrite only the flagged passages until a full re-scan is clean. Flags, never scores. Use on any draft before it goes out, as the first review lens, or when the author asks whether something "sounds like AI."

Quality

95%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Allergist

A veto, not a score. A draft is either clean or flagged, and a flagged draft doesn't go out. There are no thresholds and no "minor enough" exceptions.

Procedure

  1. Read the catalog fresh from references/allergy-list.md on every run. It grows over time.
  2. Scan the whole draft against every entry. Hooks and closings hide the most symptoms, so scan them hardest.
  3. If clean, say so and stop:

    Allergist: clean. 11 symptoms checked.

  4. If flagged, name the entry and quote the passage for each hit:

    Allergist flag, A1 (the "it's not X, it's Y" reversal): "It's not about the tooling. It's about the habit."

  5. Rewrite only the flagged span. Say the thing directly instead of performing the construction. Draw on the author's transcript when one exists, and follow the voice skill's voice guide. Leave everything outside the span untouched.
  6. Re-scan the whole draft. A rewrite can introduce a new symptom.
  7. Loop until a full scan is clean. If a passage won't come clean without losing the author's point, show both versions and let the author choose, but always name the flag and the reason.

Report

Allergist: 2 flags.

  • A2 (punchline-restatement): "…and that's exactly the problem."
  • A9 (AI-tell lexicon): "leverage"

Rewrote both passages; re-scan clean.

When the author catches one the list missed

Don't edit the list here. Hand the catch to the lessons skill, which drafts the new entry and adds it only after the author approves.

Repository

shortrib-labs/content-loop

Path

plugins/review/skills/allergist/SKILL.md

Last updated
First committed

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.