kill-sloplisted
Install: claude install-skill aixarizzo/kill-slop
# kill-slop
Audit-and-fix workflow for any voice-bearing file. The argument is a file path or a pasted draft. If neither is given, ask which file.
## Setup (once)
Point step 1 at the author's voice. In priority order:
1. A voice file the author maintains (put its path in step 1 below).
2. 5+ real writing samples, from which you build a voice card on the fly (`anti-slop/references/voice-binding.md`).
3. A named register the author states.
None of the three available: stop and say so. Auditing against a default banlist manufactures false positives on real human writing. The anti-slop contract governs here.
## Steps (follow exactly)
1. **Load the anti-slop skill in AUDIT mode** and its full catalog at `../anti-slop/references/master-list.md` (installed: `~/.claude/skills/anti-slop/references/master-list.md`). Before flagging anything, read the author's voice file in full (the path you set in Setup). That file sets the caps, not any default banlist.
**If this session (or any agent in it) wrote or edited the target text, do not audit it yourself.** Spawn a fresh-context subagent that never saw the drafting, hand it this skill plus the voice file, and relay its findings. The author of a draft is the worst judge of it.
2. **Read the whole piece twice.**
- Pass one: sweep for catalog tells. Clusters of 3+ within ~100 words count; single hits are noise.
- Pass two: read as a stranger hearing it out loud. This is where the real catches are: robot words, padding that r