// Detect repetitive AI defaults for a domain and generate a reusable avoidance profile. Use when asked to "unslop", "de-slop", "remove AI patterns", "make less generic", generate an anti-slop profile, or analyze AI output patterns for any domain (writing, landing pages, emails, code, etc.).
Audit and reconcile Thomas's todo list against all active data sources — calendar, email, customer deal docs, deal tracker spreadsheet, and any future sources. Use when Thomas asks to "review my todos", "what's outstanding", "todo audit", "anything I'm missing", "check my follow-ups", "what's stale", or as part of a Monday morning / Friday EOD review. Also use when he asks about overdue items, missed follow-ups, or wants a pipeline hygiene check.
Design things that AI agents can operate effectively — CLIs, tools, file formats, codebases, context layers, skills, visual assets, and any interface where agents are the primary or frequent consumer. Use when building a CLI for agents to use, structuring a codebase or repo for AI-assisted development, choosing file formats for agent-readable content, designing MCP tools or skills, creating agent-operable assets (HTML templates, markdown-driven workflows), setting up context infrastructure (AGENTS.md, SKILL.md, progressive disclosure), or making any existing system more agent-friendly. Also use when the user asks about agent DX, agent UX, or how to make something easy for agents to work with.
Extract session cookies from Chrome on macOS by decrypting Chrome's cookie database. Use when you need to authenticate API calls using the user's existing browser session — e.g., refreshing expired session cookies, accessing a service the user is logged into, or bootstrapping API access for a tool that uses cookie auth.
Process sales call recordings into structured customer intelligence. Use when the user asks to process a call transcript, create or update a deal doc, add to the playbook or glossary, or do any work involving call transcripts, deal qualification, or sales reference material.
| name | unslop |
| description | Detect repetitive AI defaults for a domain and generate a reusable avoidance profile. Use when asked to "unslop", "de-slop", "remove AI patterns", "make less generic", generate an anti-slop profile, or analyze AI output patterns for any domain (writing, landing pages, emails, code, etc.). |
Empirically detect the repetitive defaults a model falls back on, then produce a reusable instruction file that makes future outputs less generic.
# Text domains (writing, emails, tutorials, code)
python3 SKILL_DIR/unslop.py --domain "blog writing"
# Visual domains (websites, landing pages, HTML)
pip install playwright && playwright install chromium
python3 SKILL_DIR/unslop.py --domain "startup SaaS landing pages" --type visual --count 20 --concurrency 3
The script uses pi -p (non-interactive mode) to generate samples and run analysis. It works with whatever model/provider pi is configured for.
| Flag | Default | Description |
|---|---|---|
--domain | required | What to analyze |
--type | text | text for writing/code/prose, visual for websites/HTML |
--count | 50 | Number of samples to generate |
--concurrency | 5 | Parallel pi calls |
--model | pi default | Model to use (passed through to pi --model) |
--thinking | pi default | Thinking level: off, minimal, low, medium, high, xhigh |
--timeout | 600 | Seconds per pi call |
--analysis-timeout | 1800 | Seconds for the analysis pass |
--retries | 1 | Retries per failed call |
--output | ./unslop-output | Where to put results |
--skip-comparison | false | Skip the before/after step |
Results land in ./unslop-output/:
unslop-output/
skill.md ← the reusable avoidance profile (main deliverable)
analysis.md ← detailed pattern analysis with counts
prompts.json ← generated prompt set
samples/ ← raw AI outputs
screenshots/ ← rendered pages (visual only)
before-after/ ← vanilla vs. profile-guided comparison
Ready-to-use profiles are in SKILL_DIR/profiles/:
profiles/react-design.md — anti-patterns for React/SaaS landing pagesprofiles/writing.md — anti-patterns for blog writing, essays, articlesThese can be used immediately as pi skills or system prompt additions without running the full analysis.
pi -pskill.md with specific avoidance instructionsThe generated skill.md can be used as:
After running, verify:
analysis.md is concrete, counted, and specific (not vague)skill.md mostly says what to avoid, not prescribing one new stock stylebefore-after/after.html feels meaningfully less generic than before.html