ai-slop

Discovery before changes: explore the local codebase, run multi-source external research, and reconstruct why a past decision was made from evidence outside the code. Each dispatches a subagent by default so the reading stays out of the main thread, with source tiers, falsification, recency gates and a coverage ledger, and persists EXPLORE.md / RESEARCH.md / INTENT.md handoff artifacts. A research sweep workflow (/discovery:research-sweep) backs deep research with adversarial claim verification.

8 skills · 6 agents · hooks

Copy of claude-code-plugins' work-items plugin, for the work-resolve-issue lane's work skill.

12 skills

Ingests external knowledge into synthesized artifacts: book-distill (PDF or EPUB into author-attributed reference files), video-digest (one YouTube or X video: transcript, links, repo applicability), course-digest (Dometrain and Teachable courses into recommendations), docpage-digest (one documentation page into a verified knowledge slice), and map-corpus (a multi-resource corpus into a classified link map and an approved docpage-digest queue). setup sets where artifacts land.

7 skills

Copy of claude-code-plugins' source-control plugin, for the pr-unblock lane's resolve-conflicts skill.

6 skills · hooks

Test fixture for the pr-run-activity runner: skills that print or commit a fixed base marker string.

4 skills

Eval-only: puts the gh-forge stand-in first on the run's Bash PATH (fixtures/gh-forge/install.sh)

hooks

Zero-dependency HTML presentation generator with safe presets, bold template-library styles, PPT conversion, and anti-AI-slop design philosophy.

1 skill

Anti Slop: Rules for AI Coding Agents. Stops generic AI slop in generated UI, copy, and code. Loads as six skills.

6 skills · 1 MCP server

Design engineering for Claude Code. Build production-grade interfaces with strong visual hierarchy, review craft against an approval bar, and strip AI design slop. Maintains design decisions across sessions.

1 skill

If you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize with confidence. Original pstack by Lauren Tan (poteto).

68 skills · 4 agents · hooks

Real UI, not AI slop. The free no-ui-slop and uxkin-research skills (work with no account), plus the optional UXKIN MCP server for real iOS app screens, user journeys and website design systems (sign in with UXKIN; searching needs a UXKIN plan). Tool results are treated as data, never as instructions.

7 skills · 1 MCP server

Comprehensive codebase cleanup across 11 quality dimensions — dead code, duplication, weak types, circular deps, defensive cruft, legacy code, AI slop, type consolidation, security, performance, and async patterns. Confidence scoring and build verification gates.

1 skill · 11 agents