strikersam
@strikersam
Public Skills
Skill: system-prompt-audit
by strikersam
council-review — multi-agent review process
Skill: prompt-library
by strikersam
docs-sync — general documentation sync
browserbase-ui-test
by strikersam
Adversarial UI testing via browser automation — tries to BREAK the app, not confirm it works. Analyzes git diffs to test changed code, or explores the full app for defects. Use before merging UI changes or to audit the deployed platform.
modularity-review
by strikersam
Review codebase or design for modularity problems and produce actionable improvement recommendations. Also guides design of new modular boundaries from functional requirements. Inspired by Vlad Khononov's balanced-coupling model and golden-age-of-modularity principles. NOTE: Full upstream plugin at https://github.com/vladikk/modularity Install it for the complete experience: follow instructions at that URL. This skill is a clean-room local adaptation for this repo.
wrap-up
by strikersam
Session closing ritual with learning capture. Run at the end of every coding session. 5 steps: changes audit, quality check, learning capture, next session planning, summary.
Skill: ticket-to-pr
by strikersam
→ scope-guard: to stay focused
implementation-planner
by strikersam
Plan a multi-file or multi-step implementation before writing any code. Use before any change touching more than two files, adding a new feature, or changing a module interface.
repo-memory-updater
by strikersam
Keep CLAUDE.md files and .claude/state/ in sync with the current repo reality. Use after significant structural changes, after adding risky modules, or when CLAUDE.md feels stale.
agent-browser
by strikersam
Browser automation via Chrome DevTools Protocol — use real Chrome to navigate, interact with, and test web UIs. 93% fewer tokens than Playwright MCP. Use when asked to test a UI, set up a web platform, fill in forms, or verify a deployed app works correctly.
deslop
by strikersam
Remove AI code slop before committing. Review AI-generated code for unnecessary verbosity, redundant comments, over-engineering, and low-signal patterns that degrade codebase quality over time.
dependency-audit
by strikersam
Review, validate, and update Python dependencies safely. Use when adding a new package, upgrading an existing one, or reviewing the dependency surface.
fabric-patterns
by strikersam
Implements a Fabric-like reusable prompt pattern system. Allows storing, retrieving, and composing prompt patterns for consistent AI interactions.
Skill: lr-schedule-advisor
by strikersam
Pairs with insights to compare schedule experiments across runs
test-first-executor
by strikersam
Write or update tests before (or alongside) implementation. Ensures every code change is verifiably correct before merging.
modularity-review
by strikersam
Review codebase or design for modularity problems and produce actionable improvement recommendations. Also guides design of new modular boundaries from functional requirements. Inspired by Vlad Khononov's balanced-coupling model and golden-age-of-modularity principles. NOTE: Full upstream plugin at https://github.com/vladikk/modularity Install it for the complete experience: follow instructions at that URL. This skill is a clean-room local adaptation for this repo.
Skill: data-quality-audit
by strikersam
Re-run after any tokenizer change — fertility and special token checks are tokenizer-dependent
docs-sync
by strikersam
Keep documentation in sync after code changes. Run after any change that alters module behaviour, APIs, env vars, or architecture.