deslop
Deslop analyzes git branch diffs against main to identify and remove AI-generated code artifacts like unnecessary comments, defensive error handling, premature abstractions, and over-engineering. Use it after completing feature work but before committing to simplify code while preserving functionality.
git clone --depth 1 https://github.com/rohitg00/pro-workflow /tmp/deslop && cp -r /tmp/deslop/skills/deslop ~/.claude/skills/deslopSKILL.md
# Remove AI Code Slop Check the diff against main and remove AI-generated slop introduced in the branch. ## Trigger Use after completing changes, before committing, or when code feels over-engineered. ## Commands ```bash git fetch origin main git diff origin/main...HEAD --stat git diff origin/main...HEAD ``` ## Workflow 1. Run diff commands to see all changes on the branch. 2. Identify slop patterns from the focus areas below. 3. Apply minimal, focused edits to remove slop. 4. Re-run `git diff origin/main...HEAD` to verify only slop was removed. 5. Run tests or type-check to confirm behaviour unchanged: `npm test -- --changed --passWithNoTests 2>&1 | tail -10` 6. Summarise what was cleaned. ## Focus Areas - Extra comments that state the obvious or are inconsistent with local style - Defensive try/catch blocks that are abnormal for trusted internal code paths - Casts to `any` used only to bypass type issues - Over-engineered abstractions for one-time operations (premature helpers, factories) - Deeply nested code that should be simplified with early returns - Backwards-compatibility hacks (renamed `_vars`, re-exports, `// removed` comments) - Features, refactoring, or "improvements" beyond what was requested - Added docstrings, type annotations, or comments on code that wasn't changed - Error handling for scenarios that can't happen in trusted internal paths ## Guardrails - Keep behavior unchanged unless fixing a clear bug. - Prefer minimal, focused edits over broad rewrites. - Three similar lines of code is better than a premature abstraction. - If you remove something, verify it's truly unused first. - Keep the final summary concise (1-3 sentences). ## Skill-file mode When the target is a `SKILL.md` (not a code diff), lint it against the same slop instinct applied to prose. Run this before promoting a skill. Flag: - **Stale lines** - guidance written for an old version of the skill that no longer matches what it does. Cut it. - **Bloat** - the skill runs past one screen with detail that belongs in a linked reference. Push it down: in-skill step, then in-skill reference, then an external file behind a pointer. - **Dead sentences** - a line that changes nothing if deleted. Delete it. - **Duplication** - the same instruction stated in two places, so edits drift. Keep one source of truth. - **Premature stop** - the method ends before the work does (asks the question but never records the answer, cleans but never verifies). - **Weak anchor** - no single concept the skill turns on. A skill the reader can name in one word triggers and executes in fewer tokens. - **Missing invocation intent** - no declared human-run vs auto-triggered mode. See [`rules/skill-conventions.mdc`](../../rules/skill-conventions.mdc). - **Wrong write op** - a state-changing skill that does not say whether it adds, updates, or appends, or that duplicates its output on a second run. **Skill-file mode output:** the flagged issues by line, the edits applied, the cleanup summary, and whether the skill is ready to promote. ## Output (code mode) - List of slop patterns found with file locations - Edits applied - One-line summary of what was cleaned
Coordinate multiple Claude Code sessions as a team — lead + teammates with shared task lists, mailbox messaging, and file-lock claiming. Patterns for team sizing, task decomposition, and when to use teams vs sub-agents vs worktrees.
Auto-configure quality gates, hooks, and settings for a new project. Detects project type and sets up appropriate tooling. Use when onboarding a new codebase.
Decompose large-scale changes into independent units and spawn parallel agents in isolated worktrees. Use for migrations, refactors, codemods, and any change touching 10+ files with the same pattern.
Capture a user-reported defect as a durable GitHub issue written in the project's own domain language. Explores the codebase in parallel for context but never leaks file paths or line numbers into the issue. Use when the user reports a bug conversationally, runs a QA pass, or says "file an issue", "log this as a bug", "capture this".
Smart context compaction with state preservation. Saves critical files, task progress, and working state before compaction, restores after. Use before manual compact or when auto-compact triggers.
Analyzes and optimizes context window usage across sessions. Use when context feels bloated, sessions run slow, or approaching compaction limits.
Master the four operations of context engineering — Write, Select, Compress, Isolate. Manage token budgets, compaction strategies, and context partitioning to keep AI sessions sharp and efficient.
Optimize token usage and context management. Use when sessions feel slow, context is degraded, or you're running out of budget.