deslop
Run a multi-agent review-readiness pass on a nearly finished change before commit; fan out parallel review agents across rule conformance, type safety, and overengineering, then synthesize and apply the worthwhile fixes.
What this skill does
# Deslop Run this only after the change is functionally correct and before `commit`. PR text should describe already-deslopped code. ## Goals - Keep the smallest clear diff that still solves the task. - Run focused reviews in parallel instead of one subjective final pass. - Preserve behavior while improving clarity, type safety, and rule alignment. ## Required review vectors (exactly 3 agents, in parallel) All 3 agents get the same context bundle, but each gets one vector: 1. **Rules and docs conformance** - Check `AGENTS.md`, nested `AGENTS.md`, design docs, and core beliefs. - Flag drift from documented patterns or ownership boundaries. 2. **Type safety and source of truth** - Preserve canonical types and inference flow. - Flag casts, duplicated/redefined types, or unnecessary widening. - Prefer compile-time guarantees inside typed internal code. - Validate only at untrusted boundaries; do not re-validate trusted internal values. 3. **Overengineering and simplification** - Remove unnecessary code, wrappers, abstractions, factories, or indirection. - Prefer direct, local solutions when equivalent. ## Required context bundle Read and pass these paths: - repo root `AGENTS.md` - nested `AGENTS.md` for changed areas - `docs/index.md` - `docs/PLANS.md` - `docs/design-docs/index.md` - `docs/design-docs/core-beliefs.md` - directly relevant design docs - active exec plan for this work (if any) - changed files plus nearby context If working on an ExecPlan: - inspect `docs/exec-plans/active/` - if one clearly matches, tell reviewers to study it carefully before reviewing ## Delegation protocol 1. Read the full context bundle yourself first. 2. Launch all 3 required review agents immediately (in parallel). - Do **not** wait for local lint/slop checks. 3. Give each agent: - same context bundle - one assigned review vector - instruction to return findings first, ordered by severity, with file refs 4. While agents run, start with: - `pnpm -w lint:slop:delta` 5. After all responses arrive, synthesize under these exact headings: - `How did we do?` - `Feedback to keep` - `Feedback to ignore` - `Plan of attack` 6. Use balanced synthesis over any single reviewer’s extreme take. ## Auto-apply feedback (unattended flows) Apply clear, in-scope fixes before commit, prioritizing: - type drift, casts, duplicate type definitions - documented boundary/design-belief violations - dead helpers/code/debug leftovers/placeholders - removable local indirection Skip speculative, conflicting, or scope-expanding suggestions; note briefly in synthesis/workpad. ## Execution steps 1. Gather context bundle. 2. Launch 3 required review agents in parallel. 3. Run `pnpm -w lint:slop:delta` and narrow local checks while they run. 4. Wait for responses and synthesize. 5. Apply worthwhile in-scope feedback. 6. Re-run the narrowest affected validation. 7. Update workpad/commit/PR text to describe final post-deslop state. ## Stop rules - No refactors unrelated to the ticket. - No churn outside changed area for style only. - Leave subjective/unclear “improvements” alone. - Do not blindly apply every suggestion.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.