code-review-and-quality
Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human.
What this skill does
# Code Review and Quality Adapted from `addyosmani/agent-skills` (MIT), commit `82ceff41ed4d3c644e3dcca8a0514390b2911223`. ## Overview Review changes across five axes: correctness, readability, architecture, security, and performance. The standard is not perfection; it is whether the change clearly improves the codebase without introducing avoidable risk. ## When to Use - Before merging any change - After completing a feature, bug fix, or refactor - When reviewing code produced by another agent or automation - When validating whether tests and verification are actually sufficient ## The Five-Axis Review ### 1. Correctness - Does the change do what the task or spec requires? - Are happy paths, edge cases, and error paths handled? - Do tests cover the real behavior change? ### 2. Readability and Simplicity - Are names clear and consistent with the codebase? - Is control flow easy to follow? - Are there any clever shortcuts that should become straightforward code? ### 3. Architecture - Does the change follow existing patterns? - Are boundaries between modules still clean? - Is the abstraction level appropriate for the current need? ### 4. Security - Is untrusted input validated at boundaries? - Are secrets kept out of code and logs? - Are auth, permissions, and external data flows handled safely? ### 5. Performance - Any N+1 access patterns, repeated expensive work, or unbounded operations? - Any missing pagination, batching, caching, or async boundaries? ## Review Process ### Step 1: Understand Intent Before commenting on the code, identify: - What changed - Why it changed - What proof should exist that it works ### Step 2: Review Tests First Tests reveal intent faster than implementation details. - Are there regression tests for bug fixes? - Do tests verify behavior rather than private implementation? - Would the tests fail if the bug returned? ### Step 3: Review the Implementation Inspect each changed file with the five axes in mind. Prefer concrete findings over style preferences. ### Step 4: Label Findings Clearly Use explicit severity so the author knows what blocks merge. - `Critical:` security issue, broken behavior, or data loss risk - Required: must change before merge - `Optional:` worthwhile but not blocking - `Nit:` cosmetic or style-only - `FYI:` context only ### Step 5: Verify the Verification Story Check what was actually run: - targeted tests - full relevant suite - build and typecheck - manual verification for UI or operational changes ## Review Output Template ```markdown ## Findings - Critical: ... - Required: ... - Optional: ... ## Verification - Tests: ... - Build: ... - Manual: ... ``` ## Common Rationalizations | Rationalization | Reality | |---|---| | "The tests pass, so it is fine" | Tests are necessary, not sufficient. They do not prove architecture, readability, or security are sound. | | "AI-generated code is probably okay" | AI code needs more scrutiny, not less. It is often plausible and confidently wrong. | | "We can clean it up later" | Deferred cleanup usually does not happen. | ## Red Flags - No regression test for a bug fix - Large change with no explanation or verification summary - Review feedback that never labels severity - Security-sensitive changes reviewed only for style - Large diffs that should have been split ## Verification - [ ] Critical issues resolved - [ ] Required issues resolved or explicitly deferred with justification - [ ] Relevant tests pass - [ ] Build succeeds - [ ] Review summary documents what was checked
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.