review
Run a structured code review against the project's own conventions in claude/claude.md.
Skill by krone9
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/krone9-review
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/review
Tools it pre-approves 5
From allowed-tools in SKILL.md: the agent may use these without asking you each time.
Read,Bash(gitdiff:*),log:*),Bash(find:*)
What's inside
- Skill name
review- Description
- Run a structured code review against the project's own conventions in claude/claude.md. Use when the user types /review or asks for a code review.
- License
- MIT
- Allowed tools
- Read,, Bash(git, diff:*),, Bash(git, log:*),, Bash(find:*)
- Instructions
- 56 lines in SKILL.md · view on GitHub
Before installing
- Pre-approves some shell commands
Files (1)
- SKILL.md
SKILL.md (first lines)
## Task: Code review against project conventions This review checks code against YOUR project's rules in `claude/claude.md`, not just generic best practices. ### Step 1: Load project conventions Read `claude/claude.md` in full. Extract: - Naming conventions - Architectural rules - Forbidden patterns - Stack preferences - Folder structure rules If `claude/claude.md` does not exist, note this and fall back to general best practices. Recommend creating it after the review. ### Step 2: Determine what to review If $ARGUMENTS is provided, review that specific file or folder. Otherwise, review changed files since last commit: `git diff HEAD --name-only` ### Step 3: Run the review For each file, check against: **Convention violations** — anything that breaks rules explicitly defined in claude/claude.md. These are highest priority. **Architecture issues** — files in wrong folders, responsibilities in wrong modules, patterns that conflict with the project's established approach. **Code quality** — logic errors, edge cases, missing error handling, security issues (hardcoded secrets, unvalidated inputs). **Consistency** — naming that doesn't match the rest of the codebase, patterns used differently from how they're used elsewhere. ### Step 4: Output the review Format as: ``` ## Code Review — [date] ### 🔴 Convention Violations (must fix) - [file:line] — [what rule it breaks] — [suggested fix] ### 🟠 Architecture Issues - [file] — [issue] — [suggested fix] ### 🟡 Code Quality - [file:line] — [issue] — [suggested fix] ### 🔵 Consistency - [file:line] — [issue] — [suggested fix] ### ✅ Summary [count] issues found. [count] must fix, [count] advisory. ``` If no issues found in a category, omit that section. If claude/claude.md is missing, append: "⚠️ No claude/claude.md found — review used general standards only. Run /scaffold to create it."
From krone9/pi-superpowers, MIT.
More from krone9/pi-superpowers
- 0.497score
audit-structure
krone9
Audit an existing project against the standard structure and report gaps.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
dependencies
krone9
Scan the codebase and produce a plain-English map of how the main modules depend on each other.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
dispatching-parallel-agents
krone9
Use when the task contains 2+ independent sub-tasks that don't depend on each other's outputs.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
optimise
krone9
Run a structured optimisation sweep across the codebase — redundancy, efficiency, dead code.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
restart
krone9
Load context from the last session — changes log and next steps from build plan.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
rollback
krone9
Safely revert the last commit or staging push.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
status
krone9
Quick read-only project health snapshot.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
systematic-debugging
krone9
Use when something is broken or behaving unexpectedly — bugs, regressions, failing tests, mysterious errors.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
brief
krone9
Generate a one-page human-readable project brief for onboarding or re-orientation.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
changes
krone9
Append a log of all changes made in this session to claude/changes.md.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
nextsteps
krone9
Derive and record the next 3-5 prioritised tasks from the current build plan.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
rules
krone9
Load and display the project rules from claude/claude.md.
SkillCFreshness: C★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- May 5, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/krone9/pi-superpowers
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from krone9
- 0.497score
dependencies
krone9
Scan the codebase and produce a plain-English map of how the main modules depend on each other.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
dispatching-parallel-agents
krone9
Use when the task contains 2+ independent sub-tasks that don't depend on each other's outputs.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
optimise
krone9
Run a structured optimisation sweep across the codebase — redundancy, efficiency, dead code.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
restart
krone9
Load context from the last session — changes log and next steps from build plan.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
rollback
krone9
Safely revert the last commit or staging push.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
status
krone9
Quick read-only project health snapshot.
SkillCFreshness: C★ 1Claude Code +9
Cite this page
review skill. Agent Mart. https://agentmart.dev/skills/krone9-review (last updated 2026-10-24)