kiro-review
Skill15 starsChanged 8 months agoApache-2.0View on GitHub
Run Kiro CLI to review code changes made in the current session or branch. Invokes `kiro-cli chat` in non-interactive mode with focused review instructions derived from the actual changes. Use when the user says "kiro review", "second opinion", "rival review", "cross-review", or "/kiro-review".
5 other projects use a version of this.
Adopted by
Most recently taken up by
- aiproxer/aiproxertheir own version, first seen Nov 8, 2026
- growilabs/growitheir own version, first seen Oct 8, 2026
- kksmiles/claude-skills-kirotheir own version, first seen Aug 25, 2026
- kyuki3rain/cc-sdd-adrtheir own version, first seen Jul 27, 2026
- studiogadget/skillstheir own version, first seen May 22, 2026
Used with
Projects with it also use kiro-debug, kiro-discovery and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
studiogadgetSkillkiro-debug
Investigate implementation failures using root-cause-first debugging. Use when an implementer is blocked, verification fails, or repeated remediation does not converge.
Also in 4 projects that use this
studiogadgetSkillkiro-discovery
Entry point for new work. Determines the best action path or work decomposition (update existing spec, create new spec, mixed decomposition, or no spec needed) and refines ideas through structured dialogue.
Also in 4 projects that use this
- +10 more from studiogadget
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- growilabs/growi★ 1.5ksame name
- aiproxer/aiproxer★ 24same name
- studiogadget/skills★ 3same name
- kksmiles/claude-skills-kiro★ 1same name
- kyuki3rain/cc-sdd-adr★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository63 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- agent-browserSkill
- ast-grepSkill
- branch-review-before-prSkill
- browse-qaSkill
- browser-useSkill
- browseSkill
- bugfixSkill
- build-dmgSkill
- claude-reviewSkill
- codemapSkill
- code-simplifySkill
- codex-reviewSkill
- commitSkill
- cost-estimateSkill
- create-prSkill
- find-agentsSkill
- find-bugsSkill
- frontend-design-ui-uxSkill
- git-merge-expertSkill
- git-merge-expert-worktreeSkill
- laravel-filamentSkill
- laravelSkill
- lokeiSkill
- map-project-monorepoSkill
- map-projectSkill
- nextjsSkill
- plan-founder-reviewSkill
- plan-to-task-list-with-dagSkill
- pr-retroSkill
- run-parallel-agents-feature-buildSkill
- run-parallel-agents-feature-debugSkill
- rustSkill
- secretsSkill
- startSkill
- update-agent-learningsSkill
- update-claude-learningsSkill
- update-claude-settingsSkill
- update-skill-learningsSkill
- ast-grepSkill
- branch-review-before-prSkill
- codemapSkill
- code-simplifySkill
- commitSkill
- cost-estimateSkill
- create-prSkill
- find-bugsSkill
- frontend-design-ui-uxSkill
- git-merge-expertSkill
- git-merge-expert-worktreeSkill
- map-project-monorepoSkill
- map-projectSkill
- plan-founder-reviewSkill
- plan-to-task-list-with-dagSkill
- pr-retroSkill
- run-parallel-agents-feature-buildSkill
- run-parallel-agents-feature-debugSkill
- startSkill
- update-agent-learningsSkill
- The first 60 shown.
The file
Show its rules and text
We split this skill into the rules it gives an agent
17 rules. 0 are common, 12 are distinctive, and 5 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
12
Distinctive
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 9
Use Kiro CLI to get an independent AI review of code changes.
- Distinctive: line 46
Read the diff to understand what areas need review focus.
- Very specific: line 57
Write a focused review prompt to /tmp/kiro-review-prompt.md:
- Very specific: line 100
Always capture stderr with 2>&1 (kiro logs to stderr)
- Distinctive: line 102
Run this in the background if the review is expected to take long:
- Very specific: line 103
Use run_in_background on the Bash tool
- Distinctive: line 112
Read the kiro output and extract findings.
- Distinctive: line 127
If the user wants to fix the findings:
- Distinctive: line 128
Read each cited file to verify the finding is real
- Distinctive: line 130
Run tests and typecheck
- Distinctive: line 137
Update the prompt to list all previously fixed issues
- Distinctive: line 138
Run round N+1 with the updated prompt
- Distinctive: line 141
Critical for iteration: Always add previously fixed issues to the prompt's exclusion list.
- Very specific: line 205
Kiro not installed: Check which kiro-cli first, tell user to install
- Very specific: line 206
Not logged in: Run kiro-cli whoami — user needs to kiro-cli login
- Distinctive: line 208
Repeated findings: Always maintain the exclusion list between rounds
- Distinctive: line 209
False positives: Always read the cited code before acting on findings
“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Kiro Review
Use Kiro CLI to get an independent AI review of code changes.
When to Use
- User explicitly asks for a kiro review, second opinion, or cross-review
- User says "run kiro", "kiro review", "/kiro-review"
- User wants an independent AI to verify Claude's work before merging
Prerequisites
kiro-climust be installed (which kiro-cli)- User must be logged in (
kiro-cli whoami)
Workflow
Step 1: Determine the Review Scope
Identify what to review:
# Option A: Review current branch against main
git log --oneline main..HEAD | head -20
# Option B: Review uncommitted changes
git diff --stat
# Option C: Review a specific commit
git show --stat <sha>Determine the diff to feed into the review:
- Branch review:
git diff main..HEAD - Uncommitted changes:
git diff - Single commit:
git show <sha>
Step 2: Analyze the Changes and Build the Prompt
Read the diff to understand what areas need review focus. Build a focused review prompt based on the actual code changes.
# Get the diff summary
git diff --stat <base>..HEAD
# Identify key areas
git diff --name-only <base>..HEAD | sed 's|/[^/]*$||' | sort -uWrite a focused review prompt to /tmp/kiro-review-prompt.md:
Review the code changes on this branch compared to main.
The changes cover: [brief description of what changed].
Focus your review on:
1. [Area 1 based on actual changes]
2. [Area 2 based on actual changes]
3. [Area 3 based on actual changes]
For each finding, report:
- Priority: P1 (critical), P2 (important), P3 (minor)
- File and line number
- Description of the issue
- Suggested fix
Verify each finding against the actual code. Read the relevant
source files before reporting. Do not report style issues.
Output a markdown table of findings.Key principles for the prompt:
- Be specific about what changed -- generic prompts get generic results
- List previously known issues so kiro doesn't re-report them
- Focus on the areas where bugs are most likely (security, concurrency, edge cases)
- Tell kiro to verify findings against actual code before reporting
Step 3: Run Kiro Review
kiro-cli chat \
--no-interactive \
-a \
"$(cat /tmp/kiro-review-prompt.md)" \
2>&1Important flags:
--no-interactive-- runs without expecting user input, returns output directly-a(trust all tools) -- kiro needs file read access to verify findings against source- Always capture stderr with
2>&1(kiro logs to stderr)
Run this in the background if the review is expected to take long:
- Use
run_in_backgroundon the Bash tool - The output will be available when the command completes
Optional flags:
--model <model>-- specify a particular model if needed--agent <agent>-- use a specific agent profile for the review
Step 4: Parse and Report Findings
Read the kiro output and extract findings. Look for:
- Priority markers (
P1,P2,P3) - File paths with line numbers
- Markdown tables of findings
Report findings to the user in a clear table:
| # | Priority | Description | File:Line |
|---|----------|-------------|-----------|
| 1 | P1 | ... | ... |Step 5: Fix Findings (if requested)
If the user wants to fix the findings:
- Read each cited file to verify the finding is real
- Apply fixes
- Run tests and typecheck
- Commit the fixes
Step 6: Iterate (if requested)
For thorough review, run multiple rounds:
- Fix findings from round N
- Update the prompt to list all previously fixed issues
- Run round N+1 with the updated prompt
- Repeat until findings converge to zero
Critical for iteration: Always add previously fixed issues to the prompt's exclusion list. Otherwise kiro will re-report the same issues every round, wasting time and API costs.
Example: Branch Review
# 1. Write review prompt
cat > /tmp/kiro-review-prompt.md << 'EOF'
Review the code changes on this branch compared to main.
The changes cover a new authentication module.
Focus on:
1. SECURITY: JWT validation, token expiry, session management
2. CORRECTNESS: Error handling, edge cases, missing null checks
3. TESTING: Are there tests for error paths?
Verify each finding against the actual code before reporting.
Output a markdown table with Priority, File:Line, Description, and Suggested Fix columns.
EOF
# 2. Run review
kiro-cli chat \
--no-interactive \
-a \
"$(cat /tmp/kiro-review-prompt.md)" \
2>&1Example: Iterative Deep Review
# Round 2 prompt (after fixing round 1 findings)
cat > /tmp/kiro-review-prompt.md << 'EOF'
Round 2 review. Prior fixes (do NOT re-report):
- SQL injection in user query (parameterized)
- Missing auth check on /api/admin (added middleware)
- XSS in profile page (escaped output)
Focus on genuinely NEW issues only.
Review the current branch against main.
Output a markdown table of findings.
EOF
kiro-cli chat \
--no-interactive \
-a \
"$(cat /tmp/kiro-review-prompt.md)" \
2>&1Safety Rules
| Rule | Reason |
Always use -a (trust all tools) | Kiro needs file read access to verify findings |
| Always list prior fixes in iterative reviews | Prevents wasting rounds on already-fixed issues |
| Always verify findings before fixing | Kiro can produce false positives |
| Run from the correct directory | Kiro reviews the repo it's invoked in |
| Never pass secrets in the prompt | The prompt may be logged |
Failure Modes
- Kiro not installed: Check
which kiro-clifirst, tell user to install - Not logged in: Run
kiro-cli whoami— user needs tokiro-cli login - Too large diff: Kiro may truncate; break into smaller review scopes
- Repeated findings: Always maintain the exclusion list between rounds
- False positives: Always read the cited code before acting on findings
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

