interactive-diff-review
Guarded patch inspection, regression analysis, memory safety review, and pre-commit diff auditing.
Skill by M4F-S
Chalk Labs
Need help deploying interactive-diff-review?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
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/m4f-s-interactive-diff-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/interactive-diff-review
What's inside
- Skill name
interactive-diff-review- Description
- Guarded patch inspection, regression analysis, memory safety review, and pre-commit diff auditing.
- License
- Apache-2.0
- Instructions
- 33 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Interactive Diff Review & Pre-Commit Audit Protocol
## Objective
Thoroughly inspect all staged or unstaged code mutations before committing. Guarantee zero regressions, deterministic resource management, and strict conformance to repository standards.
## Execution Steps
1. **Diff Extraction**:
- Run `git_status` to identify modified, added, or untracked files.
- Run `git_diff` with `staged=false` for working copy changes or `staged=true` for staged changes.
- For focused inspections, provide the exact `path` parameter to `git_diff`.
2. **Multi-Vector Audit**:
- **Functional Correctness**: Verify the diff directly addresses the user request without scope creep or unintended side effects.
- **Memory & Resource Safety**:
- Check every `malloc`/`calloc` has a non-NULL check and corresponding deterministic `free`.
- Check file descriptors, SQLite statements, sockets, and child processes are reaped on all exit paths.
- Verify buffer bounds and ensure no unbounded string functions (`strcpy`, `sprintf`) are introduced.
- **Error Propagation**: Ensure error return codes are checked, not silently swallowed.
- **Style & Documentation**: Preserve existing comments, formatting, and public interface signatures.
3. **Compilation & Test Gating**:
- Run the project test suite (`bash` with `make test` or equivalent) to verify 100% clean execution.
- If ASan/UBSan targets are available, run sanitizer builds to verify 0 memory leaks and 0 undefined behaviors.
4. **Structured Review Report**:
- Present a clear summary categorized by:
- **Files Changed**: List of files and lines added/deleted.
- **Safety Assessment**: Clean / Warnings / Blockers.
- **Verification Evidence**: Test commands executed and exit codes.
- **Recommended Action**: Proceed to commit or patch fixes required.From M4F-S/Almaz, Apache-2.0.
More from M4F-S/Almaz
- 0.558score
safe-refactor-guard
M4F-S
Atomic multi-file refactoring, AST call-graph verification, preflight compilation check, and rollback guard.
SkillAFreshness: AClaude Code +9 - 0.558score
vps-deploy
M4F-S
Protocols for deploying updates to Belya and Almaz daemons on remote VPS.
SkillAFreshness: AClaude Code +9 - 0.558score
benchmark-profiler
M4F-S
Rigorous latency, resident memory (RSS), and performance profiling for systems software.
SkillAFreshness: AClaude Code +9 - 0.558score
web-research
M4F-S
Autonomous documentation retrieval, API endpoint exploration, and web research using native REST tools.
SkillAFreshness: AClaude Code +9 - 0.558score
codebase-onboarding
M4F-S
Rapid autonomous repository reconnaissance, architecture mapping, and codebase onboarding.
SkillAFreshness: AClaude Code +9 - 0.513score
git-workflow
M4F-S
Strict git repository workflow, atomic commits, rollback guards, and semantic version tagging.
SkillBFreshness: BClaude Code +9 - 0.513score
arena-evolution
M4F-S
Autonomous 4-phase audit, mutation, benchmark, and reflection protocol for self-evolution.
SkillBFreshness: BClaude Code +9 - 0.513score
c99-safety
M4F-S
Zero-tolerance C99 memory safety, bounds checking, and deterministic resource deallocation.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 13, 2026 (18 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/M4F-S/Almaz
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
More from M4F-S
- 0.558score
safe-refactor-guard
M4F-S
Atomic multi-file refactoring, AST call-graph verification, preflight compilation check, and rollback guard.
SkillAFreshness: AClaude Code +9 - 0.558score
vps-deploy
M4F-S
Protocols for deploying updates to Belya and Almaz daemons on remote VPS.
SkillAFreshness: AClaude Code +9 - 0.558score
benchmark-profiler
M4F-S
Rigorous latency, resident memory (RSS), and performance profiling for systems software.
SkillAFreshness: AClaude Code +9 - 0.558score
web-research
M4F-S
Autonomous documentation retrieval, API endpoint exploration, and web research using native REST tools.
SkillAFreshness: AClaude Code +9 - 0.558score
codebase-onboarding
M4F-S
Rapid autonomous repository reconnaissance, architecture mapping, and codebase onboarding.
SkillAFreshness: AClaude Code +9 - 0.513score
git-workflow
M4F-S
Strict git repository workflow, atomic commits, rollback guards, and semantic version tagging.
SkillBFreshness: BClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get interactive-diff-review running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
interactive-diff-review skill. Agent Mart. https://agentmart.dev/skills/m4f-s-interactive-diff-review (last updated 2026-10-24)