n4m3z/StagedReview
skills/StagedReview/SKILL.md
Review your own staged changes via a code-review TUI before triggering a commit. USE WHEN about to commit, walking through your own staged diff, self-reviewing before approval, tuicr, revdiff, git diff cached.
$ install --global
skillsauthnpx skillsauth add n4m3z/forge-core StagedReviewInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 25, 2026, 5:33 AM105.1s1 file scanned
SKILL.md
- name:
- StagedReview
- description:
- Review your own staged changes via a code-review TUI before triggering a commit. USE WHEN about to commit, walking through your own staged diff, self-reviewing before approval, tuicr, revdiff, git diff cached.
- version:
- 0.1.0
- allowed-tools:
- Bash, Read
StagedReview
After staging changes with git add, walk the diff before committing. Annotate friction points, fix them, restage, re-review.
This skill is paired with the StageForReview rule: agents stage but do not commit; the user reviews the staged set and signals approval; then the commit runs.
Tools
| Tool | Strength | Worktree compatibility |
|---------------------|-----------------------------------------------------------|------------------------|
| tuicr | TUI with vim keybindings, GitHub-style annotation export | Limited (see caveat) |
| revdiff | TUI with --staged flag, in-place annotations | Limited (see caveat) |
| git diff --cached | Plain text, universal, no install | Full |
tuicr and revdiff are equivalent in role; pick by personal preference. git diff --cached is the always-available baseline.
Flow
- Stage:
git add <files>by name. Never-Aor.. - Open the staged diff with one of:
revdiff --staged # purpose-built for the staged set tuicr -w # working-tree mode; see `tuicr --help` for revset combos git diff --cached # plain text fallback - Annotate issues in the TUI; export to clipboard or stdout if the tool supports it.
- Fix issues by editing the affected files. Re-
git addthem. - Re-review until clean.
- Approve and commit. The agent commits only after the user signals approval.
Worktree caveat
In a git worktree (.worktrees/<branch> per GitWorktrees), the .git entry is a file pointing to the parent's .git/worktrees/<branch> directory. tuicr and revdiff can fail to walk this indirection cleanly.
Workarounds:
- Fall back to
git diff --cachedin the worktree. Universal and works. - Switch the main checkout to the branch under review:
git worktree remove .worktrees/<branch>thengit switch <branch>in the main checkout. Run the TUI from the main checkout, which has a real.gitdirectory. - Run with explicit git paths:
GIT_DIR=$(git rev-parse --git-dir) GIT_WORK_TREE=$(git rev-parse --show-toplevel) tuicr .... Hit-or-miss depending on the tool's internals.
Until upstream support lands, the main-checkout path is the cleanest for non-trivial diffs.
What to look for during self-review
- Unintended files staged (config dumps, build artifacts, secrets)
- Comments left as TODO or scratch notes
- Inconsistent naming across the diff
- Tests that don't actually assert content (
assert!(result.is_ok())without checking the value — see TestCorrectness) - Inline duplication of logic that already exists elsewhere (AvoidDuplication)
- Em dashes (NoEmDash)
Related Skills
n4m3z/Wtf
development
VerifiedTrustedCommunity
Reactive correction and root-cause fix. USE WHEN something went wrong, user is frustrated, demands a correction, says wtf, what the hell, why did you, that's wrong, this is broken, no not that, stop. Executes the immediate fix, then hunts the upstream artifact that caused it and creates a corrective change.
4SKILL.mdUpdated May 28, 2026
n4m3z/ResearchTopic
development
VerifiedTrustedCommunity
Decompose a research question into sub-queries, spawn parallel WebResearcher agents per angle, synthesize findings with citations and explicit confidence. USE WHEN the user asks to research, investigate, look online, look up, dig into, find sources, gather evidence, or survey what's known about a topic. Single-pass; for multi-round adversarial research use ResearchCouncil in forge-council.
4SKILL.mdUpdated May 27, 2026
n4m3z/WriteDocs
tools
VerifiedTrustedCommunity
Author project documentation that future humans (and AI sessions) actually read. Covers TLDRs for tools, READMEs, runbooks, journals. USE WHEN write documentation, create tldr, tool one-pager, document a cli, write readme, runbook, journal entry, capture knowledge about a tool, distill a session into reusable notes.
4SKILL.mdUpdated May 25, 2026
n4m3z/RefinePrompt
tools
VerifiedTrustedCommunity
Apply targeted transforms to prompt-shaped documents: align conventions, debrand vendor references, minimize filler, rescope tool grants, extract bulk reference, adapt for downstream repos. USE WHEN refining an adopted skill, polishing an authored skill/rule/agent, removing rot, or porting prompts across repos.
4SKILL.mdUpdated May 15, 2026