pstack-review

Review a branch, working diff, or named files for reachable defects and missing behavioral coverage.

IndexedMIT

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/machinelearning-nerd-pstack-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

Review a branch, working diff, or named files for reachable defects and missing behavioral coverage. Produces a read-only review with evidence.

Use cases: testing

Reviews

Write a review

No 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/pstack-review

What's inside

Skill name: pstack-review
Description: Review a branch, working diff, or named files for reachable defects and missing behavioral coverage. Produces a read-only review with evidence.
License: MIT
Instructions: 19 lines in SKILL.md · view on GitHub

Files (1)

SKILL.md

SKILL.md (first lines)

# Code review

Read ../pstack-harness/SKILL.md and ../interrogate/SKILL.md. Establish the exact
artifact and base before reviewing. For a working tree, include tracked and
untracked files relevant to the request. Identify changed contracts and callers.
Do not checkout, stage, fix, commit, or publish anything in a review request.

Use independent reviewers when available, one bounded review per configured
`interrogate reviewers` arm. Every arm receives the same artifact and scope, with
its own context and inherits the current chat's model. Label the panel independent
same-model review; do not claim model diversity.
Consolidate findings, confirm reachable behavior against source or a safe repro,
and reject speculation. A command failure or missing tool is not a clean verdict.

Lead with concrete defects in priority order, citing files and symbols, the
trigger, impact, and missing test. Note disagreements and remaining uncertainty.
If no supported finding remains, say so and identify material coverage limits.

From MachineLearning-Nerd/pstack-dual, MIT.

Signals

Stars: 0
Forks: 0
Open issues: 0
Last commit (this folder): Oct 11, 2026 (19 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License: MIT
Repository: github.com/MachineLearning-Nerd/pstack-dual
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: GitHub github-graphql

More from MachineLearning-Nerd

Cite this page

pstack-review skill. Agent Mart. https://agentmart.dev/skills/machinelearning-nerd-pstack-review (last updated 2026-10-24)