Programming · Review & audit
spudstack
/spudstack
Use when independently reviewing plans, specs, diffs or builds.
For whom
- Author
- dax8it ↗
- Repository
- spudstack ↗
- Licence
- MIT
- Last repository change
- 06.11.2026
Assessment and security
86/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability21 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content25 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
Deprecation
No signals detected. Repository changed on 06.11.2026, without references to retired models or APIs.
Licence
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Use when independently reviewing plans, specs, diffs or builds.
Original author description
Use when independently reviewing plans, specs, diffs or builds.
How it works
- Setup
- Review
- Output
- Boundaries
Original SKILL.md headings · 26 lines, 353 words
SKILL.md preview
---
name: spudstack
description: Use when independently reviewing plans, specs, diffs or builds.
version: 1.0.0
license: MIT
metadata:
hermes:
tags: [review, evidence, quality, rigor]
---
# SpudStack
Review plans, specifications, changes and builds independently. Do not implement the work under review or sign off your own work. Follow the user's current instructions, project policies and hard gates; do not override a higher-priority rule.
## Setup
Use known context rather than asking again. When necessary, establish the artifact and scope, acceptance criteria, who implements and independently verifies, approval boundaries, evidence available, and the owner's review-round and escalation rules. Do not invent named reviewers or imply an unavailable reviewer participated.
## Review
1. Inspect the artifact and requirements. Identify assumptions and material risks, including impact on existing callers and side effects.
2. For each mandatory requirement, seek reproducible evidence: the relevant command or observation, its actual output and the expected result. Distinguish a proposed check from a completed one. Do not claim a run you did not perform.
3. Return **PASS** only when all mandatory criteria and required approvals are satisfied; otherwise return **FAIL**. A missing prerequisite or missing evidence means acceptance is not established, not necessarily that the implementation is defective. Do not use PASS WITH NOTES.
4. Report blocking findings with location, impact, evidence and the smallest practical correction. List nonblocking findings separately with an owner and due review when known; unresolved findings become blocking at their specified due review.
5. Follow the owner's specified review-round limit. Where a one-round rule applies, stop after a FAIL and request authorization before another review. Do not invent such a restriction for a different owner.
6. Separate your review from required independent reviewers and human approval. Your verdict cannot substitute for a named reviewer or grant authority to deploy, send, spend, delete or access secrets.
## Output
Lead with PASS or FAIL and the reviewed scope. Then show blocking findings, nonblocking findings, evidence actually checked, missing evidence and the next authorized action. Be brief without hiding material uncertainty.
## Boundaries
Do not create jobs, install or update skills, change files, send messages, or overwrite a persona or memory merely because this skill was loaded. Those actions require separate authorization. pstack is optional and separately licensed; see the repository README for attribution.
Versions
The database has no other skills named spudstack.
Database snapshot: 13.11.2026 · package version 1b42639baa3a (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 90reviewing-code-diffs
Use when reviewing code diffs is required during implementation work, especially when the result must be traceable, independently reviewable, and safe to hand to another agent. - 90review
Selvage AST-based smart context code review. Use when reviewing code changes, checking diffs, or analyzing code quality. - 100code-review
Use when reviewing code changes before committing or merging — staged diffs, branch diffs, or PR readiness checks. Triggers: 'review my code', 'check these changes', 'review this branch', 'give feedback on my diff', 'is this PR ready?'. Not for implementing features, running… - 100create-issues
Use when turning approved plans, specs, PRDs, or Epics into trackable GitHub Issues. - 100create-project
Create a Diffy project with the diffy CLI from user-provided project details. Use when the user asks to create a Diffy project, set up a new project in Diffy, or turn a base URL, pages, and breakpoints into a new Diffy project. Requires the user to provide base_url and returns… - 90reviewing-impl-plans
Use when reviewing implementation plans before execution. Triggers: 'is this plan solid', 'review the plan', 'check before I start building', 'anything missing from this plan', 'will this plan work', 'audit the implementation plan'. NOT for: reviewing design documents (use…