Quality control

Skill Liberty91LTD/cti-skills/skills/quality-control

Peer review checklist and quality standards for intelligence products. Loaded by the quality-reviewer agent.From its SKILL.md

Install

npx -y skills add Liberty91LTD/cti-skills --skill quality-control

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

8 stars8 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

3.0 KB, 663 tokens by cl100k_base, as published. Nobody here has run it

Quality Control Standards

Review Process

All products must be reviewed before moving to "published" status
Reviews are performed by the quality-reviewer agent
Products with CRITICAL issues are returned for revision
Products with 3+ MAJOR issues are returned for revision
MINOR issues are noted but don't block publication

Peer Review Checklist

A. Structural Integrity (Weight: 15%)

Correct product template used
Complete frontmatter (all required fields)
TLP marking present and correctly applied
Logical section ordering
Appropriate length for product type

B. Analytical Rigor (Weight: 30%)

Conclusions supported by evidence
Key assumptions explicitly identified
Alternative hypotheses considered (where applicable)
Structured analytic techniques applied appropriately
No logical leaps or unsupported assertions
Temporal scope specified for all predictions
Intelligence gaps acknowledged

C. Sourcing (Weight: 20%)

All sources assessed with Admiralty Scale
Source ratings justified and reasonable
Source diversity (not single-source unless noted)
Derivative vs independent sources distinguished
No unattributed claims

D. Mandated Language (Weight: 20%)

Confidence levels on all assessments (with rationale)
Likelihood language on all predictions (with percentage ranges)
No hedge-stacking
No vague probabilistic language without probability band
Confidence and likelihood not conflated
Facts clearly distinguished from assessments

E. Technical Accuracy (Weight: 10%)

MITRE ATT&CK mappings correct
IOCs properly formatted and validated
Technical claims verifiable
No contradictions with known intelligence

F. Writing Quality (Weight: 5%)

Scoring

Calculate weighted score (0-10):

Each section: 0 (none met) to 10 (all met)
Weighted by percentages above
Final score = weighted average

Score	Verdict
8-10	Approved — publish
6-7	Approved with minor revisions — can publish after fixes
4-5	Revision required — significant issues
0-3	Rejected — fundamental problems

Issue Severity

CRITICAL: Factual error in key finding, missing TLP on sensitive content, unsupported primary conclusion, potential harm if published as-is
MAJOR: Missing confidence level on assessment, vague likelihood language on prediction, missing source assessment on key evidence, logical flaw in reasoning, missing key section
MINOR: Grammar/formatting, style inconsistency, minor Admiralty rating disagreement, non-essential section could be improved

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 326,679. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.