Liberty91LTD/cti-skills / skills/quality-of-information-check
quality-of-information-check
VerifiedUse when evidence needs grading before anyone reasons from it: "how reliable is this?", "grade this source", "check this report", "is this corroborated?", or a URL, pasted report or Liberty91 event handed over ahead of an ACH or assessment. Resolves each document to its originating source, splits it into claims and grades each on access level and claim support with a rationale and hard caps; not an Admiralty rating. Returns a graded claim table, gaps, a deception screen and JSON. Run first by /ach, /threat-assessment and /writing-assessments.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 15.9 KB |
| references/aliases.example.yml | config | 1.7 KB |
| references/deception-screen.md | markdown | 5.6 KB |
| references/doctrine.md | markdown | 6.6 KB |
| references/evidence-item-schema.md | markdown | 10.2 KB |
| references/grading-rubric.md | markdown | 12.2 KB |
| references/worked-examples.md | markdown | 11.3 KB |
| scripts/validate_evidence.py | script | 25.2 KB |
references/aliases.example.yml
View on GitHub# Alias file for cross-vendor name matching.
#
# Copy this file to aliases.yml in the same directory and maintain it yourself.
# aliases.yml is gitignored. /quality-of-information-check loads it when present
# and labels every match made with it as alias_source: user.
#
# The pack ships the mechanism only, not the mappings. Which vendor cluster equals
# which is an analytical judgement that changes over time, and it is yours to make.
# With a LIBERTY91_API_KEY the Threat Library is used instead (alias_source: liberty91).
# With neither, names are not matched across vendors and corroboration for
# name-based claims stays at 1, unchecked.
#
# Hashes, CVE identifiers, IP addresses and domains match exactly and do not
# need entries here.
#
# Fields:
# canonical the name you use
# aliases other vendors' names for what you judge to be the same thing
# note optional: basis for the mapping, date, caveats
#
# An alias may appear under one canonical name only. Where two vendor clusters
# overlap but are not the same, do not alias them: list them separately and say
# so in the note.
#
# The entries below are invented, to show the format.
actor:
- canonical: Crimson Heron
aliases:
- TEMP.Embers
- Group 0417
- Storm-9901
note: >
Storm-9901 merged on the basis of the vendor's own statement of 2026-03-02.
Group 0417 is a partial overlap in one vendor's reporting; treated as the
same for corroboration, reviewed quarterly.
malware:
- canonical: Embers
aliases:
- EMBERLOADER
- Backdoor.Cinder
note: Same family by code comparison published by two vendors.
tool:
- canonical: QuietDump
aliases:
- credtool-q
note: Custom credential dumper.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |