Run any Skill in Manus with one click

aivss-score

Stars3

Forks1

UpdatedJune 27, 2026 at 10:37

Run AIVSS v4 scorer on a report directory (ground_truth.json + governance_signals.json) and print the full inbound/internal/outbound breakdown, per-threat table, and a cached-vs-fresh delta if a prior score exists. Pass an architecture name as an argument, or omit for the most recent report. Read-only.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

BerdTan

BerdTan/threatassessor

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Software DevelopersComputer and Mathematical Occupations·SOC 15-1252

File Explorer

2 files

SKILL.md

readonly

name	aivss-score
description	Run AIVSS v4 scorer on a report directory (ground_truth.json + governance_signals.json) and print the full inbound/internal/outbound breakdown, per-threat table, and a cached-vs-fresh delta if a prior score exists. Pass an architecture name as an argument, or omit for the most recent report. Read-only.
allowed-tools	Bash(python3:) Bash(source:)

AIVSS Score Inspector

Recomputes AIVSS scores from disk and prints the full breakdown. No LLM calls. Takes ~1 second.

Run

# Most recent report
cd "$(git rev-parse --show-toplevel)" && source .venv/bin/activate && python3 .claude/skills/aivss-score/scripts/aivss-score.py

# Specific architecture
cd "$(git rev-parse --show-toplevel)" && source .venv/bin/activate && python3 .claude/skills/aivss-score/scripts/aivss-score.py 00_serviceentry_3

What it shows

Section	Contents
Summary	Inbound / Internal / Outbound composite + severity + coverage %; Overall composite + severity; industry profile
Flow Metric Breakdown	Per-flow: each AIVSS metric (CS, LL, MR, DS, GV, AA, DC, AD, EI…) with sub-scores and composite
Per-Threat Scores	Technique ID, name, composite, severity, top_metric, mitigation_multiplier — sorted by score descending
Cached vs Fresh	If governance_signals.json already has an `aivss` block, shows delta between cached and freshly computed
Coverage warnings	Flags any flow with <50% signal coverage — low coverage = sparse signals, not necessarily clean

Failure fixes

Error	Fix
`ground_truth.json not found`	Architecture has no analysis yet — run analysis first from dashboard or CLI
`AIVSSFlowScorer import fails`	Run `/quick-test` to verify harness_aivss module is importable
All composites show None	governance_signals.json missing or empty — run `/backfill-aivss <arch_name>`
Internal score = 0.0	Expected when no Expert Review has run — internal flow uses MoE/SM signals

Notes

Internal flow stays near zero until Expert Review (MoE) runs — it reads critic divergence and SM retrigger signals
Inbound / Outbound are fully deterministic from ground_truth.json alone
The script does not write governance_signals.json — use /backfill-aivss to persist scores

Related skills

/backfill-aivss — generate and persist governance_signals.json for past reports
/aivss-gate — show gate thresholds and last SIEM event without recomputing
/quick-test — broader integration sanity check

More from this repository

same repository

rerun-corpus

BerdTan/threatassessor

Audit and selectively re-run the deterministic analysis engine across all 26 corpus architectures. Default (no args) shows a staleness check — which reports are missing metadata, which arch types need engine fixes re-applied, and the current corpus score table. Pass --ai-only to re-run only AI/agentic architectures, --all to re-run everything, or a single arch name to re-run one. Use after engine changes (self_validation.py, ground_truth_generator.py, rapids_driven_controls.py) to confirm scores are consistent and no regressions landed.

2026-07-123

tatb-score

BerdTan/threatassessor

Run TATB (TA Test Benchmark) on a single architecture and print the four-rubric scorecard — Threat-Relevant, TTP-Accurate, Risk-Defensible, Plan-Actionable. Uses the same scoring logic as the dashboard TATB tab. Pass an architecture name as argument, or omit for the most recent report. Read-only. ~3 seconds (includes MITRE API fetch).

2026-07-123

tatb-corpus

BerdTan/threatassessor

Score all architectures in /report/ across the four TATB rubrics and print a visual corpus map — bar table, heatmap, and pipeline stage attribution. Shows which architectures are Excellent/Solid/Weak/Draft on each dimension and identifies which pipeline stages to fix for the largest corpus-wide gain. No UI needed. ~10-15 seconds (MITRE fetch batched once).

2026-07-113

run-er

BerdTan/threatassessor

Run Expert Review (MoE critics + ScrumMaster) on any architecture that has an existing analysis. Three modes — sequential (3 core critics), full_moe (5 critics + SM, generates Plan-Actionable data), or single-critic (re-run one critic by name). Streams live critic results with scores, gaps, and final confidence. ~60–120s for full_moe, ~30–60s for sequential.

2026-07-113

tatb-loop

BerdTan/threatassessor

TATB feedback loop — observe corpus or single-arch TATB scores, diagnose weak signals, propose targeted pipeline stage fixes, gate on human approval, apply changes, re-run TATB to verify improvement, and log the before/after delta to docs/DECISIONS.md. The agent does NOT autonomously commit code; every code change requires explicit human approval.

2026-07-043

quick-test

BerdTan/threatassessor

Runs a fast ~15 second integration sanity check — verifies dependencies, rate limiter, MITRE data load (≥835 techniques), OpenRouter API key, API connection, and one real embedding call. Use at session start or after installing dependencies to confirm everything is working before coding.

2026-07-023

name	aivss-score
description	Run AIVSS v4 scorer on a report directory (ground_truth.json + governance_signals.json) and print the full inbound/internal/outbound breakdown, per-threat table, and a cached-vs-fresh delta if a prior score exists. Pass an architecture name as an argument, or omit for the most recent report. Read-only.
allowed-tools	Bash(python3:) Bash(source:)

AIVSS Score Inspector

Recomputes AIVSS scores from disk and prints the full breakdown. No LLM calls. Takes ~1 second.

Run

# Most recent report
cd "$(git rev-parse --show-toplevel)" && source .venv/bin/activate && python3 .claude/skills/aivss-score/scripts/aivss-score.py

# Specific architecture
cd "$(git rev-parse --show-toplevel)" && source .venv/bin/activate && python3 .claude/skills/aivss-score/scripts/aivss-score.py 00_serviceentry_3

What it shows

Section	Contents
Summary	Inbound / Internal / Outbound composite + severity + coverage %; Overall composite + severity; industry profile
Flow Metric Breakdown	Per-flow: each AIVSS metric (CS, LL, MR, DS, GV, AA, DC, AD, EI…) with sub-scores and composite
Per-Threat Scores	Technique ID, name, composite, severity, top_metric, mitigation_multiplier — sorted by score descending
Cached vs Fresh	If governance_signals.json already has an `aivss` block, shows delta between cached and freshly computed
Coverage warnings	Flags any flow with <50% signal coverage — low coverage = sparse signals, not necessarily clean

Failure fixes

Error	Fix
`ground_truth.json not found`	Architecture has no analysis yet — run analysis first from dashboard or CLI
`AIVSSFlowScorer import fails`	Run `/quick-test` to verify harness_aivss module is importable
All composites show None	governance_signals.json missing or empty — run `/backfill-aivss <arch_name>`
Internal score = 0.0	Expected when no Expert Review has run — internal flow uses MoE/SM signals

Notes

Internal flow stays near zero until Expert Review (MoE) runs — it reads critic divergence and SM retrigger signals
Inbound / Outbound are fully deterministic from ground_truth.json alone
The script does not write governance_signals.json — use /backfill-aivss to persist scores

Related skills

/backfill-aivss — generate and persist governance_signals.json for past reports
/aivss-gate — show gate thresholds and last SIEM event without recomputing
/quick-test — broader integration sanity check