bigeasyfreeman/brief-clarity-judge
skills/brief-clarity-judge/SKILL.md
Resolve ambiguous triage outcomes in the middle confidence band.
tools
Updated Apr 22, 2026
$ install --global
skillsauthnpx skillsauth add bigeasyfreeman/adlc brief-clarity-judgeInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 22, 2026, 1:17 PM135.9s1 file scanned
SKILL.md
- name:
- brief-clarity-judge
- description:
- Resolve ambiguous triage outcomes in the middle confidence band.
- contract_version:
- 1.0.0
- side_effect_profile:
- read_only
- mode:
- judgement
- consumes_manifest:
- true
- model_class:
- fast_judge
- max_tokens_per_call:
- 700
- expected_calls_per_run:
- 1
Brief Clarity Judge
Use this judge only when 0.6 <= task_classification_confidence < 0.8.
Purpose
The confidence band is advisory. This judge decides whether the brief is clear enough to continue or should escalate for human clarification.
Inputs
{
"request": "string",
"signal_features": {
"language_hints": ["py"],
"intent_keywords": ["fix", "bug"],
"linked_refs": ["PR-123"],
"reproducer_present": true
},
"task_classification": "bugfix",
"task_classification_confidence": 0.72,
"classification_evidence": ["..."],
"contamination": {},
"missing": ["..."]
}
Output
{
"verdict": "proceed | escalate",
"rationale": "string"
}
Rules
- Judge clarity, not implementation detail.
- Prefer
proceedwhen the task has a concrete objective, bounded scope, and a plausible verifier path. - Return
escalatewhen the task is internally contradictory, underspecified, or missing the information needed to classify safely. - Do not rewrite or invent the evidence inventory. Consume the deterministic feature summary as given.
Related Skills
bigeasyfreeman/paved-road-registry
development
VerifiedTrustedCommunity
Discovers and records repo-local approved build paths so agents reuse proven patterns instead of inventing parallel architectures.
1SKILL.mdUpdated Jun 8, 2026
bigeasyfreeman/learning-refresh
development
VerifiedTrustedCommunity
Scoped maintenance for docs/solutions entries when stale signals, refactors, or explicit user scope require refresh.
1SKILL.mdUpdated Jun 8, 2026
bigeasyfreeman/learning-capture
documentation
VerifiedTrustedCommunity
Conditionally captures verified reusable ADLC learnings into docs/solutions after successful closeout.
1SKILL.mdUpdated Jun 8, 2026
bigeasyfreeman/graph-research
development
VerifiedTrustedCommunity
Uses Graphify as ADLC's graph-backed research layer and Beads as an optional dependency-aware task memory layer. Produces evidence for compatibility, reuse, accuracy, dark-code hotspots, and long-horizon handoff.
1SKILL.mdUpdated Jun 8, 2026