chemistrywow31/Granularity Calibration
.claude/skills/granularity-calibration/SKILL.md
Provide quantitative methods for evaluating whether agent decomposition granularity is appropriate
$ install --global
skillsauthnpx skillsauth add chemistrywow31/A-Team Granularity CalibrationInstall 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 15, 2026, 9:02 PM25.2s1 file scanned
SKILL.md
- name:
- Granularity Calibration
- description:
- Provide quantitative methods for evaluating whether agent decomposition granularity is appropriate
Granularity Calibration
Description
Provide quantitative methods for evaluating whether agent decomposition granularity is appropriate, preventing over-decomposition or under-decomposition.
Belongs To
This skill belongs exclusively to agents/discovery/role-designer.md
Calibration Methods
Responsibility Weight Assessment
Evaluate the "weight" of each agent's responsibilities to ensure weights are roughly balanced across team agents.
Assessment dimensions:
- Professional depth: How deep is the domain knowledge required? (shallow/medium/deep)
- Task complexity: How many steps does each task involve? (1-3 steps/4-7 steps/8+ steps)
- Decision density: How many judgment-based decisions are made during work? (few/medium/many)
Balance Determination
Ideal state: The difference between the "heaviest" and "lightest" agents in the team should not exceed one level.
If the gap is too large:
- Overweight agents → Consider splitting into 2-3 more specialized roles
- Underweight agents → Consider merging with similar roles, or expanding their responsibility scope
Practical Determination Method
Answer the following questions. If most answers are "yes", granularity is appropriate:
- Can each agent's core responsibility be clearly stated in one sentence?
- After removing any agent, is there clearly identifiable work that would have no one responsible?
- Are agent interactions primarily "deliverable handoffs" rather than "ongoing discussions"?
- Does each agent have distinct quality evaluation criteria?
- Can the coordinator assign tasks without needing to understand technical details?
Related Skills
chemistrywow31/Team Topology Analysis
data-ai
VerifiedTrustedCommunity
Evaluate whether a proposed agent graph supports safe handoffs and useful parallel work
43SKILL.mdUpdated Apr 15, 2026
chemistrywow31/Structured Interview
testing
VerifiedTrustedCommunity
Extract precise team requirements through staged, single-direction questioning
43SKILL.mdUpdated Apr 15, 2026
chemistrywow31/Skill Discovery
content-media
VerifiedTrustedCommunity
Search external sources for reusable skills before designing a new one
43SKILL.mdUpdated Apr 15, 2026
chemistrywow31/Skill Creator
data-ai
VerifiedTrustedCommunity
Create or improve a skill by using the system skill when available and the legacy local bundle as fallback
43SKILL.mdUpdated Apr 15, 2026