calibrate
Context-adaptive delegation calibration through scenario-based interview. Detects execution context to select entry mode (Solo/TeamAugment/TeamRestructure) and produces a DelegationContract. Type: (DelegationAmbiguous, AI, CALIBRATE, TaskScope) → CalibratedDelegation. Alias: Epitrope(ἐπιτροπή).
Install with Tessl CLI
npx tessl i github:jongwony/epistemic-protocols --skill calibrate48
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Evaluation results
88%
50%API Service Onboarding — Delegation Setup
Solo calibration domain priority and question format
AskUserQuestion for Phase 0
0%
100%
AskUserQuestion for Phase 2
100%
100%
External domain first
0%
100%
FileModification before Strategy
100%
100%
Binary/ternary options
0%
100%
Concrete task-specific scenarios
70%
100%
AskUserQuestion for Phase 4
50%
100%
Exploration default in contract
0%
50%
Other uncalibrated defaults
0%
22%
Question count within Solo cap
100%
100%
Without context: $0.3077 · 1m 56s · 13 turns · 15 in / 5,646 out tokens
With context: $0.3581 · 1m 51s · 13 turns · 1,134 in / 4,925 out tokens
100%
62%Team Delegation Setup for Microservices Migration
TeamAugment WHO phase and scope guard
WHO discussion before domains
100%
100%
AskUserQuestion for WHO
0%
100%
Epistemic roles only
100%
100%
Implementation agent rejection
70%
100%
Total roles within cap
100%
100%
TeamCoordination scenario
0%
100%
ScopeCreep scenario
0%
100%
External domain priority
0%
100%
Authority replacement statement
0%
100%
AskUserQuestion for Phase 4
0%
100%
Without context: $0.3951 · 2m 34s · 14 turns · 18 in / 8,736 out tokens
With context: $0.5929 · 2m 51s · 21 turns · 760 in / 7,652 out tokens
92%
27%Delegation Decision Log for Evolving Project
Skip detection and recalibration triggers
Situation A triggers calibration
100%
100%
Situation B skip — single domain
100%
100%
Situation B uses existing contract
100%
100%
Situation C triggers recalibration
100%
100%
Situation D no recalibration
0%
100%
Situation E triggers recalibration
100%
100%
Exploration defaults to autonomous
0%
100%
Other uncalibrated domains default to ask-before
20%
20%
Without context: $0.1709 · 1m 11s · 11 turns · 15 in / 3,298 out tokens
With context: $0.5516 · 2m 21s · 20 turns · 970 in / 6,669 out tokens
- Evaluated
- Agent
- Claude Code
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.