verify
This skill should be used when the user asks to "verify protocols", "check consistency before commit", "validate definitions", "run pre-commit checks", "verify soundness", or wants to ensure epistemic protocol quality. Invoke explicitly with /verify for pre-commit validation.
Install with Tessl CLI
npx tessl i github:jongwony/epistemic-protocols --skill verify69
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
100%
68%Pre-Commit Protocol Verification
Static check execution
Script execution evidence
0%
100%
Critical section present
0%
100%
Concern/Note sections present
80%
100%
fail→Critical mapping
0%
100%
warn→Concern/Note mapping
40%
100%
Plugin.json issue identified
20%
100%
Unicode notation issue identified
0%
100%
Directive verb issue identified
80%
100%
File locations included
100%
100%
No files modified
100%
100%
Without context: $0.2950 · 1m 39s · 12 turns · 16 in / 5,766 out tokens
With context: $1.8838 · 2m 54s · 10 turns · 12 in / 10,407 out tokens
96%
49%Expert Protocol Review
Parallel expert perspectives
Three perspectives spawned
20%
100%
Type Design perspective
80%
100%
Specification Clarity perspective
70%
100%
Claude Code Ecosystem perspective
90%
100%
Parallel execution
0%
100%
False positive filtering applied
46%
100%
Synthesis convergence
20%
80%
Synthesis divergence
0%
60%
Severity categorization
80%
100%
Collect before synthesize
60%
100%
Without context: $0.4223 · 2m 39s · 14 turns · 19 in / 8,021 out tokens
With context: $1.5751 · 7m 45s · 30 turns · 5,696 in / 20,708 out tokens
95%
49%Protocol Suite Pre-Commit Review
Verification presentation format
Verification Results header
50%
100%
Critical section with count
50%
100%
Concerns section
20%
100%
Notes section
30%
100%
Filtered section
0%
100%
All four options listed
50%
75%
Commit annotation format
13%
100%
Issue locations
100%
100%
Advisory framing
80%
100%
Severity populated
100%
100%
Without context: $0.3860 · 1m 59s · 15 turns · 19 in / 6,508 out tokens
With context: $1.6153 · 3m 41s · 8 turns · 10 in / 12,408 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.