agentic-jujutsu

Quantum-resistant, self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordination

Install with Tessl CLI

npx tessl i github:ruvnet/claude-flow --skill agentic-jujutsu

What are skills?

1.26x

Review — 28%

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/skill

Learn more

Evaluation — 81%

↑ 1.26x

Agent success when using this skill

Validation — 9 / 11 Passed

Validation for skill structure

SKILL.md

Review

Evals

Evaluation results

100%

Automated Deployment Pipeline with Learning

Self-learning trajectory workflow

Criteria

Without context

With context

Correct import

100%

startTrajectory called

100%

addToTrajectory called

100%

finalizeTrajectory called

100%

Meaningful task descriptions

87%

100%

Varied honest scores

100%

Failure recorded with details

100%

getSuggestion usage

100%

getLearningStats usage

100%

Operations before finalizing

100%

output.json written

100%

Without context: $0.8359 · 2m 48s · 36 turns · 72 in / 9,893 out tokens

With context: $1.2079 · 4m 13s · 47 turns · 342 in / 15,031 out tokens

88%

Parallel Feature Branch Management

Multi-agent concurrent coordination

Criteria

Without context

With context

Concurrent execution

100%

Separate JjWrapper per agent

100%

Branch naming convention

queryTrajectories usage

100%

getPatterns usage

100%

Trajectory lifecycle per agent

100%

No lock-waiting pattern

100%

Descriptive trajectory names

70%

100%

results.json written

100%

Without context: $1.8001 · 6m 31s · 59 turns · 65 in / 21,928 out tokens

With context: $1.1455 · 3m · 43 turns · 206 in / 9,307 out tokens

56%

47%

Secure Artifact Integrity Verification System

Quantum security and operation auditing

Criteria

Without context

With context

Quantum fingerprint import

generateQuantumFingerprint usage

verifyQuantumFingerprint usage

Encryption enabled

100%

Base64 key generation

100%

getStats usage

100%

getOperations usage

100%

Trajectory lifecycle complete

100%

audit-report.json written

100%

Fingerprint as hex

Without context: $0.8302 · 2m 39s · 26 turns · 1,801 in / 8,792 out tokens

With context: $1.4451 · 4m 9s · 44 turns · 49 in / 13,434 out tokens

Evaluated: 3 days ago
Agent: Claude Code
Model: Unknown

Table of Contents

Automated Deployment Pipeline with Learning Parallel Feature Branch Management Secure Artifact Integrity Verification System

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.