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/agentic-flow --skill agentic-jujutsu41
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
Discovery
7%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is heavily padded with marketing buzzwords and technical jargon while failing to communicate any concrete capabilities or usage triggers. It tells Claude nothing about what actions the skill performs or when to select it. The description prioritizes sounding impressive over being functional.
Suggestions
Replace buzzwords with concrete actions: specify what version control operations this skill performs (e.g., 'Track file changes, create branches, merge code, resolve conflicts').
Add an explicit 'Use when...' clause with natural trigger terms users would say (e.g., 'Use when the user mentions git, commits, branches, version history, or tracking changes').
Remove or clarify jargon like 'ReasoningBank intelligence' and 'quantum-resistant' - either explain what these mean in practical terms or remove them entirely.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses abstract buzzwords ('quantum-resistant', 'self-learning', 'ReasoningBank intelligence') without describing any concrete actions. No specific operations like 'commit', 'merge', 'branch', or 'track changes' are mentioned. | 1 / 3 |
Completeness | Missing both clear 'what' (no concrete actions described) and 'when' (no explicit trigger guidance or 'Use when...' clause). The description is entirely abstract with no actionable information. | 1 / 3 |
Trigger Term Quality | Contains technical jargon and marketing terms that users would never naturally say. Terms like 'quantum-resistant', 'ReasoningBank intelligence', and 'multi-agent coordination' are not natural user queries for version control tasks. | 1 / 3 |
Distinctiveness Conflict Risk | While the buzzwords are unique, 'version control' is a recognizable domain that provides some distinctiveness. However, the vague nature could still cause confusion with other version control or AI coordination skills. | 2 / 3 |
Total | 5 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides comprehensive, executable documentation for the agentic-jujutsu library with excellent code examples and API coverage. However, it severely violates token efficiency principles with marketing language, redundant examples, and content that should be in separate reference files. The skill reads more like product documentation than a concise skill file for Claude.
Suggestions
Reduce content to ~100 lines by moving advanced use cases, API reference tables, and troubleshooting to separate files (e.g., ADVANCED.md, API.md, TROUBLESHOOTING.md)
Remove marketing language and performance claims ('23x faster', '87% success rate') - focus only on how to use the tool
Add explicit validation checkpoints to workflows, e.g., 'After finalizeTrajectory(), verify with getLearningStats() that the trajectory was recorded'
Consolidate the 4 similar 'Example' sections into a single Quick Start with one complete workflow
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at 500+ lines with extensive marketing language ('23x faster', '87% success rate'), redundant examples showing the same concepts multiple times, and explanations Claude doesn't need (what trajectories are, how patterns work). The 'When to Use' checklist and performance comparison tables add little actionable value. | 1 / 3 |
Actionability | Provides fully executable JavaScript code examples throughout, with copy-paste ready snippets for all major features including trajectory management, pattern discovery, multi-agent coordination, and error handling. API reference tables are complete with method signatures and return types. | 3 / 3 |
Workflow Clarity | Multi-step processes like trajectory management (start → add → finalize) are shown but lack explicit validation checkpoints. The 'Best Practices' section shows good/bad patterns but doesn't integrate validation steps into the workflows. Error handling examples exist but aren't woven into the main workflow sequences. | 2 / 3 |
Progressive Disclosure | References external documentation (VALIDATION_FIXES_v2.3.1.md, AGENTDB_GUIDE.md) but the main file is monolithic with extensive inline content that could be split. The 'Related Documentation' section is good, but 500+ lines of examples and use cases should be in separate files with the SKILL.md providing a concise overview. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (649 lines); consider splitting into references/ and linking | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Reviewed
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.