agentic-jujutsu
Quantum-resistant, self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordination
49
28%
Does it follow best practices?
Impact
84%
2.62xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/agentic-jujutsu/SKILL.mdQuality
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 reads like marketing copy rather than a functional skill description. It relies heavily on buzzwords and jargon without explaining concrete capabilities or providing trigger terms users would naturally use. The lack of actionable language and explicit usage guidance makes it nearly impossible for Claude to correctly select this skill.
Suggestions
Replace buzzwords with concrete actions (e.g., 'Track code changes, manage branches, coordinate commits across multiple AI agents').
Add a 'Use when...' clause with natural trigger terms like 'version control', 'git', 'commit history', 'branch management', or 'code collaboration'.
Remove or explain jargon like 'ReasoningBank intelligence' and 'quantum-resistant' - either make them concrete features 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 | Neither 'what does this do' nor 'when should Claude use it' is clearly answered. There is no 'Use when...' clause, and the capabilities are described only in vague, marketing-style language. | 1 / 3 |
Trigger Term Quality | Contains technical jargon ('quantum-resistant', 'ReasoningBank intelligence', 'multi-agent coordination') that users would never naturally say. Missing common version control terms like 'git', 'commit', 'branch', 'merge', or 'repository'. | 1 / 3 |
Distinctiveness Conflict Risk | The phrase 'version control' provides some domain specificity, and 'AI agents' narrows the scope somewhat. However, the buzzword-heavy language could still overlap with other AI/automation 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 code examples but suffers from severe verbosity with marketing language, promotional metrics, and emoji decorations that waste tokens. The content is actionable but poorly organized - a 500+ line monolithic file that could be condensed to ~100 lines with proper progressive disclosure to separate files.
Suggestions
Remove all marketing language, performance comparisons, and promotional metrics (e.g., '23x faster', '87% success rate') - focus only on how to use the tool
Condense to a Quick Start section (~50 lines) with essential operations, moving API reference, advanced use cases, and troubleshooting to separate linked files
Remove emoji decorations and status badges - they add no instructional value
Add explicit validation checkpoints in multi-step workflows (e.g., 'Verify trajectory started before calling addToTrajectory()')
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at 500+ lines with extensive marketing language ('23x faster', 'quantum-resistant'), emoji decorations, and repetitive examples. Much content explains concepts Claude already knows (what version control is, how async/await works) and includes promotional metrics that don't aid task execution. | 1 / 3 |
Actionability | Provides fully executable JavaScript code examples throughout, with copy-paste ready snippets for all major operations. Code is complete with imports, proper async/await usage, and realistic usage patterns. | 3 / 3 |
Workflow Clarity | Multi-step processes like trajectory management are shown but lack explicit validation checkpoints. The 'Best Practices' and 'Troubleshooting' sections help but workflows don't include feedback loops for error recovery or explicit 'validate before proceeding' steps. | 2 / 3 |
Progressive Disclosure | References external documentation (README.md, VALIDATION_FIXES.md, AGENTDB_GUIDE.md) but the main file is monolithic with extensive inline content that could be split. API reference tables, advanced use cases, and troubleshooting could be separate files with clear navigation. | 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 (663 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 | |
- Repository
- ruvnet/ruvector
- Commit
462536e
- 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.