agentic-jujutsu
Quantum-resistant, self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordination
41
17%
Does it follow best practices?
Impact
81%
1.26xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/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 is packed with buzzwords ('quantum-resistant', 'self-learning', 'ReasoningBank intelligence') that provide no actionable information about what the skill actually does or when Claude should select it. It fails on nearly every dimension due to lack of concrete actions, natural trigger terms, and explicit usage guidance.
Suggestions
Replace buzzwords with concrete actions the skill performs (e.g., 'Commits changes, manages branches, resolves merge conflicts for AI agent workflows').
Add an explicit 'Use when...' clause with natural trigger terms users would actually say (e.g., 'Use when the user asks about version control, git operations, committing code, or managing branches').
Remove or minimize marketing language like 'quantum-resistant' and 'self-learning' unless they describe genuinely distinct, user-facing capabilities that differentiate this from standard version control skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses abstract buzzwords like 'quantum-resistant', 'self-learning', and 'ReasoningBank intelligence' without describing any concrete actions. There are no specific operations listed (e.g., commit, branch, merge). | 1 / 3 |
Completeness | The description vaguely hints at 'what' (version control) but provides no 'when' clause or explicit trigger guidance. There is no 'Use when...' or equivalent, and the 'what' itself is obscured by marketing-style language. | 1 / 3 |
Trigger Term Quality | The keywords are highly technical jargon ('quantum-resistant', 'ReasoningBank intelligence', 'multi-agent coordination') that no user would naturally say when needing version control help. 'Version control' is the only somewhat natural term, but it's buried among buzzwords. | 1 / 3 |
Distinctiveness Conflict Risk | The heavy use of niche buzzwords like 'quantum-resistant' and 'ReasoningBank intelligence' ironically makes it unlikely to conflict with other skills, but the core concept ('version control') is generic enough that it could overlap with standard git/VCS skills. | 2 / 3 |
Total | 5 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads more like a comprehensive product README/marketing document than a focused skill for Claude. It is extremely verbose, repeating the same trajectory pattern across 8+ code blocks, includes marketing claims and performance benchmarks that don't help Claude execute tasks, and packs everything into a single monolithic file. While the code examples are reasonably concrete, the sheer volume of redundant content and lack of progressive disclosure significantly reduce its effectiveness as a skill.
Suggestions
Reduce content by 60-70%: consolidate the repeated trajectory pattern into one canonical example, remove marketing language (performance tables, '23x faster'), version history, and status badges.
Split into multiple files: keep SKILL.md as a concise overview (~50-80 lines) with quick start and API summary, then move advanced use cases to ADVANCED.md, API reference to API.md, and troubleshooting to TROUBLESHOOTING.md.
Remove redundant code examples: Use Cases 1-4 and Examples 1-2 all demonstrate the same startTrajectory/addToTrajectory/finalizeTrajectory pattern—keep one comprehensive example and reference it.
Add explicit validation checkpoints in workflows, e.g., verify trajectory exists before addToTrajectory(), and check getSuggestion response structure before accessing properties.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~400+ lines. Includes extensive marketing language ('23x faster than Git', 'quantum-resistant'), redundant examples showing the same trajectory pattern 8+ times, performance comparison tables, version history, and status badges—none of which help Claude execute tasks. The same startTrajectory/addToTrajectory/finalizeTrajectory pattern is repeated in nearly every code block. | 1 / 3 |
Actionability | Code examples are concrete and appear executable with specific API calls and return types. However, many examples rely on undefined helper functions (executeOperation, verifyDeployment, executeTask, agent.analyze) making them incomplete, and some use cases are more illustrative than copy-paste ready. | 2 / 3 |
Workflow Clarity | The trajectory workflow (start → operate → add → finalize) is clear and repeated many times, and error handling patterns are shown. However, there are no explicit validation checkpoints between steps (e.g., verifying trajectory was started before adding operations), and the troubleshooting section is reactive rather than integrated into workflows as checkpoints. | 2 / 3 |
Progressive Disclosure | The skill is a monolithic wall of text with no bundle files to support it. References to external docs (VALIDATION_FIXES_v2.3.1.md, AGENTDB_GUIDE.md) are listed but not provided. The API reference tables, 4 advanced use cases, 4 best practices sections, troubleshooting, and multiple full examples should be split into separate files rather than inlined in a single massive document. | 1 / 3 |
Total | 6 / 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 (646 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/claude-flow
- Commit
e6dc21f
- 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.