agentic-jujutsu

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

1.26x

Quality

17%

Does it follow best practices?

Impact

81%

1.26x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agents/skills/agentic-jujutsu/SKILL.md

Quality

Discovery

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 dominated by marketing buzzwords and abstract jargon without describing any concrete actions or providing trigger guidance. It fails to tell Claude what specific tasks this skill performs or when to select it. A user asking for help with version control, commits, or branching would have no clear signal to match against this description.

Suggestions

Replace buzzwords with concrete actions the skill performs (e.g., 'Manages branches, commits changes, resolves merge conflicts, tracks file history').

Add an explicit 'Use when...' clause with natural trigger terms users would actually say (e.g., 'Use when the user asks about git, commits, branching, merging, or version history').

Remove or demote marketing language like 'quantum-resistant' and 'self-learning' — focus on what the skill actually does in practical terms.

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, diff).	1 / 3
Completeness	The description vaguely gestures at 'what' (version control) but provides no explicit 'when' clause or trigger guidance. Both the what and when are very weak — there's no 'Use when...' or equivalent.	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 somewhat distinctive, as few other skills would use these terms. However, the core concept of 'version control' is generic enough to 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 is extremely verbose and repetitive, showing the same trajectory pattern (start/add/finalize) at least 8 times across different sections. It reads more like product marketing documentation than a concise skill file, with performance comparison tables, version history, and buzzword-heavy descriptions ('quantum-resistant', '23x faster'). The core API usage is reasonably actionable but buried in excessive repetition and incomplete advanced examples.

Suggestions

Reduce content by 70%+: Show the trajectory pattern once in Quick Start, then reference it. Remove the performance comparison table, version history, marketing claims, and status badges entirely.

Move API reference tables, advanced use cases, troubleshooting, and validation rules into separate bundle files (e.g., API_REFERENCE.md, ADVANCED_EXAMPLES.md) and reference them from a concise overview.

Make advanced examples fully executable by either providing the helper function implementations or removing them in favor of self-contained examples.

Add explicit validation checkpoints to the core workflow (e.g., verify trajectory was created before adding operations, check suggestion confidence before proceeding).

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~400+ lines. Massive amounts of redundant code examples showing the same patterns repeatedly (trajectory start/add/finalize appears 8+ times). Marketing language ('23x faster', 'quantum-resistant'), performance comparison tables, version history, and badge-like status indicators waste tokens. Explains concepts Claude already knows (what SHA3-512 is, how Promise.all works).	1 / 3
Actionability	Code examples are concrete and mostly executable JavaScript with real API calls. However, many examples rely on undefined helper functions (executeOperation, verifyDeployment, executeTask, agent.analyze) making them incomplete pseudocode in practice. The Quick Start section is actionable, but advanced use cases are more illustrative than copy-paste ready.	2 / 3
Workflow Clarity	The trajectory workflow (start → operations → add → finalize) is clear and repeated many times. However, there are no explicit validation checkpoints for the multi-step processes. Error handling is shown in best practices but not integrated into the core workflows. The troubleshooting section helps but doesn't constitute proper feedback loops in the main workflow sequences.	2 / 3
Progressive Disclosure	Monolithic wall of text with no bundle files to support it. References to external docs (VALIDATION_FIXES_v2.3.1.md, AGENTDB_GUIDE.md) exist but no bundle files are provided. The API reference tables, all advanced use cases, all examples, best practices, troubleshooting, and validation rules are all inlined when most should be in separate files. The content that is inline is heavily repetitive.	1 / 3
	Total	6 / 12 Passed

Validation

81%

Warnings & errors only

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/ruflo
Commit: 619b263

Reviewed: about 11 hours ago

Table of Contents

Discovery Implementation Validation

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.