github-multi-repo
Multi-repository coordination, synchronization, and architecture management with AI swarm orchestration
39
11%
Does it follow best practices?
Impact
88%
2.83xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/github-multi-repo/SKILL.mdQuality
Discovery
22%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 relies heavily on abstract buzzwords and lacks concrete actions or explicit trigger guidance. It fails to tell Claude what specific tasks this skill performs or when it should be selected. The 'AI swarm orchestration' phrase adds jargon without clarity.
Suggestions
Add a 'Use when...' clause with specific trigger scenarios, e.g., 'Use when the user needs to coordinate changes across multiple repositories, sync dependencies between repos, or orchestrate parallel tasks across codebases.'
Replace abstract nouns with concrete actions, e.g., 'Synchronizes dependencies across multiple repositories, coordinates cross-repo pull requests, manages shared configuration, and orchestrates parallel CI/CD pipelines.'
Include natural user terms like 'cross-repo', 'monorepo', 'multi-repo', 'dependency sync', 'repo coordination' to improve trigger term coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses abstract, buzzword-heavy language like 'coordination', 'synchronization', 'architecture management', and 'AI swarm orchestration' without listing any concrete actions. There are no specific tasks like 'merge branches', 'sync dependencies', or 'coordinate pull requests'. | 1 / 3 |
Completeness | The description only vaguely addresses 'what' with abstract nouns and completely lacks any 'when' clause or explicit trigger guidance. There is no 'Use when...' or equivalent guidance for Claude to know when to select this skill. | 1 / 3 |
Trigger Term Quality | It includes some relevant terms like 'multi-repository' and 'synchronization' that a user might mention, but 'AI swarm orchestration' is jargon unlikely to appear in natural user requests. Missing common variations like 'monorepo', 'cross-repo', 'repo sync', or specific tool names. | 2 / 3 |
Distinctiveness Conflict Risk | The 'multi-repository' focus provides some distinctiveness, but terms like 'coordination', 'architecture management', and 'synchronization' are broad enough to overlap with general project management, CI/CD, or architecture skills. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
0%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is an extremely verbose, largely aspirational document that describes a hypothetical multi-repository coordination system rather than providing actionable instructions. The code examples mix real shell commands with fictional APIs in unclear execution contexts, making them non-executable. Critical safety concerns — destructive multi-repo operations with no validation, rollback, or error recovery — combined with poor organization and massive token waste make this skill ineffective.
Suggestions
Reduce to under 100 lines by removing hypothetical features, aspirational CLI commands, and configuration examples (Kafka, Redis, Raft) that aren't actually implemented. Focus only on what works today.
Make code examples executable by clearly separating real shell/gh CLI commands from fictional API calls, and provide actual working examples rather than pseudocode with invented function signatures.
Add explicit validation checkpoints and rollback procedures for all destructive operations (pushing to repos, creating PRs, modifying files) — e.g., dry-run flags, confirmation steps, and error recovery workflows.
Split content into multiple files (e.g., SYNC.md, ARCHITECTURE.md, SECURITY.md) with a concise overview in SKILL.md that links to each, rather than inlining everything into one 500+ line document.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at 500+ lines with massive redundancy. Many sections are aspirational CLI commands that appear to be hypothetical rather than functional. Includes unnecessary configuration examples (Kafka, Redis, Raft consensus), role definitions, and metrics descriptions that pad the document without adding actionable value. Claude doesn't need explanations of what 'eventually consistent' means or what microservices are. | 1 / 3 |
Actionability | Most code examples are pseudocode-like or use invented APIs (mcp__claude-flow__swarm_init, Task(), mcp__github__push_files) without explaining what these actually resolve to. The CLI commands (npx claude-flow skill run github-multi-repo ...) appear to be hypothetical/aspirational rather than executable. The JavaScript blocks mix real shell commands with fictional function calls in an unclear execution context. | 1 / 3 |
Workflow Clarity | Despite involving highly destructive multi-repo operations (pushing changes, creating PRs, modifying files across repositories), there are no validation checkpoints, rollback procedures, or error recovery steps. The 'Synchronized Operations' section runs npm update and pushes without verifying results properly. No feedback loops for failed operations beyond a single gh issue comment. | 1 / 3 |
Progressive Disclosure | Monolithic wall of text with no bundle files to support it. Everything is inlined into a single massive document — configuration examples, architecture patterns, communication strategies, troubleshooting, monitoring, and advanced features all crammed together. No references to external files despite the content clearly warranting separation into multiple documents. | 1 / 3 |
Total | 4 / 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 (875 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
c2089c4
- 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.