Generates a plan to coordinate a dependency upgrade across multiple Oxide repos with cyclic dependencies. Triggered when upgrading a shared dependency (like progenitor, reqwest, dropshot) that must be synchronized across omicron, crucible, propolis, dendrite, maghemite, lldp, or other repos. Produces a reviewable plan document rather than executing directly.
Install with Tessl CLI
npx tessl i github:oxidecomputer/claude-plugins --skill cross-repo-upgradeOverall
score
90%
Does it follow best practices?
Validation for skill structure
Discovery
100%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 is an excellent skill description that clearly defines a specific use case for coordinating dependency upgrades across Oxide's interconnected repositories. It excels in all dimensions by providing concrete actions, natural trigger terms including specific dependency and repo names, explicit 'Triggered when' guidance, and a highly distinctive scope that prevents conflicts with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists specific concrete actions: 'Generates a plan to coordinate a dependency upgrade', 'Produces a reviewable plan document'. Also names specific dependencies (progenitor, reqwest, dropshot) and specific repos (omicron, crucible, propolis, dendrite, maghemite, lldp). | 3 / 3 |
Completeness | Clearly answers both what ('Generates a plan to coordinate a dependency upgrade', 'Produces a reviewable plan document') and when ('Triggered when upgrading a shared dependency... that must be synchronized across' specific repos). The 'Triggered when' clause explicitly defines usage conditions. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'dependency upgrade', 'shared dependency', specific dependency names (progenitor, reqwest, dropshot), specific repo names, and 'cyclic dependencies'. These are terms developers would naturally use when facing this problem. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: specifically targets Oxide repos with cyclic dependencies, names exact repos and common shared dependencies. Very unlikely to conflict with generic dependency or planning skills due to the specific organizational context. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill for a complex coordination task. It excels at workflow clarity with explicit checkpoints and a human-review gate before execution, and appropriately uses progressive disclosure to keep the main document focused on strategy while delegating details. The main weakness is some verbosity in explaining concepts (Cargo.lock behavior, why aliases work) that could be trimmed for experienced users.
Suggestions
Trim the 'Core principles' section by removing explanations of why Cargo.lock provides insulation—state the implication ('No breakage windows, no branch stepping stones needed') without the mechanism explanation.
Consider moving the detailed 'How to find them' subsection in Step 4 to REFERENCE.md, leaving just the summary of what constitutes a cross-repo type boundary.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some explanatory content that could be tightened. The 'Core principles' section explains concepts like Cargo.lock insulation that experienced Rust developers would know, and some sections repeat information (e.g., alias naming convention appears in both principles and later sections). | 2 / 3 |
Actionability | Provides concrete, executable guidance throughout: specific TOML syntax for version aliasing, exact naming conventions, clear checklist format, specific file paths to scan, and references to external files for commands and templates. The workflow steps are specific about what to gather and produce. | 3 / 3 |
Workflow Clarity | Excellent multi-step workflow with explicit checkpoints: a progress checklist at the start, numbered steps with clear sequencing, explicit validation point (Step 8: present for review before execution), and guardrails section that enforces the review gate. The three-phase execution structure with per-phase checklists provides clear feedback loops. | 3 / 3 |
Progressive Disclosure | Well-structured with clear one-level-deep references: REFERENCE.md for VCS commands and search patterns, EXECUTION-TEMPLATE.md for detailed execution plan template. The main skill provides the overview and decision-making framework while appropriately delegating mechanical details to referenced files. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
75%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 12 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
description_trigger_hint | Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...') | Warning |
metadata_version | 'metadata' field is not a dictionary | Warning |
license_field | 'license' field is missing | Warning |
body_output_format | No obvious output/return/format terms detected; consider specifying expected outputs | Warning |
Total | 12 / 16 Passed | |
Table of Contents
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.