onboarding
Deploy your own Open-Inspect instance. Use when the user wants to set up, deploy, or onboard to Open-Inspect. Guides through repository setup, credential collection, Terraform deployment, and verification with user handoffs.
Install with Tessl CLI
npx tessl i github:ColeMurray/background-agents --skill onboarding86
Quality
81%
Does it follow best practices?
Impact
100%
1.51xAverage score across 3 eval scenarios
Discovery
85%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 a strong skill description that clearly defines its purpose and when to use it. It provides specific concrete actions and has explicit trigger guidance. The only minor weakness is that trigger terms could include more natural variations users might say when requesting deployment help.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'repository setup, credential collection, Terraform deployment, and verification with user handoffs' - these are clear, actionable steps. | 3 / 3 |
Completeness | Clearly answers both what ('Deploy your own Open-Inspect instance... Guides through repository setup, credential collection, Terraform deployment, and verification') AND when ('Use when the user wants to set up, deploy, or onboard to Open-Inspect'). | 3 / 3 |
Trigger Term Quality | Includes good terms like 'deploy', 'set up', 'onboard', 'Open-Inspect', and 'Terraform', but missing common variations users might say like 'install', 'configure', 'spin up', or 'infrastructure'. | 2 / 3 |
Distinctiveness Conflict Risk | Very specific niche targeting 'Open-Inspect' deployment specifically, with distinct triggers like 'Terraform deployment' and 'Open-Inspect' that are unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong deployment guide with excellent actionability and workflow clarity. The 13-phase structure with explicit validation steps and comprehensive error handling makes it highly usable. Main weakness is the monolithic structure - at this length, some content (credential collection details, post-deployment setup) could be split into separate files for better progressive disclosure.
Suggestions
Extract credential collection instructions (Phase 3) into a separate CREDENTIALS.md file, keeping only a summary checklist in the main skill
Move post-deployment Slack and GitHub bot setup (Phases 9-10) to separate files like SLACK_SETUP.md and GITHUB_BOT_SETUP.md
Remove explanatory text like 'The App Home provides a settings interface where users can configure their preferred Claude model' - Claude can infer purpose from context
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some unnecessary explanations (e.g., explaining what URLs look like, describing what App Home provides). Some sections could be tightened, though most content is necessary for the complex deployment process. | 2 / 3 |
Actionability | Provides fully executable commands throughout with specific bash commands, exact URLs, and copy-paste ready code blocks. Terraform configurations are concrete with actual variable names and values to substitute. | 3 / 3 |
Workflow Clarity | Excellent multi-phase workflow with explicit sequencing (13 numbered phases), clear validation checkpoints (two-phase Terraform deployment, verification phase with curl commands), and explicit error handling section with recovery guidance. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear phase headers, but the skill is monolithic at ~300 lines. Some sections (like the full Slack/GitHub bot setup) could be split into separate reference files. The TodoWrite checklist helps but doesn't replace proper file organization. | 2 / 3 |
Total | 10 / 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 |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- 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.