CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

85%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is an exceptionally actionable, well-sequenced deployment guide with real commands, explicit validation checkpoints, and a genuine error-recovery section. Its main weakness is structure: with no reference bundle, all ~400 lines — including long click-through UI guides — sit in SKILL.md itself rather than being split into one-level-deep reference files.

Suggestions

Move the step-by-step UI walkthroughs (GitHub App creation in Phase 4, Slack App configuration in Phase 5/9) into reference files (e.g., references/github-app.md, references/slack-app.md) and keep only the decision points and credential collection in SKILL.md.

Trim transitional prose such as the opening "This is a multi-phase process requiring user interaction" paragraph, which restates what the phase checklist already shows.

Consider moving the Error Handling section to a short reference file with the most common two or three failures inline, reducing baseline token cost.

DimensionReasoningScore

Conciseness

The body is command-first and dense, with almost no explanation of concepts Claude already knows (no "what is Terraform" padding), and explanatory asides are mostly load-bearing (e.g., "files:read forwards user-attached images into sessions"). A few sentences could be trimmed (e.g., the "This is a multi-phase process requiring user interaction" preamble), keeping it at anchor 4 rather than the every-token-earns-its-place anchor 5.

4 / 5

Actionability

Guidance is copy-paste ready throughout: exact bash commands (gh repo create, wrangler r2 bucket create, openssl rand, terraform apply, npx vercel --prod), exact console URLs, explicit permission lists, and concrete verification curls. Specific examples cover the common cases, matching the top anchor.

5 / 5

Workflow Clarity

The 14 phases are clearly sequenced with a TodoWrite checklist, the two-phase Terraform deployment is explicitly ordered with the reason given, Phase 12 includes a dry-run → execute → re-verify feedback loop, Phase 13 provides explicit health-check verification, and an Error Handling section maps failures to fixes. This matches the clear-sequence-with-explicit-validation anchor.

5 / 5

Progressive Disclosure

No bundle files exist, so the entire deployment manual lives inline in SKILL.md; references to docs/GETTING_STARTED.md are clearly signaled and one level deep, but substantial UI walkthroughs (GitHub App creation, Slack App configuration) are inlined where separate reference files would fit better. Section headers are good, so this is not anchor 2, but content that should be separate is inline, fitting anchor 3 rather than anchor 4's "most content is appropriately placed".

3 / 5

Total

17

/

20

Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is strong: it names the product and concrete deployment sub-actions, uses an explicit third-person voice, and includes a clear "Use when" trigger clause. Its only weakness is modest trigger synonym coverage (no "install"/"self-host" variants), which leaves a small chance of missing natural user phrasings.

Suggestions

Add common trigger synonyms such as "install", "self-host", or "host my own instance of Open-Inspect" to the Use-when clause.

Optionally mention the key external services involved (Cloudflare, Modal, Anthropic, Vercel) so users describing their stack by tool name can also surface this skill.

DimensionReasoningScore

Specificity

Lists multiple concrete actions covering the full lifecycle — "Deploy your own Open-Inspect instance", "repository setup, credential collection, Terraform deployment, and verification" — with a specific named technology (Terraform). Coverage is comprehensive across the deployment pipeline rather than leaving gaps, matching the top anchor.

5 / 5

Completeness

Explicitly answers both questions: the "what" is deploying an Open-Inspect instance with enumerated sub-actions, and the "when" is a concrete "Use when the user wants to set up, deploy, or onboard to Open-Inspect" trigger clause. Both are present and concrete, matching the top anchor.

5 / 5

Trigger Term Quality

The "Use when the user wants to set up, deploy, or onboard" clause includes natural user phrasing, but common synonyms such as "install", "self-host", or "host my own" are missing. Good keyword coverage with a few natural terms absent, fitting anchor 4 rather than the comprehensive-synonym anchor 5.

4 / 5

Distinctiveness Conflict Risk

All capabilities and triggers are tied to the specific named product "Open-Inspect", giving it a clear niche with distinct triggers and minimal risk of firing for unrelated skills. Voice is third person ("Guides through"), so no specificity penalty applies.

5 / 5

Total

19

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository

ColeMurray/background-agents

Path

.claude/skills/onboarding/SKILL.md

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.