offload-onboard

Onboard a repository to use Offload for parallel test execution on Modal. Detects test setup, creates config, Dockerfile, CI job, and optimizes performance.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/offload-onboard/SKILL.md

Quality

Content

77%Weight 40%Scale 1-3

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

The content is highly actionable with clear, validated multi-step workflows specific to Offload onboarding. It loses points for verbosity in spots and for keeping all reference material inline rather than splitting it into bundled files.

Suggestions

Trim explanations of general concepts Claude already knows (e.g., the .gitignore vs .dockerignore note, the .venv explainer) and remove the duplicated config-reference block at the end of Step 4.

Move the troubleshooting table, the full config reference, and the CI workflow examples into separate reference files (e.g., TROUBLESHOOTING.md, CONFIG.md, CI.md) and link to them one level deep to improve progressive disclosure.

Fix the step numbering gap (jumps from Step 9 to Step 11) so the sequence is unambiguous.

Dimension	Reasoning	Score
Conciseness	Most content is concrete, product-specific guidance Offload requires, but it includes explanations of concepts Claude already knows (e.g., "Do not confuse .gitignore ... with .dockerignore", the .venv explainer) and a config-reference block that duplicates the inline comments.	2 / 3
Actionability	Provides fully executable, copy-paste-ready artifacts: Dockerfiles, offload.toml templates, a bash invocation script, and a complete GitHub Actions workflow, plus specific commands like `offload collect` and `cargo install offload`.	3 / 3
Workflow Clarity	Steps are explicitly sequenced with strong validation checkpoints and feedback loops ("Do not continue until all prerequisites are confirmed", "Repeat until offload collect succeeds", "Keep running ... until Offload's pass/fail counts match the baseline").	3 / 3
Progressive Disclosure	The body is well-sectioned but monolithic at ~585 lines with no bundle reference files; the troubleshooting table, config reference, and CI examples that could live in separate one-level-deep references are all inline.	2 / 3
	Total	10 / 12 Passed

Description

67%Weight 40%Scale 1-3

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 specific and distinctive, clearly conveying the onboarding actions and niche. Its main weakness is the missing explicit "Use when..." trigger guidance and somewhat jargon-heavy trigger terms.

Suggestions

Add a "Use when..." clause with natural trigger phrases (e.g., "Use when onboarding a repo to Offload, parallelizing tests on Modal, or when the user mentions Offload or running tests in parallel").

Soften product jargon by including plain user-facing terms like "run tests in parallel" and "speed up test suites" alongside Offload/Modal.

Dimension	Reasoning	Score
Specificity	"Detects test setup, creates config, Dockerfile, CI job, and optimizes performance" enumerates multiple concrete actions, matching the score-3 anchor that lists several specific actions.	3 / 3
Completeness	It clearly states what the skill does but provides no explicit "Use when..." trigger clause, which per the judging guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Relevant keywords appear (Offload, parallel test execution, Modal, Dockerfile, CI job) but they lean on product jargon and miss common user phrasings, fitting the anchor for some relevant keywords without full coverage.	2 / 3
Distinctiveness Conflict Risk	The Offload + Modal + parallel test execution niche is specific with distinct triggers, making conflict with other skills unlikely.	3 / 3
	Total	10 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (585 lines); consider splitting into references/ and linking	Warning
referenced_paths_exist	Referenced path issues: 3 missing	Warning

	Total	14 / 16 Passed

Repository: imbue-ai/offload
Path: skills/offload-onboard/SKILL.md
Commit: 5cc6a7c

Reviewed: 6 days 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.