CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

offload-benchmark

Run local vs Offload benchmarks for mng and sculptor, then update the Benchmarks section of the Offload README.

Quality

80%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/offload-benchmark/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

88%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 body is a highly actionable, well-sequenced benchmark workflow with explicit validation and feedback loops, only slightly held back by minor redundancy between Steps 3 and 4 and an inline template that could be externalized.

DimensionReasoningScore

Conciseness

Mostly efficient and task-focused with concrete commands and a necessary output template; not a 5 because the Placeholder Reference table repeats formulas already given in Step 3 and could be trimmed.

4 / 5

Actionability

Provides copy-paste-ready commands (e.g. 'time just test-integration', 'time PYTEST_NUMPROCESSES=8 just test-integration'), exact env-var overrides, file paths, and a complete fill-in template covering the common cases.

5 / 5

Workflow Clarity

Steps 1-6 are explicitly sequenced with validation checkpoints (prerequisite verification, INVALID flagging on test failures, re-read to confirm README replacement) and feedback loops for a batch/update operation.

5 / 5

Progressive Disclosure

Well-organized into clearly headed sections (Prerequisites, Steps 1-6, Rules) with no nested references; not a 5 because the large README template is fully inlined in a 200-line file and could be split into a reference file.

4 / 5

Total

18

/

20

Passed

Description

62%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 specific and clearly distinct, naming concrete actions and exact targets, but it lacks an explicit 'Use when' trigger clause, which limits its trigger-term quality and completeness scores.

Suggestions

Add a 'Use when...' clause with natural trigger phrases, e.g. 'Use when the user asks to benchmark or compare local vs Offload test runs for mng or sculptor, or to refresh the Offload README benchmarks.'

Include common synonyms such as 'speedup', 'test timing', or 'benchmark the test suite' so it matches how users actually phrase the request.

Briefly mention the downstream steps (compute speedups, report results) so the 'what' is comprehensive rather than just run-and-update.

DimensionReasoningScore

Specificity

Names concrete actions ('Run local vs Offload benchmarks', 'update the Benchmarks section') tied to specific targets (mng, sculptor, Offload README); not a 5 because it omits computing metrics/speedups and reporting that the skill also covers.

4 / 5

Completeness

Clearly answers 'what' (run benchmarks for mng/sculptor and update the README) but provides no explicit 'when' / 'Use when' trigger guidance, which per guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

'benchmarks' is a natural term a user would say, but coverage is thin with no synonyms or 'Use when' phrasing; not a 4 because several natural trigger variants (e.g. 'speedup', 'benchmark the test suite') are missing.

3 / 5

Distinctiveness Conflict Risk

Targets named internal repos (mng, sculptor) and a specific file section (Offload README Benchmarks), forming a clear niche with minimal conflict risk against other skills.

5 / 5

Total

15

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

imbue-ai/offload

Path

skills/offload-benchmark/SKILL.md

Revision

6998230

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill