CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

remote-compute-modal

Run GPU jobs on the user's own Modal account via host.compute.create('byoc:modal', ...). Covers the create→submit→wait_for_notification flow, the compute_provider kernel for env setup, image/volume resolution, and the two approval cards. Load once you've decided to dispatch to Modal.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

77%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.

An expert-grade operational skill: the two-kernel architecture, image-reference rule, timeout model, and error catalog are all rendered as concrete executable guidance with strong validation loops. Its weaknesses are a ~780-line monolithic body that keeps deep-dive reference material inline despite pointing to env-setup.md elsewhere, and noticeable repetition of the timeout, notification-payload, and image-ref rules.

Suggestions

Move the reference-heavy material — the error-kind catalog under "When the job fails", the network-egress debugging guide, and "Common env gotchas" — into a separate reference file (like the existing env-setup.md pattern), leaving SKILL.md as a lean overview with clearly signaled one-level-deep pointers.

Deduplicate the repeated rules: state the container-vs-job timeout distinction, the compute_done payload fields, and the im-… image-reference rule once each (the image rule alone appears in prose, bold text, two code comments, and its own section), and cut the rest to a back-reference.

Consider relocating the GPU tier table and measured latency table to a reference file as well, keeping only the headline numbers (~3–6 min first GPU result, ~5–10 s warm resubmit) inline where the workflow needs them.

DimensionReasoningScore

Conciseness

The body is dense with host-specific operational detail and never explains concepts Claude already knows, but it is noticeably repetitive: the container-timeout vs job-timeout explanation appears in both "Two timeouts, one timeline" and again in "Workflow"; the `compute_done` payload field list (status/exit_code/featured_files plus error_kind/system_hint/deadline_fired) is given twice; and the "pass `r['image']`, not the bare env name" rule is stated at least four times ("Carry `r['image']` … NOT the env name", "**Pass `r['image']` (the `im-…` ref)**", two code comments, plus the dedicated "image-reference rule" section). This is more than the minor trimmable instances of anchor 4, so anchor 3 fits.

3 / 5

Actionability

Fully executable, copy-paste-ready code cells for both the `repl` and `compute_provider` kernels with real kwargs (image refs, gpu tiers, volumes, timeout_seconds), a per-error-kind → remedy catalog, measured latency and GPU-tier tables, and concrete teardown commands like `modal.Sandbox.list(app_id=app.app_id, tags={"claude-science-job": "<job_id>"})` — anchor 5.

5 / 5

Workflow Clarity

The multi-step process is clearly sequenced (check the `compute_details` ledger via `spec_sha` → build env in the `compute_provider` kernel → hand off via a workspace JSON file → append the ledger block → submit → `wait_for_notification` → attach/close) with explicit validation checkpoints: `compute_provider_config()` staleness check "before anything expensive", per-error-kind recovery loops, and an end-of-task teardown checklist ("every handle closed … no sandbox of yours still alive"). Feedback loops for the risky batch/spend operations are present, matching anchor 5.

5 / 5

Progressive Disclosure

Section headers are clear and `env-setup.md` is repeatedly and clearly signaled with its scope, but no bundle files exist (`references/`, `scripts/`, `assets/` are absent) and the ~780-line body inlines deep-dive material that belongs in separate files — the full error troubleshooting catalog, the egress-fence debugging guide, the env gotchas list, and the GPU-tier/latency tables. Structure is real but the monolithic inline bulk matches anchor 3 rather than the well-split content of anchor 4.

3 / 5

Total

16

/

20

Passed

Description

83%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.

A strong description: concrete API-level actions, an explicit load condition, and a clearly bounded niche around the user's Modal account. The only soft spot is trigger coverage, which names the Modal/GPU-job vocabulary but offers no synonyms a user might use instead.

DimensionReasoningScore

Specificity

"Run GPU jobs on the user's own Modal account via host.compute.create('byoc:modal', ...)" plus "create→submit→wait_for_notification flow", "compute_provider kernel for env setup", "image/volume resolution", and "the two approval cards" names multiple concrete actions covering the skill's full surface — anchor 5, not 4, since coverage is comprehensive rather than having minor gaps.

5 / 5

Completeness

Both halves are explicitly present: the what ("Covers the create→submit→wait_for_notification flow, the compute_provider kernel for env setup, image/volume resolution, and the two approval cards") and the when ("Load once you've decided to dispatch to Modal"). The when-clause is a single gating instruction rather than concrete user-facing trigger phrases, so it falls short of anchor 5 but is far more than the weakly-implied when of anchor 3.

4 / 5

Trigger Term Quality

Natural terms like "GPU jobs", "Modal account", and "dispatch to Modal" are phrases a user would actually say, but coverage stops there — no synonyms or variations ("cloud compute", "remote GPU", "serverless") — matching anchor 4 rather than the comprehensive synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

"Modal account", "byoc:modal", and GPU jobs on a named provider carve out a clear niche with distinct triggers — a user naming Modal or asking for GPU dispatch would land here, not on a generic compute skill — matching anchor 5's minimal conflict risk.

5 / 5

Total

18

/

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

skill_md_line_count

SKILL.md is long (790 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository

UnicomAI/wanwu

Path

configs/microservice/bff-service/configs/agent-skills/claude-science/remote-compute-modal/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.