CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

distributed-offline-packing

Bilingual guide for running offline_packing/auto_pipe.sh across multiple nodes to produce padding-free packed WebDataset shards for SFT, with Energon Metadataset assembly

Quality

74%

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 ./.opencode/skills/distributed-offline-packing/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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.

A highly actionable, well-sequenced operational runbook with concrete commands, validation checkpoints, and a sanity checklist; its main weaknesses are the token cost of the full bilingual mirror and the absence of any bundle-file split for progressive disclosure.

Suggestions

Move the bilingual Chinese mirror into a separate reference file (e.g. references/zh.md) and link to it, so the English SKILL.md body stays lean while preserving the bilingual feature.

Add an explicit feedback loop in Step 5 (e.g. "If tar count or utilization is off, re-check --no-npy and --shard-prefix, then re-run the affected node") to turn verification into a retry cycle.

Consider extracting the Metadataset yaml template and Performance Reference into references/ files referenced one level deep, which would let progressive_disclosure reach 5.

DimensionReasoningScore

Conciseness

The English content is lean and assumes competence (no primers on WebDataset/Energon/BFD), but every section is mirrored verbatim in Chinese, roughly doubling the token budget; the bilingual duplication is the main tightening opportunity.

3 / 5

Actionability

Fully executable, copy-paste-ready bash commands with exact flags (--factor 48 --min-pixels 3136 --max-pixels 4000000, --seq-len 4096, --no-npy), a concrete split recipe, a verification one-liner, and a complete Metadataset yaml template covering the common multi-node case.

5 / 5

Workflow Clarity

Steps 0–6 are clearly sequenced with a pre-flight L-scan checkpoint, a Step 5 verification block, and an end-of-process sanity checklist; held at 4 because there is no explicit "if verify fails → fix → retry" loop embedded in the run sequence (error recovery lives in the separate Pitfalls section).

4 / 5

Progressive Disclosure

Well-structured with clear section headers and a clearly signaled "Related Files" pointer list to the codebase scripts and dataclasses, but all detail (yaml template, performance reference, pitfalls) is inlined in a single ~220-line SKILL.md with no bundle reference files to split into.

4 / 5

Total

16

/

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 highly distinctive, naming the exact tool, output, and assembly step, but it omits any explicit trigger guidance and leans on technical jargon without natural-phrase variations. Adding a "Use when..." clause would raise both completeness and trigger-term quality.

Suggestions

Append a "Use when..." trigger clause, e.g. "Use when packing a large SFT JSONL into padding-free Energon WebDataset shards across multiple nodes."

Soften jargon-only coverage by adding a natural synonym or file-type cue (e.g. ".jsonl", "sharded .tar datasets") so users phrasing the need differently still match.

Drop the "Bilingual guide for" meta-framing in favor of a verb-led capability statement ("Packs ...", "Assembles ...") to keep the focus on what the skill does.

DimensionReasoningScore

Specificity

Lists several concrete actions — "running offline_packing/auto_pipe.sh across multiple nodes", "produce padding-free packed WebDataset shards for SFT", and "Energon Metadataset assembly" — but the "Bilingual guide for" meta-framing describes the document rather than the capability, leaving minor gaps.

4 / 5

Completeness

The "what" is clear and concrete, but there is no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the rubric.

3 / 5

Trigger Term Quality

Relevant niche keywords are present ("packed WebDataset shards", "SFT", "Energon Metadataset", "auto_pipe.sh", "padding-free") but they are technical jargon with no synonyms or natural-phrase variations, and no trigger phrasing.

3 / 5

Distinctiveness Conflict Risk

The named script (auto_pipe.sh), framework (Energon), and task (padding-free packed WebDataset shards for SFT) carve out a very specific niche with minimal overlap risk against other skills.

5 / 5

Total

15

/

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

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

EvolvingLMMs-Lab/LLaVA-OneVision-2

Path

.opencode/skills/distributed-offline-packing/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.