CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

datachain

Process and query data files in S3, GCS, Azure or local datasets, including inventories, media metadata, batched inference, saved results, refresh and resume.

Quality

82%

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

90%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.

This is a high-quality skill body: dense, copy-paste-ready recipes covering inventory, metadata, inference, search, joins, diffing, incremental refresh, crash resume, and export, with real operational gotchas and error-recovery guidance instead of fluff. Structure is good with a clearly signaled one-level-deep SDK.md reference, though a couple of specialized recipes could arguably be split out and verification steps could be more explicit.

DimensionReasoningScore

Conciseness

The body is exceptionally lean: every sentence carries operational guidance or a gotcha ("use `parallel=True` (one process per CPU), not a larger number, and let errors raise: `except: return 0` turns a failed read into a wrong answer") with zero padding and no explanation of concepts Claude already knows, matching "lean and efficient; assumes Claude's competence; every token earns its place". It is not 4 because there is no over-explanation to trim — even multi-sentence caveat blocks (e.g. on row indices in the nearest-neighbor recipe) are non-obvious operational constraints, not filler.

5 / 5

Actionability

Every recipe ships complete, executable code with imports and real API calls — e.g. the inventory loop, the `load_encoder`/`embed_images`/`batch_map` inference pipeline, the `file_diff` update recipe, and the fully implemented `nearest_rows` blocked scorer — covering the common cases end to end, matching "fully executable; copy-paste ready code or commands". The single placeholder `text_or_image_embedding()` is an intentional, clearly-commented stub for user-supplied input rather than a gap, so this is not 4.

5 / 5

Workflow Clarity

Recipes are clearly sequenced (reuse saved results before recomputing, filter before downloading, pin previous listing before diffing) and batch/inference operations include error-recovery loops ("catch them inside `embed_images` and return a sentinel row", "fix the failure and rerun to reuse saved checkpoints", re-run unchanged after a crash), matching "clear sequence with most checkpoints present". Not 5 because validation appears as prose guidance within recipes rather than explicit validate→fix→retry checkpoints, and some recipes (e.g. the join recipe) lack any verification step; not 3 because error handling and recovery are explicitly addressed for the batch and destructive-adjacent operations.

4 / 5

Progressive Disclosure

The body is well-organized into a short overview, a saved-results section, and eight titled recipes, with the bulk API detail pushed to a clearly signaled one-level-deep reference ("Read `{skill_dir}/SDK.md` for API details when needed: storage arguments, settings, typed UDFs, functions, windows and file types"), matching "good structure; most content is appropriately placed; references mostly clear". Not 5 because only a single external reference exists and some specialized content (the multi-page nearest-neighbor brute-force recipe, the MCAP reader) is inlined and could live in reference files; not 3 because the one reference present is clearly signaled and no content is misplaced or buried.

4 / 5

Total

18

/

20

Passed

Description

66%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, dense, and third-person, covering the skill's main capability areas and storage backends with good natural trigger terms. Its main weakness is the complete absence of any "Use when..." trigger clause, which caps completeness at 3, plus a few missing natural synonyms (bucket, object storage, embeddings).

Suggestions

Add an explicit trigger clause, e.g. "Use when listing, inventorying, or running batched inference over files in S3/GCS/Azure buckets, or when re-querying or refreshing saved dataset results."

Include natural synonyms users would say, such as "bucket", "object storage", "embeddings", and common file types (.jpg, .parquet, video/audio files), to raise trigger-term coverage from good to comprehensive.

Consider naming one or two more distinctive body capabilities (e.g. diffing listings since the last run, joining files with annotation tables) to further reduce overlap with generic data-analysis skills.

DimensionReasoningScore

Specificity

The description lists several specific capability areas — "inventories, media metadata, batched inference, saved results, refresh and resume" — across named storage backends ("S3, GCS, Azure or local"), matching the anchor "lists several specific actions; minor gaps in coverage". It falls short of 5 because the verbs "process and query" are generic and some body capabilities (joins, exports, diffs) are absent, and it exceeds 3 because it names far more than 1-2 concrete actions.

4 / 5

Completeness

The "what" is clear ("Process and query data files in S3, GCS, Azure or local datasets, including inventories, media metadata, batched inference..."), but there is no "Use when..." clause or equivalent explicit trigger guidance, capping this dimension at 3 per the judging guidelines. It is not 2 because the "what" is concrete rather than vague, and not 4 because "when" is entirely absent rather than just under-specified.

3 / 5

Trigger Term Quality

Strong natural triggers like "S3, GCS, Azure", "inventories", "media metadata", and "batched inference" match users' phrasing, fitting "good keyword coverage; a few natural terms missing". Not 5 because common variations such as "bucket", "object storage", "cloud storage", "embeddings", and file extensions (".jpg", ".parquet") are missing; not 3 because coverage goes well beyond "some relevant keywords".

4 / 5

Distinctiveness Conflict Risk

The niche — batched processing and querying of files in cloud object storage with saved, resumable datasets — is mostly distinct, with only minor overlap risk against generic data-analysis skills, matching "mostly distinct; minor overlap risk with closely related skills". Not 5 because "process and query data files" could still collide with general data-processing skills; not 3 because "batched inference, saved results, refresh and resume" pins a clear niche.

4 / 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

datachain-ai/datachain

Path

src/datachain/skill/datachain/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.