datachain-knowledge

Use whenever datasets, cloud storage buckets, or data pipelines are mentioned — creating, saving, querying, listing, exploring, deleting, or processing data in S3, GCS, Azure Blob, or local storage. Also use when running any script that may create datasets as a side effect. Maintains a knowledge base at dc-knowledge/ (JSON + markdown). ALWAYS use this skill when the user creates a dataset, saves pipeline output, runs a data script, or references any storage bucket.

Quality

92%

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

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 highly actionable and workflow-clear, with executable commands and well-placed validation checkpoints for batch/destructive operations. Its main weakness is progressive disclosure: several referenced companion files are not present in the bundle, so some signaled navigation points currently dead-end.

Suggestions

Ensure the referenced companion files (CAST.md, prompts/enrich.md, prompts/enrich_bucket.md, ../core/SKILL.md) are included in the bundle, or inline the minimal essential content they carry so signaled references resolve.

Tighten the Mode B precondition block into a short checklist so the operational steps stand out from the rationale prose.

Consider a one-line table of contents or mode-decision line at the top so readers can jump straight to the relevant Mode A-D without scanning prose.

Dimension	Reasoning	Score
Conciseness	Mostly lean with no conceptual padding and good delegation to CAST.md/core SKILL.md, but a few prose blocks (the Mode B precondition and per-mode descriptions) could be tightened further.	4 / 5
Actionability	Copy-paste-ready commands with explicit script paths, flags, and outputs plus concrete error handling (exit code 124 timeout fallback, stop-on-auth-error JSON on stderr) cover the common cases fully.	5 / 5
Workflow Clarity	A clear 7-step sequence with explicit validation checkpoints (access check stop, "up_to_date" stop, expiry warning) and feedback loops (timeout -> hierarchical fallback), satisfying the batch/destructive validation requirement.	5 / 5
Progressive Disclosure	Good one-level-deep structure (overview in SKILL.md, methodology in CAST.md, prompts and scripts in separate dirs) with clearly signaled references, but several referenced files (CAST.md, prompts/enrich.md, prompts/enrich_bucket.md, ../core/SKILL.md) are absent from the provided bundle.	4 / 5
	Total	18 / 20 Passed

Description

96%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, comprehensive, and clearly answers both what the skill does and when to use it, with strong natural trigger coverage. Its only weakness is a handful of overly generic execution triggers that could invite conflict with non-data skills.

Suggestions

Tighten generic execution triggers like "run script" and "run pipeline" to data-scoped variants (e.g. "run data pipeline", "run dataset script") to reduce overlap with unrelated skills.

Consider naming the DataChain library explicitly in the first sentence so the skill's niche is unambiguous at a glance.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("creating, saving, querying, listing, exploring, deleting, or processing") across named backends (S3, GCS, Azure Blob, local) plus the knowledge-base maintenance function, giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both 'what' (dataset/bucket/pipeline operations plus knowledge-base maintenance) and 'when' ("Use whenever...", "Also use when running any script that may create datasets as a side effect", "ALWAYS use this skill when...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural keywords including synonyms ("list datasets", "show me the schema", "explore bucket", "scan bucket") and URI schemes ("s3://", "gs://", "az://") that users would naturally say.	5 / 5
Distinctiveness Conflict Risk	Clear DataChain/cloud-storage niche with distinct backend-specific triggers, but a few triggers ("run script", "run pipeline", "python scan") are generic enough to risk overlap with unrelated execution skills.	4 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: datachain-ai/datachain
Path: src/datachain/skill/knowledge/SKILL.md
Commit: bc3e2c8

Reviewed: ~19 hours 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.