data-throughput-accelerator

Diagnose and accelerate large data movement — ingestion, backfill, export, ETL, warehouse loading, manifest catch-up, and table synchronization — by isolating the true bottleneck, benchmarking variants, and codifying the fastest path with a hard accounting block proving rows and timestamps cohere. Use when a pipeline or backfill is too slow and must get faster without losing data correctness.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

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 tight, well-structured skill body with excellent token efficiency, a clear sequenced workflow, and built-in correctness gates. Its main gap is actionability: benchmarking and comparison steps describe what to vary but never show a runnable command, SQL pattern, or benchmark harness, leaving the operator to invent the mechanics.

Suggestions

Add one executable example per critical step — e.g., a sample warehouse SQL pattern or a concrete benchmark command showing how to time variants with batch size and worker count, so 'compare variants' becomes copy-paste runnable.

Include a fix-and-retry feedback loop when the correctness gate fails (e.g., 'If manifest counts and table timestamps disagree: reprocess the mismatched partitions, then rerun the accounting block') to raise workflow clarity.

Show how to measure backlog with an actual query or CLI snippet (manifest rows, min/max timestamps, unprocessed counts) rather than just listing what to measure.

Dimension	Reasoning	Score
Conciseness	The body is lean bullet-and-ordered-list prose that assumes Claude's competence — it never explains what ETL or a manifest is, and every section (First Distinction, Fast Path Heuristics, Workflow, Accounting Output, Guardrails) earns its tokens. It matches the 'every token earns its place' anchor.	5 / 5
Actionability	The only concrete artifact is the copy-paste accounting block; the rest is directional guidance ('Run a safe catch-up or sample benchmark', 'Compare variants: batch size, worker count, warehouse SQL...') with no executable commands, SQL snippets, or benchmark scaffolding. It sits between the vague and mostly-executable anchors — concrete in shape but missing the key details to execute.	3 / 5
Workflow Clarity	The seven-step workflow is clearly sequenced with real validation checkpoints ('Promote only the fastest path that keeps counts and timestamps coherent', 'Rerun final accounting', guardrail 'Do not call a pipeline complete until the target tables and manifest agree'), so the batch-operation validation cap does not apply. It falls short of the top anchor because there is no explicit fix-and-retry feedback loop when the correctness gate fails.	4 / 5
Progressive Disclosure	The file is well-sectioned with everything appropriately inline and no bundle files exist to reference, which is good organization. It misses the top anchor because the body runs past the ~50-line simple-skill threshold with domain heuristics (Fast Path Heuristics, Guardrails) that could be signposted as one-level-deep references if the skill grows.	4 / 5
	Total	16 / 20 Passed

Description

88%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: it names concrete capabilities, scopes a clear niche, and pairs an explicit what with an explicit use-when trigger. Only minor gains available from adding common synonyms like 'load', 'import', or 'migrate' to widen trigger coverage.

Dimension	Reasoning	Score
Specificity	The description lists multiple specific concrete actions — 'isolating the true bottleneck, benchmarking variants, and codifying the fastest path with a hard accounting block proving rows and timestamps cohere' — and comprehensively names the domain (ingestion, backfill, export, ETL, warehouse loading, manifest catch-up, table synchronization). It matches the comprehensive-coverage anchor; nothing is generic or padded.	5 / 5
Completeness	Both halves are explicit: the 'what' is diagnose-and-accelerate via bottleneck isolation, benchmarking, and codification, and the 'when' is the concrete trigger clause 'Use when a pipeline or backfill is too slow and must get faster without losing data correctness'. This mirrors the top anchor's what-plus-when structure.	5 / 5
Trigger Term Quality	Strong natural phrases a user would actually say: 'pipeline or backfill is too slow', 'warehouse loading', 'table synchronization', 'ETL'. A few common synonyms are missing ('load', 'import', 'migrate', 'data transfer'), keeping it just short of the comprehensive-synonyms anchor.	4 / 5
Distinctiveness Conflict Risk	The data-movement-throughput niche is clear with distinct triggers ('manifest catch-up', 'backfill', 'table synchronization'), but it could overlap with general performance-tuning or database-administration skills, so it is 'mostly distinct' rather than minimal conflict risk.	4 / 5
	Total	18 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: affaan-m/ECC
Path: skills/data-throughput-accelerator/SKILL.md
Commit: c70874f

Reviewed: 1 day 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.