dm-limits-and-best-practices

CDF Data Modeling limits: concurrency (429s), pagination, batching, search vs filter, QueuedTaskRunner, and the cap on LLM calls over query results (5 default, 50 max, cached). Triggers: DMS limits, 429, pagination, nextCursor, cdfTaskRunner, instances.query, chat completions over query results.

1.75x

Quality

76%

Does it follow best practices?

Impact

98%

1.75x

Average score across 1 eval scenario

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/dm-limits-and-best-practices/SKILL.md

Quality

Content

61%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 with concrete, executable TypeScript and explicit limits, but it ships a large source implementation inline with no bundle files, and its batch/destructive workflows omit validation feedback loops. Organization is solid, but progressive disclosure and workflow-validation gaps pull the overall score down.

Suggestions

Move the full QueuedTaskRunner implementation into scripts/semaphore.ts and reference it from SKILL.md, keeping only the usage pattern inline, to improve both conciseness and progressive disclosure.

Add explicit validation/verification steps to the batched upsert and delete workflows (e.g., confirm applied item count, verify deletes, retry on 429) with a fix-and-retry feedback loop, which would lift the workflow-clarity cap.

Split the per-section API reference and decision-guide material into a references/ file so SKILL.md acts as a concise overview pointing one level deep to details.

Dimension	Reasoning	Score
Conciseness	The prose is lean (decision tables, terse pitfalls, checklists, no basic-concept filler), but a ~115-line full QueuedTaskRunner class implementation is inlined in SKILL.md when it could be offloaded, so it is mostly efficient with substantial padding that could be tightened.	3 / 5
Actionability	Provides copy-paste-ready TypeScript for search, list, query, pagination, batching, deletes, and semaphore usage, with concrete numeric limits and BAD/GOOD contrast examples covering the common cases.	5 / 5
Workflow Clarity	Sections are well-organized with a pitfalls list and summary checklist, but the batch upsert and delete workflows lack validation/verification checkpoints or error-recovery feedback loops, and the rubric caps batch/destructive operations without validation at 3.	3 / 5
Progressive Disclosure	No bundle files exist (references/scripts/assets absent) and the full QueuedTaskRunner source is inlined despite the body itself instructing the reader to place it in src/shared/utils/semaphore.ts; content that clearly belongs in a separate file is inlined with minimal signaling.	2 / 5
	Total	13 / 20 Passed

Description

92%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 strong: it concisely enumerates concrete capabilities with numeric limits and provides an explicit, term-rich 'Triggers:' clause answering both what and when. The only minor gap is a slight bias toward API-identifier terms over colloquial user phrasing.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities (concurrency/429s, pagination, batching, search vs filter, QueuedTaskRunner) plus specific numeric limits (5 default, 50 max, cached), matching the comprehensive-coverage anchor.	5 / 5
Completeness	Clearly states what the skill covers (CDF Data Modeling limits and reliability concerns) and explicit when-to-use guidance via a concrete 'Triggers:' clause, satisfying both halves with concrete trigger phrases.	5 / 5
Trigger Term Quality	An explicit 'Triggers:' clause surfaces natural domain terms (429, pagination, nextCursor, cdfTaskRunner, instances.query, chat completions over query results), but the terms skew toward API identifiers over colloquial synonyms, leaving a few natural phrasings missing.	4 / 5
Distinctiveness Conflict Risk	Scoped to a distinct niche (CDF Data Modeling runtime reliability, DMS concurrency limits, QueuedTaskRunner) with triggers unlikely to fire sibling skills; minimal conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (624 lines); consider splitting into references/ and linking	Warning
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
metadata_version	'metadata.version' is missing	Warning

	Total	13 / 16 Passed

Repository: cognitedata/builder-skills
Path: skills/dm-limits-and-best-practices/SKILL.md
Commit: c87160a

Reviewed: 5 days 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.