ds-analysis-campaign

Use when a quest needs one or more follow-up runs such as ablations, robustness checks, error analysis, or failure analysis after a main experiment.

Quality

82%

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

81%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 thorough, highly actionable campaign protocol with concrete tool calls, exact paths, and well-sequenced validation feedback loops. Its main weakness is verbosity from repeated field lists and prescriptive cadences that could be consolidated.

Suggestions

Consolidate the repeated paper-contract field lists (section_id, item_id, claim_links, paper_role) and the six-field evaluation_summary into a single canonical definition, then reference it instead of restating it in Quick workflow, Non-negotiable rules, and Workflow 0.1.

Move the detailed bash_exec monitoring cadence (60s/120s/300s/600s/1800s) and mode reference into a dedicated reference file, keeping only the principle ('wait-and-check with escalating cadence') inline.

Trim restated 'Do not ...' rules that reappear across sections to a single non-negotiable list, reducing inline body length.

Dimension	Reasoning	Score
Conciseness	Avoids explaining basic concepts but is densely long with notable repetition: the paper-contract fields (section_id, item_id, claim_links, paper_role) and the six-field evaluation_summary recur across multiple sections, and monitoring cadences are very prescriptive.	3 / 5
Actionability	Provides fully executable guidance: concrete artifact calls with parameters (artifact.create_analysis_campaign, artifact.record_analysis_slice), exact bash_exec modes, explicit file paths, and precise per-slice field lists.	5 / 5
Workflow Clarity	Clear numbered workflow (0, 0.1, 1-6) with explicit validation checkpoints (smoke test before real run, completion confirmation, paper-contract return-path verification) and feedback loops for a batch operation.	5 / 5
Progressive Disclosure	Uses clearly signaled one-level-deep references to real bundle files (campaign-design.md, campaign-plan-template.md, campaign-checklist-template.md, writing-facing-slice-examples.md, artifact-orchestration.md), though a large amount of protocol detail remains inline in the 640-line body.	4 / 5
	Total	17 / 20 Passed

Description

83%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 clear, third-person description that states a concrete trigger condition and enumerates the specific follow-up run types it covers. It answers both 'what' and 'when' explicitly and stays well-scoped to its niche.

Dimension	Reasoning	Score
Specificity	Names the domain plus several concrete run types ('ablations, robustness checks, error analysis, or failure analysis'), though all are variants of 'follow-up runs' rather than distinct action verbs.	4 / 5
Completeness	Explicitly answers both what (coordinated follow-up runs) and when ('Use when a quest needs one or more follow-up runs ... after a main experiment') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural research terms a user would say ('ablations', 'robustness checks', 'error analysis', 'follow-up runs') with good coverage, missing only a few synonyms.	4 / 5
Distinctiveness Conflict Risk	Carves a clear post-main-experiment follow-up niche with distinct triggers, with only minor overlap risk against a generic experiment stage.	4 / 5
	Total	17 / 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
skill_md_line_count	SKILL.md is long (644 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: OpenLAIR/dr-claw
Path: skills/ds-analysis-campaign/SKILL.md
Commit: 4b35756

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.