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

92%

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

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill is a well-structured, highly actionable orchestration guide with clear sequencing, validation gates, and correctly organized one-level-deep references. Its only weakness is length and conceptual repetition across overlapping sections, which keeps conciseness below the top anchor.

Suggestions

Consolidate the overlapping Validation, Hard success gates, and Negative cases sections, which restate the same checks (e.g., keeping null/failed slices visible, screening against resource limits) three times — fold the redundant items into a single canonical gate list.

Merge near-duplicate guidance between Constraints, AVOID/pitfalls, and Negative cases/stop rules, keeping one authoritative statement of each rule and cross-referencing it elsewhere instead of re-explaining.

Move the longer Paper-facing analysis quantity and Writing-facing boundary detail into a reference file, leaving a brief pointer in SKILL.md to reduce the inline token footprint while preserving the control surface.

Dimension	Reasoning	Score
Conciseness	The body is dense and mostly earns its tokens with domain-specific guidance Claude would not know, but at ~294 lines it repeats the same ideas across Validation, Hard success gates, Constraints, AVOID/pitfalls, and Negative cases (e.g., hiding null/negative/failed slices is restated several times), so it could be tightened.	2 / 3
Actionability	As an instruction-only orchestration skill it gives concrete, copy-ready guidance — specific API calls like `artifact.get_paper_contract(detail='full')` and `record_analysis_slice(..., comparison_baselines=[...])`, explicit field lists, route names, and file paths — fully actionable without being vague.	3 / 3
Workflow Clarity	The Control workflow is a clearly sequenced 6-step process, reinforced by explicit validation gates ("Before analysis-campaign can end, all applicable checks should be true"), Hard success gates, and feedback/stop rules such as stopping after two non-progressing slices.	3 / 3
Progressive Disclosure	The main file is an overview/control surface that signals one-level-deep references with clear use-conditions (campaign-design, operational-guidance, artifact-flow-examples, boundary-cases, templates), and all seven referenced files exist, with longer operational detail correctly split out.	3 / 3
	Total	11 / 12 Passed

Description

100%

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 concise, specific, and uses an explicit "Use when" trigger that covers both capability and invocation context. It lists concrete follow-up analysis types with natural trigger terms and occupies a distinct niche. No changes needed.

Dimension	Reasoning	Score
Specificity	Lists several concrete follow-up action types — "ablations, robustness checks, error analysis, or failure analysis" — matching the score-3 anchor of multiple specific concrete actions rather than vague language.	3 / 3
Completeness	Explicitly opens with "Use when a quest needs one or more follow-up runs", answering both what (the listed follow-up run types) and when (after a main experiment) with an explicit trigger clause.	3 / 3
Trigger Term Quality	Uses natural researcher-facing terms ("ablations", "robustness checks", "error analysis", "failure analysis", "after a main experiment") that a user would actually say, giving good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	Carves a clear niche — bounded follow-up evidence after a durable main result — and is distinguished from a fresh main experiment, making it unlikely to trigger for the wrong skill.	3 / 3
	Total	12 / 12 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: ResearAI/DeepScientist
Path: src/skills/analysis-campaign/SKILL.md
Commit: b366244

Reviewed: 2 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.