aris-ablation-planner

Use when main results pass result-to-claim (claim_supported=yes or partial) and ablation studies are needed for paper submission. Codex designs ablations from a reviewer's perspective, CC reviews feasibility and implements.

Quality

85%

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.

A well-structured, actionable workflow with a clear sequence, a smoke-test checkpoint, and a concrete tool-invocation template. The only real weakness is repetition of the Codex/CC division of labor and some restated guidance that could be trimmed.

Suggestions

State the Codex/CC division of labor once (e.g., in the opening) and reference it from later steps instead of restating it in Step 2 and the Rules section.

Trim overlapping Rules entries (e.g., the priority ordering is partly repeated across Step 4 and Rules) to reduce redundancy.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids teaching known concepts, but the Codex/CC division of labor is restated three times (intro, Step 2 header, Rules) and the embedded prompt repeats guidance, so it could be tightened.	2 / 3
Actionability	Provides a concrete, copy-ready Codex MCP invocation with a full prompt template plus structured markdown tables to normalize the output — fully actionable, not abstract.	3 / 3
Workflow Clarity	A clear five-step sequence with an explicit validation checkpoint ('Smoke test each ablation before full run') and a feedback loop for the batch compute operation (CC proposes cuts, Codex re-prioritizes).	3 / 3
Progressive Disclosure	A single self-contained SKILL.md organized into clear labeled sections with no nested references; nothing here benefits from being split into separate bundle files.	3 / 3
	Total	11 / 12 Passed

Description

85%

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 specific, well-triggered description that clearly states both what the skill does and when to use it, occupying a distinct niche. Its main weakness is reliance on internal slash-command and status jargon that a user would not naturally phrase.

Suggestions

Replace internal references like 'result-to-claim (claim_supported=yes or partial)' with natural phrasing such as 'when experiment results support a claim and reviewers need ablation studies'.

Add common natural trigger terms (e.g., 'design ablations', 'reviewer-requested ablations', 'sensitivity studies') so the description matches how users actually ask.

Dimension	Reasoning	Score
Specificity	Lists concrete actions — 'designs ablations from a reviewer's perspective', 'reviews feasibility and implements' — naming a clear division of labor rather than vague verbs.	3 / 3
Completeness	Explicit 'Use when main results pass result-to-claim ... and ablation studies are needed for paper submission' covers when, and the second sentence covers what (designs, reviews, implements).	3 / 3
Trigger Term Quality	'ablation studies' and 'paper submission' are natural user terms, but the description leans on internal jargon like 'result-to-claim' and 'claim_supported=yes or partial', missing common variations a user would actually say.	2 / 3
Distinctiveness Conflict Risk	A clear niche — ablation planning for paper submission with a Codex/CC split — that is unlikely to trigger for other skills.	3 / 3
	Total	11 / 12 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	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/aris-ablation-planner/SKILL.md
Commit: 6da7f7c

Reviewed: about 8 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.