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

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 well-structured, actionable workflow with concrete tool calls, a clear five-step sequence, and built-in validation checkpoints. The main improvements are de-duplicating the intro against the description, making the smoke-test retry loop explicit, and templating the large prompt/output blocks.

Suggestions

Remove the redundant opening sentence ('Systematically design ablations... CC reviews feasibility and implements') since it duplicates the frontmatter description.

Make the smoke-test feedback loop explicit in Step 5: 'If a smoke test fails, diagnose and fix before re-running; do not proceed to the full run.'

Consider extracting the large Codex prompt block and output markdown template into a reference file (e.g. references/ablation_prompt.md) to tighten SKILL.md and improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly lean and assumes Claude's competence (no basic-concept padding), with minor redundancy: the opening sentence repeats the frontmatter description and the Codex prompt block is long though justified as executable content.	4 / 5
Actionability	Provides a concrete MCP call with exact config (model_reasoning_effort: xhigh), a full prompt, structured output tables, and a feasibility checklist — mostly executable, with minor gaps from template placeholders like '[description from project files]'.	4 / 5
Workflow Clarity	Five clearly sequenced steps with checkpoints (Step 4 feasibility review, Step 5 smoke test before full run), satisfying the batch-operation validation requirement; falls short of 5 because the error-recovery feedback loop (smoke-test-fails -> fix -> retry) is implicit rather than explicit.	4 / 5
Progressive Disclosure	Well-organized into clear sections (When to Use, Workflow, Rules) with no bundle files present; the large inline Codex prompt and output-template blocks keep it just short of a 5, though it is appropriately self-contained.	4 / 5
	Total	16 / 20 Passed

Description

87%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, specific description that clearly states both capability and trigger conditions in third person, with concrete domain terms. Minor room for tighter action granularity and more synonym coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'Codex designs ablations from a reviewer's perspective, CC reviews feasibility and implements' — naming the domain plus three distinct actions, with only minor granularity gaps (no per-action detail).	4 / 5
Completeness	Explicitly answers both what ('Codex designs ablations... CC reviews feasibility and implements') and when ('Use when main results pass result-to-claim (claim_supported=yes or partial) and ablation studies are needed for paper submission') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural domain terms a target user would say ('ablation studies', 'ablations', 'paper submission') plus concrete trigger conditions ('result-to-claim', 'claim_supported=yes or partial'), though a few common synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (ARIS ablation planning tied to result-to-claim gating) with distinct, specialized triggers and minimal overlap risk with other skills.	5 / 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
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: 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.