rebuttal

Workflow 4: Submission rebuttal pipeline. Parses external reviews, enforces coverage and grounding, drafts a safe text-only rebuttal under venue limits, and manages follow-up rounds. Use when user says "rebuttal", "reply to reviewers", "ICML rebuttal", "OpenReview response", or wants to answer external reviews safely.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

77%

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

A highly actionable, well-sequenced workflow with strong validation gates, but it is a long monolithic body that could offload detail to reference files and lacks the referenced bundle files within the skill itself.

Suggestions

Move large inline blocks (REVISION_PLAN.md structure, reviewer-defensive moves, the Phase 6 stress-test prompt) into reference files under references/ and link to them one level deep to improve progressive disclosure.

Create the referenced shared-references/ files (reviewer-routing.md, review-tracing.md, integration-contract.md) and save_trace.sh as actual bundle assets so signaled references resolve to real files.

Tighten the Constants and Key Rules sections by collapsing near-duplicate guidance (e.g. anti-fabrication rules appear in both Safety Model and Key Rules) to reduce token cost while preserving the operational content.

Dimension	Reasoning	Score
Conciseness	The body is dense and operational with little concept re-explanation, but at ~360 lines it carries large inline blocks (REVISION_PLAN structure, reviewer-defensive moves, full phase prompts) that could be tightened or moved to reference files rather than earning every token in SKILL.md.	2 / 3
Actionability	Provides concrete, copy-paste-ready guidance: exact MCP tool names and configs, full stress-test prompt templates, specific file paths, character-budget percentages, and a worked checklist example — fully executable rather than descriptive.	3 / 3
Workflow Clarity	A clear Phase 0–9 sequence with explicit validation checkpoints (Phase 5 lints, provenance/commitment/coverage gates) and feedback loops (draft → lint → revise; stress-test → revise before finalizing), matching the anchor for sequenced validation with error recovery.	3 / 3
Progressive Disclosure	External references are clearly signaled (reviewer-routing.md, review-tracing.md, integration-contract.md, save_trace.sh), but no bundle directories (references/scripts/assets) or shared-references/ files exist in this skill, and substantial detail that could be split into separate files remains inline in SKILL.md.	2 / 3
	Total	10 / 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.

A strong description: third-person voice, concrete actions, explicit trigger guidance, and a distinctive niche. It does not pad with buzzwords and clearly signals when to invoke the skill.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Parses external reviews, enforces coverage and grounding, drafts a safe text-only rebuttal under venue limits, and manages follow-up rounds' — matching the anchor for several specific actions rather than vague language.	3 / 3
Completeness	Explicitly answers both what (the pipeline actions) and when via a clear 'Use when...' clause with multiple triggers, so it is not the level-below where 'when' is only implied.	3 / 3
Trigger Term Quality	Natural trigger terms a user would actually say are well covered: 'rebuttal', 'reply to reviewers', 'ICML rebuttal', 'OpenReview response', and 'answer external reviews safely'.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (post-submission rebuttals) with distinct triggers unlikely to fire for unrelated skills; not the level-below where overlap with similar skills is possible.	3 / 3
	Total	12 / 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: wanshuiyin/Auto-claude-code-research-in-sleep
Commit: fe5963c

Reviewed: about 19 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.