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

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

77%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-sequenced, highly actionable rebuttal pipeline with strong validation gates and feedback loops, undermined by a monolithic structure and several references to shared-references files that are absent from the bundle. Conciseness is good but slightly weakened by cross-phase repetition.

Suggestions

progressive_disclosure: Either create the referenced bundle files (shared-references/reviewer-routing.md, review-tracing.md, integration-contract.md, scripts/save_trace.sh) or remove the dangling references so every cited path resolves.

progressive_disclosure: Move the detailed REVISION_PLAN.md structure spec and the issue-card field schema/enums into a reference file, keeping SKILL.md as a phase-level overview that links out.

conciseness: State PASTE_READY.txt and RENDER_HTML handling once in their defining phase and reference it elsewhere, instead of re-describing them in Constants, Phase 4, Phase 7, and Phase 9.

Dimension	Reasoning	Score
Conciseness	Dense, domain-specific procedural content with almost no basic-concept padding, but minor redundancy: PASTE_READY.txt and RENDER_HTML handling are restated across Constants, Phase 4, Phase 7, and Phase 9, which could be trimmed to a single canonical statement.	4 / 5
Actionability	Provides copy-paste-ready MCP calls with exact configs, a verbatim stress-test prompt, and complete issue-card/field schemas, but references to non-existent files (shared-references/reviewer-routing.md, review-tracing.md, integration-contract.md, save_trace.sh) leave minor executability gaps.	4 / 5
Workflow Clarity	Phases 0-9 are clearly sequenced with explicit validation checkpoints (Phase 5's eight lints, hard safety gates), feedback loops (draft-lint-revise, stress-test iterations terminating on no new issues), and checklists (REVISION_PLAN), matching the score-5 anchor.	5 / 5
Progressive Disclosure	Section/phase structure is present and clearly signaled, but the body is a ~370-line monolith that inlines bulk detail (REVISION_PLAN spec, issue-card schema, defensive-move heuristics) and references bundle files that do not exist in the package, creating dead navigation links.	3 / 5
	Total	16 / 20 Passed

Description

100%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, third-person description that concisely states concrete capabilities and provides an explicit 'Use when...' trigger clause with natural, venue-specific terms. It clearly delimits a distinct niche with minimal conflict risk.

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' — giving comprehensive coverage of the skill's capabilities, matching the score-5 anchor.	5 / 5
Completeness	Explicitly answers both 'what' (parses reviews, enforces coverage/grounding, drafts text-only rebuttal, manages follow-ups) and 'when' (an explicit 'Use when...' clause with concrete trigger phrases), satisfying the score-5 anchor.	5 / 5
Trigger Term Quality	Includes natural phrases users actually say — 'rebuttal', 'reply to reviewers', 'ICML rebuttal', 'OpenReview response', 'answer external reviews safely' — covering synonyms and venue-specific terms comprehensively.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear academic peer-review niche with distinct triggers ('ICML rebuttal', 'OpenReview response') and the 'Workflow 4' framing, giving minimal overlap risk with other skills.	5 / 5
	Total	20 / 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: wanshuiyin/Auto-claude-code-research-in-sleep
Path: skills/rebuttal/SKILL.md
Commit: f4f20f9

Reviewed: 1 day 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.