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.
83
81%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
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.
This is an excellent skill description that clearly defines a specialized academic rebuttal workflow. It lists concrete actions, provides explicit trigger terms covering natural user language, and occupies a distinct niche that minimizes conflict risk. The description is concise yet comprehensive, following the recommended pattern of capabilities followed by a 'Use when...' clause.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: parses external reviews, enforces coverage and grounding, drafts a safe text-only rebuttal under venue limits, and manages follow-up rounds. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (parses reviews, enforces coverage/grounding, drafts rebuttal under venue limits, manages follow-up rounds) and 'when' with an explicit 'Use when...' clause listing specific trigger phrases. | 3 / 3 |
Trigger Term Quality | Includes highly natural trigger terms users would actually say: 'rebuttal', 'reply to reviewers', 'ICML rebuttal', 'OpenReview response', and 'answer external reviews'. These cover common variations in the academic review domain. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche targeting academic submission rebuttals with specific venue references (ICML, OpenReview). Unlikely to conflict with other skills due to the specialized domain and explicit trigger terms. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a highly actionable and well-structured workflow with excellent validation checkpoints and safety gates, making it strong on workflow clarity and actionability. However, it is significantly over-engineered for a SKILL.md file — the extreme verbosity (detailed inline templates, repeated safety rules, exhaustive constant definitions) wastes token budget and could be substantially compressed by splitting detailed specifications into referenced sub-documents. The content reads more like a full specification document than a concise skill instruction.
Suggestions
Extract the REVISION_PLAN.md template/structure, the reviewer-defensive moves section, and the Phase 4 drafting heuristics into separate referenced files (e.g., templates/revision-plan-template.md, references/defensive-moves.md) to reduce the main skill from ~400 lines to ~150.
Consolidate the safety rules — they appear in the Safety Model section, Phase 5 lints, Phase 4 hard rules, and Key Rules. Define them once and reference that single location.
Remove explanatory rationale that Claude can infer (e.g., 'This document is the single source of truth for every paper revision promised...it exists so the author can track follow-through') — just specify the artifact structure.
Compress the Constants section into a simple table rather than verbose bullet points with inline explanations for each constant.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~400+ lines. It over-explains concepts Claude can infer (e.g., what a rebuttal is, what PDF means in context, detailed rationale for each response mode), includes extensive inline documentation of constants and modes, and repeats safety rules multiple times across sections. The REVISION_PLAN.md specification alone is excessively detailed with example markdown that could be a reference file. | 1 / 3 |
Actionability | The skill provides highly concrete, executable guidance: specific file paths, exact MCP call syntax, detailed output structures with examples, explicit lint checks, character budget percentages, and copy-paste-ready Codex prompts. Every phase has clear deliverables and specific artifacts to produce. | 3 / 3 |
Workflow Clarity | The 9-phase workflow (0-8) is clearly sequenced with explicit validation checkpoints (Phase 5 safety lints with 8 specific checks), feedback loops (Codex stress test with iteration caps, fix-and-revalidate cycles), and conditional branching (QUICK_MODE exit, AUTO_EXPERIMENT gate, VENUE_MODE branching). Destructive operations are gated by three hard safety gates. | 3 / 3 |
Progressive Disclosure | The skill references external files appropriately (shared-references/reviewer-routing.md, shared-references/review-tracing.md, tools/save_trace.sh) and generates multiple output artifacts. However, the main SKILL.md itself is monolithic — the REVISION_PLAN.md template, the detailed reviewer-defensive moves section, and the full Phase 4 drafting heuristics could all be split into referenced sub-documents to reduce the main file's bulk. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 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 | 9 / 11 Passed | |
- Commit
700fbe2
- Reviewed
Table of Contents
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.