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.
61
73%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/rebuttal/SKILL.mdQuality
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 specific academic workflow (submission rebuttal pipeline), lists concrete actions, and provides explicit trigger terms covering natural user language. It uses proper third-person voice throughout and is concise yet comprehensive, making it easy for Claude to select this skill appropriately from a large pool.
| 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 rebuttals 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 of how users would phrase this need. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche: academic submission rebuttals with venue-specific constraints. The triggers ('rebuttal', 'reply to reviewers', 'ICML rebuttal', 'OpenReview response') are very specific to this domain and unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
47%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a comprehensive but excessively verbose rebuttal workflow skill. Its strongest aspect is workflow clarity — the multi-phase pipeline with explicit safety gates, stress-test iteration rules, and venue-mode branching is well-designed and thorough. However, the skill suffers significantly from token inefficiency (explaining rebuttal strategy concepts at length, over-specifying document structures inline) and moderate actionability gaps (procedural descriptions rather than executable templates or schemas). The content would benefit greatly from aggressive compression and splitting detailed specifications into referenced sub-files.
Suggestions
Compress the skill by 50-60%: remove explanatory prose Claude already knows (what rebuttals are, why evidence beats rhetoric), collapse the REVISION_PLAN.md structure spec into a referenced template file, and tighten the reviewer-defensive moves to a bullet list of patterns without elaboration.
Add concrete executable examples: show the exact markdown schema for ISSUE_BOARD.md entries, provide a sample STRATEGY_PLAN.md snippet, and include a complete lint-check pseudocode or script rather than describing checks in prose.
Split inline specifications into referenced sub-files: move the REVISION_PLAN.md structure, reviewer-defensive heuristics, and Phase 4 drafting patterns into separate referenced documents (e.g., REVISION_PLAN_TEMPLATE.md, DRAFTING_PATTERNS.md).
Provide or verify bundle files for all external references (shared-references/reviewer-routing.md, review-tracing.md, integration-contract.md) — currently these are referenced but unverifiable.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~400+ lines. Extensive explanation of concepts Claude already understands (what a rebuttal is, what reviewer concerns look like, how to structure responses). Many sections could be compressed 3-5x without losing actionable content. The 'Reviewer-defensive moves' section, REVISION_PLAN.md structure specification, and repeated safety model explanations are particularly bloated. Constants section includes unnecessary commentary. | 1 / 3 |
Actionability | Provides concrete file names, phase structure, and specific patterns (e.g., issue classification taxonomy, response modes, lint checks). However, most guidance is procedural description rather than executable code/commands. The Codex MCP call in Phase 6 is the only concrete executable snippet. Many phases describe what to do abstractly ('Create ISSUE_BOARD.md', 'Run all lints') without showing exact formats, schemas, or executable validation logic. | 2 / 3 |
Workflow Clarity | The 10-phase workflow is clearly sequenced with explicit validation checkpoints (Phase 5 safety validation with 8 specific lint checks, Phase 6 stress test with iteration rules and hard caps, commitment gate cross-validation between draft and REVISION_PLAN.md). Feedback loops are well-defined: safety gates block finalization, Codex stress test iterates until no new issues, and follow-up rounds have clear delta-only update rules. | 3 / 3 |
Progressive Disclosure | References external files like `shared-references/reviewer-routing.md`, `shared-references/review-tracing.md`, and `shared-references/integration-contract.md`, but no bundle files are provided to verify these exist. The SKILL.md itself is monolithic — the REVISION_PLAN.md structure specification, reviewer-defensive moves heuristics, and detailed Phase 4 drafting guidance could be split into referenced sub-documents. The content is reasonably organized with clear headers but too much detail is inline. | 2 / 3 |
Total | 8 / 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
a425a71
- 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.