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 specialized academic workflow. It lists concrete actions, provides explicit trigger guidance with natural user phrases, and occupies a distinct niche that minimizes conflict risk. The description is concise yet comprehensive, following the best practices exemplified in the rubric's good examples.
| 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 that users would actually say: 'rebuttal', 'reply to reviewers', 'ICML rebuttal', 'OpenReview response', and 'answer external reviews'. These cover common variations of how a researcher would phrase this need. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche: academic submission rebuttals with specific venue references (ICML, OpenReview). Very unlikely to conflict with other skills given the specialized domain and precise trigger terms. | 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, well-structured rebuttal workflow with excellent phase sequencing, safety gates, and validation checkpoints. However, it is extremely verbose — many sections explain concepts Claude already knows (rebuttal strategy heuristics, tone advice) and could be condensed by 50%+ without losing actionable content. The workflow clarity is the strongest dimension, while conciseness is the weakest, with the document reading more like a detailed specification document than a lean skill file.
Suggestions
Drastically reduce verbosity: cut heuristic advice Claude already knows (e.g., 'Evidence > assertion', 'Concede narrowly when reviewer is right'), condense the Key Rules section into a compact checklist, and move the detailed REVISION_PLAN.md structure specification into a separate reference file.
Convert the Constants section into a compact YAML/table format instead of prose bullets with inline explanations — most of these are simple key-value pairs that don't need paragraph-length descriptions.
Split Phase 4 (Draft Initial Rebuttal) into a separate reference file — it contains ~150 lines of detailed drafting heuristics, reviewer-defensive moves, and REVISION_PLAN.md structure that could be referenced rather than inlined.
Make Phase 5 safety lints more actionable by providing concrete validation logic or pseudocode rather than abstract descriptions like 'flag aggressive/submissive/evasive phrases'.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~400+ lines. Extensive explanation of concepts Claude already knows (what a rebuttal is, how to structure responses), redundant restatements of rules, and over-specified constants/modes that could be condensed into a table. Many sections explain obvious patterns (e.g., 'Evidence > assertion', 'Concede narrowly when reviewer is right') that Claude inherently understands. | 1 / 3 |
Actionability | Provides concrete phase-by-phase workflow with specific file names, MCP tool calls, and structured output formats (ISSUE_BOARD.md schema, REVISION_PLAN.md checklist format). However, much guidance is procedural description rather than executable code — the MCP call examples are partial, the lint checks in Phase 5 are described abstractly without implementation, and many instructions are heuristic prose rather than precise specifications. | 2 / 3 |
Workflow Clarity | Excellent multi-phase workflow (Phase 0-9) with clear sequencing, explicit validation checkpoints (Phase 5 safety lints with 8 specific checks), feedback loops (stress test → revise → re-validate), error recovery paths (experiment failure → switch response mode), and hard gates that block finalization. The QUICK_MODE exit point and follow-up round handling are well-defined. | 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 — all content is inline rather than split into referenced sub-documents. The Phase 4 section alone is enormous and could benefit from splitting detailed heuristics into a separate reference file. | 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
31cc7b9
- 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.