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.
89
88%
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 variations, and occupies a distinct niche that minimizes conflict risk with other skills. The description is concise yet comprehensive.
| 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 in the academic review domain. | 3 / 3 |
Distinctiveness Conflict Risk | Occupies a very clear niche — academic submission rebuttals with specific venue references (ICML, OpenReview). Unlikely to conflict with other skills due to the highly specialized domain and distinct trigger terms. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, highly actionable skill with excellent workflow clarity and robust safety gates. The multi-phase pipeline is well-sequenced with explicit validation checkpoints, error recovery paths, and resume capability. The main weakness is that all content lives in one large file without progressive disclosure to separate reference material, and some sections could be slightly more concise.
Suggestions
Consider extracting the detailed issue board schema (Phase 2 fields/enums) and strategy plan template (Phase 3) into separate reference files like ISSUE_BOARD_SCHEMA.md and STRATEGY_TEMPLATE.md, linked from the main skill.
The Lifecycle Position block and some constants (like REVIEWER_MODEL) add marginal value — consider trimming or moving to a project-level config reference.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long (~300 lines) but most content is genuinely novel workflow-specific guidance that Claude wouldn't know. Some sections are slightly verbose (e.g., the Lifecycle Position block, some of the heuristics list), and the constants section includes details like 'REVIEWER_MODEL = gpt-5.4' that could be tighter. Overall mostly efficient but could be tightened in places. | 2 / 3 |
Actionability | Highly actionable throughout: concrete file paths, specific output document names, exact MCP prompt templates, detailed issue classification schemas with field names and enum values, character budget percentages, compression priority order, and specific per-issue reply patterns. The Codex MCP stress test includes a copy-paste-ready prompt. Phase outputs are clearly specified. | 3 / 3 |
Workflow Clarity | Excellent multi-phase workflow (Phase 0-8) with explicit validation checkpoints: Phase 5 runs 6 specific lint checks, Phase 6 is a dedicated stress test with pass/fail gate, the safety model defines 3 hard gates that block finalization. Error recovery is addressed (experiment failures switch response mode, compression has priority ordering, blockers pause for user input). Resume logic is built in via Phase 0. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear phases and sections, but it's entirely monolithic — all detail is inline in a single file with no references to external documents for advanced topics. The QUICK_MODE exit point is a nice touch for progressive engagement, but the skill could benefit from splitting detailed schemas (issue board format, strategy plan template) into separate reference files. | 2 / 3 |
Total | 10 / 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
dc00dfb
- 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.