CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

71

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

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, actionable workflow with strong validation gates and concrete artifacts, though it leans monolithic. Splitting the reference-like enum tables and REVISION_PLAN template into bundled reference files would improve progressive disclosure.

Suggestions

Move the issue_type/response_mode/severity enum tables and the REVISION_PLAN.md structure spec into a bundled reference file (e.g. references/rebuttal-spec.md) and link to it from the relevant phases to reduce inline bulk.

De-duplicate the Key Rules section against Phase 4 hard rules and the Safety Model gates so each constraint appears once.

Tighten Phase 3.5 and Phase 9 prose; the RENDER_HTML and AUTO_EXPERIMENT branches can be condensed since their behavior is already defined in Constants.

DimensionReasoningScore

Conciseness

Mostly efficient and operational with no padding of concepts Claude already knows, but a few sections (Key Rules) restate phase content ('Never fabricate', 'Full coverage') and the REVISION_PLAN spec could be trimmed.

4 / 5

Actionability

Provides concrete file names, enum vocabularies (issue_type, response_mode, severity), a concrete spawn_agent block with model/reasoning_effort, and character-budget percentages; minor gaps are instructional rather than code, which suits an instruction skill.

4 / 5

Workflow Clarity

Clear 10-phase sequence (0-9) with explicit validation in Phase 5 (six lints), three hard safety gates, draft-lint-revise feedback loops, and a QUICK_MODE exit checkpoint — validation is present for this outward-facing batch operation.

5 / 5

Progressive Disclosure

Good section headers and one-level-deep signaled references (e.g., 'See ../shared-references/reviewer-routing.md'), but no bundle files exist and reference-like material (REVISION_PLAN spec, issue/response enums, 5-rebuttal heuristics) is inlined in a single ~300-line file rather than split out.

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, specific description that clearly states concrete capabilities and provides explicit trigger guidance in third-person voice. It answers what and when comprehensively with minimal conflict risk.

DimensionReasoningScore

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 what the skill does.

5 / 5

Completeness

Explicitly answers both 'what' (the pipeline actions) and 'when' via a clear 'Use when user says...' clause with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes natural terms users would say — 'rebuttal', 'reply to reviewers', 'ICML rebuttal', 'OpenReview response' — covering synonyms and a platform name a user would naturally invoke.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (post-submission rebuttal) with distinct triggers unlikely to fire for unrelated skills; uses third-person voice ('Parses', 'enforces', 'drafts').

5 / 5

Total

20

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
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.