academic-paper

12-agent academic paper writing pipeline. 11 modes (full/plan/outline/revision/revision-coach/abstract/lit-review/format-convert/citation-check/disclosure/rebuttal-audit). 6 paper types, 5 citation formats, bilingual abstracts, LaTeX/DOCX-via-Pandoc/PDF output. Style Calibration + Writing Quality Check + Anti-Patterns with IRON RULE markers. Triggers: write paper, academic paper, guide my paper, parse reviews, audit my rebuttal, check my response draft, AI disclosure, 寫論文, 學術論文, 引導我寫論文, 審查意見, 評估回覆, 논문 작성, 초록 작성, 논문 수정, 논문 계획을 도와줘, 심사 의견 반영, 답변서 점검, AI 사용 고지.

Quality

64%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./academic-paper/SKILL.md

Quality

Content

47%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill has a clear, well-checkpointed workflow and real reference files, but the body is bloated with internal version-history and contract-lint detail, and it advertises bundle directories (shared/, agents/, scripts/, templates/, examples/) that are not actually shipped.

Suggestions

Move the v3.6.6 Generator-Evaluator Contract Protocol internals (lint check counts, Schema 13.1 field distinctions, the 5% operational monitor, unreleased v3.6.7 fallback notes) into a reference file and replace the in-body block with a one-paragraph summary plus a pointer.

Reconcile 'File Structure' with the actual bundle: either ship the shared/, agents/, scripts/, templates/, and examples/ directories it describes, or remove those listings so navigation matches reality.

Provide at least one concrete, executable command or code snippet for the core drafting/revision flow rather than describing agent behavior in prose.

Dimension	Reasoning	Score
Conciseness	The body is padded with internal-version narrative Claude does not need — the ~100-line 'v3.6.6 Generator-Evaluator Contract Protocol' details lint check counts, Schema 13.1 references, a 5% operational monitor threshold, and 'Known limitations' for unreleased v3.6.7 behavior, matching the 'verbose; explains padded with unnecessary context' anchor.	1 / 3
Actionability	It provides concrete agent/mode/phase tables, but most operational guidance is descriptive rather than executable, and referenced scripts (e.g. 'scripts/check_pipeline_integrity.py', 'scripts/ars_anchorize_draft.py') are not present in the bundle, leaving incomplete copy-paste-ready instruction.	2 / 3
Workflow Clarity	The 8-phase orchestration is clearly sequenced with explicit IRON RULE validation checkpoints (confirm Paper Configuration Record before Phase 1, max 2 revision loops, critical-severity blocks), plus a failure-path table with escalation/recovery feedback loops.	3 / 3
Progressive Disclosure	The overview signals many one-level-deep references/ files that genuinely exist (plan_mode_protocol.md, mode_selection_guide.md, etc.), but the 'File Structure' section also enumerates shared/, agents/, scripts/, templates/, and examples/ paths that are absent from the actual bundle, leaving navigation partly broken.	2 / 3
	Total	8 / 12 Passed

Description

82%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, multilingual, and clearly differentiated from sibling skills, but it presents its triggers as a bare keyword list rather than an explicit 'Use when...' clause, which caps completeness at 2.

Suggestions

Rewrite the trigger list into an explicit 'Use when...' clause (e.g., 'Use when the user wants to write, plan, revise, or format an academic paper, or generate an AI-usage disclosure statement.') to lift completeness to 3.

Move the internal version/feature labels ('Style Calibration', 'IRON RULE markers') out of the description or compress them; they add noise without aiding triggering.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities and parameters — '11 modes', '6 paper types', '5 citation formats', 'bilingual abstracts', 'LaTeX/DOCX-via-Pandoc/PDF output' — matching the rubric's 'multiple specific concrete actions' anchor.	3 / 3
Completeness	'What' is clear (12-agent pipeline, modes, outputs) but the 'when' is presented only as a flat 'Triggers:' keyword list rather than an explicit 'Use when...' clause, so per the judging guideline completeness caps at 2.	2 / 3
Trigger Term Quality	Provides broad coverage of natural terms users would actually say across English ('write paper', 'guide my paper', 'parse reviews', 'audit my rebuttal'), 繁體中文 ('寫論文', '引導我寫論文'), and 한국어 ('논문 작성'), matching the 'good coverage' anchor.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (academic paper writing) with distinct triggers and explicit contrast against sibling skills (deep-research, academic-paper-reviewer, academic-pipeline), unlikely to fire for the wrong skill.	3 / 3
	Total	11 / 12 Passed

Validation

87%

Warnings & errors only

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

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_field	'metadata' should map string keys to string values	Warning
referenced_paths_exist	Referenced path issues: 3 missing	Warning

	Total	14 / 16 Passed

Repository: Imbad0202/academic-research-skills
Path: academic-paper/SKILL.md
Commit: f7d9d07

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.