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

78%

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

62%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.

The body delivers a highly actionable, well-sequenced multi-agent pipeline with strong validation checkpoints, but it is noticeably verbose and inlines large protocol blocks that belong in reference files. Several referenced paths do not resolve in the bundle, weakening progressive disclosure despite good overall file organization.

Suggestions

Move the v3.6.6 Generator-Evaluator Contract Protocol, Model Tiering, and #390/#684 protocol detail into reference files (e.g. references/generator_evaluator_contract.md) and keep only a one-line pointer plus the load-bearing IRON RULE in SKILL.md to reduce the ~90 lines of inlined contract spec.

Resolve or de-reference paths that do not exist in the bundle (shared/references/intent_clarification_protocol.md, passport_as_reset_boundary.md, review_criteria_consumer_protocol.md, sprint_contract_protocol.md, agents/*, templates/*, examples/*, scripts/*); either include the files or rewrite pointers to reference only files that ship with the skill.

Trim version/issue-ID noise (#684, #668, #548, PR #294, etc.) from the overview body — move design-doc citations into the relevant reference file so the SKILL.md overview stays lean.

Dimension	Reasoning	Score
Conciseness	The 528-line body inlines large blocks of internal protocol machinery (the ~90-line v3.6.6 Generator-Evaluator Contract block, Model Tiering, #390 patch protocol, #684 binding) padded with version numbers and issue IDs that belong in reference files rather than the overview. It is noticeably verbose with several padded sections, though it does not explain concepts Claude already knows (avoiding a 1).	2 / 5
Actionability	Concrete execution guidance throughout: an 8-phase orchestration flow, a 12-agent table mapping roles to phases, a mode table mapping triggers to specific agent chains and outputs, named script commands ('python scripts/ars_anchorize_draft.py', 'scripts/check_pipeline_integrity.py'), and an anti-patterns table. Minor gaps keep it below 5 — some commands reference scripts not present in the bundle and guidance is occasionally abstract.	4 / 5
Workflow Clarity	The 8-phase pipeline is clearly sequenced with explicit validation checkpoints (IRON RULE: user must confirm Paper Configuration Record before Phase 1; max 2 revision loops; Critical-severity blocks progression to Phase 7), feedback loops (revision loops, lint retry semantics), and a failure-paths table — matching the anchor for clear sequence with explicit validation and error-recovery loops.	5 / 5
Progressive Disclosure	There is a well-signaled reference layer (28 reference files, a File Structure section, one-level-deep 'See references/X.md' pointers) but substantial protocol content that should live in separate files is inlined in SKILL.md, and several referenced paths (shared/references/, agents/, templates/, examples/, scripts/*) do not resolve within the provided bundle. Organization is present but undermined by inlined bulk and dangling references.	3 / 5
	Total	14 / 20 Passed

Description

95%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 dense, specific description that names a clear niche, enumerates capabilities concretely, and provides comprehensive multilingual trigger phrases for both what and when. It leans slightly on feature-listing over action-verbs, keeping specificity just short of a 5.

Dimension	Reasoning	Score
Specificity	Enumerates concrete capabilities ('12-agent pipeline', '11 modes', '6 paper types, 5 citation formats', 'LaTeX/DOCX-via-Pandoc/PDF output', 'Style Calibration + Writing Quality Check + Anti-Patterns') but presents them as a feature list rather than the action-verb density of a 5 ('extract, fill, merge, convert').	4 / 5
Completeness	Explicitly answers both what ('12-agent academic paper writing pipeline... 11 modes... output') and when ('Triggers: write paper, academic paper, guide my paper...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger terms across English ('write paper', 'guide my paper', 'parse reviews', 'audit my rebuttal'), Traditional Chinese, and Korean, including synonyms and multilingual variants users would actually say.	5 / 5
Distinctiveness Conflict Risk	Clear niche (academic paper writing pipeline) with distinct, specific triggers and enumerated modes that minimize overlap with adjacent skills like deep-research or academic-paper-reviewer.	5 / 5
	Total	19 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (543 lines); consider splitting into references/ and linking	Warning
metadata_field	'metadata' should map string keys to string values	Warning
referenced_paths_exist	Referenced path issues: 4 missing	Warning

	Total	13 / 16 Passed

Repository: Imbad0202/academic-research-skills
Path: academic-paper/SKILL.md
Commit: 9443623

Reviewed: 4 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.