CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

academic-research-suite

ARS-Codex research, writing, manuscript review, study screening, and experiments. Use for deep research, literature or systematic reviews, meta-analysis, research questions, drafts, revisions, roadmaps, abstracts, citations, integrity checks, peer review, research-to-paper. Screen records: sr-screener. Citation triggers: check citations, look over the refs, 檢查引用, 檢查參考文獻, 인용 확인, 인용 형식 검사. Korean: 논문 심사, 논문 수정, 초록 작성, 체계적 문헌고찰, 연구부터 논문까지. Español: revisión de literatura, revisar artículo, enmendar mi artículo, escribir resumen, investigación a artículo. Also use for ARS aliases: /ars-plan, /ars-outline, /ars-abstract, /ars-lit-review, /ars-citation-check, /ars-disclosure, /ars-format-convert, /ars-3w, /ars-revision-coach, /ars-revision, /ars-reviewer, /ars-mark-read, /ars-unmark-read, /ars-cache-invalidate, /ars-rebuttal-audit, /ars-full. Prompts, references, templates, and contracts live under ars/.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Failed to scan

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./skills/academic-research-suite/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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.

This is a highly actionable, well-sequenced router with excellent routing and alias tables and concrete fail-closed validation rules, but it is severely overloaded: an inlined duplicate of an existing reference file, five version-specific changelog sections, and large tables that should live in the referenced files make it token-expensive and structurally murky. The routing logic itself is among the clearest one could write for a suite this size.

Suggestions

Replace the inlined routing-core block with a one-line pointer to ars/shared/references/routing_core.md, keeping only the Codex-specific deltas inline.

Move the per-version sections (ARS v3.22.0-v3.24.2 changelogs and contract boundaries) into a CHANGELOG.md or docs/ file and keep a single short 'current-release notes' summary in the body.

Move the canonical agent filename lists and the long runtime-mapping table into codex/ reference files, keeping only the handful of mappings needed on every request.

DimensionReasoningScore

Conciseness

The ~650-line body inlines the routing core that already exists as ars/shared/references/routing_core.md, plus five per-version changelog sections (v3.22.0 through v3.24.2) that are version-number-laden and not placed in a deprecated/old-patterns section — several padded sections rather than occasional looseness, though it avoids explaining concepts Claude already knows.

2 / 5

Actionability

Fully concrete instruction-only guidance: exact routing tables mapping intent and aliases to specific WORKFLOW.md paths and modes, canonical agent filenames, exact script invocations with flags ("ars/scripts/run_ledger.py append", "report --claims <file>", "--render zh-TW"), and explicit trigger-phrase examples covering the common routing cases.

5 / 5

Workflow Clarity

A clearly sequenced Step 0-3 routing core with explicit validation gates (HANDOFF_INCOMPLETE blocking, fail-closed handoff parsing, ledger re-check after compaction/resume), but many exact commands, wordings, and checkpoint details are deferred to WORKFLOW.md files, leaving some checkpoints implicit in this file.

4 / 5

Progressive Disclosure

The 'First Rule' correctly mandates loading one workflow at a time and references are clearly signaled, but the routing core is inlined rather than referenced, version changelogs, runtime-mapping tables, and canonical agent lists are inlined content that belongs in separate files, and no bundle files exist in the package to verify the many ars/ paths against.

3 / 5

Total

14

/

20

Passed

Description

91%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 description: it names a broad but coherent set of academic-research capabilities, gives an explicit 'Use for' clause with concrete natural triggers in English, Chinese, Korean, and Spanish, and enumerates the alias commands. Its only weaknesses are noun-style capability listing rather than concrete verb actions and a couple of broad terms that slightly raise overlap risk.

DimensionReasoningScore

Specificity

Lists many specific capabilities ("manuscript review, study screening, ... meta-analysis, ... integrity checks, peer review") but they are domain nouns with minimal verb actions, so it sits just below the comprehensive concrete-actions anchor.

4 / 5

Completeness

Explicitly answers both: what it does ("ARS-Codex research, writing, manuscript review, study screening, and experiments") and when to use it ("Use for deep research...", "Citation triggers:...", "Also use for ARS aliases:...") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural trigger coverage including synonyms and multilingual variants ("deep research, literature or systematic reviews", "check citations, look over the refs", "檢查引用", "인용 확인", "revisión de literatura") plus the full alias list. Few plausible natural phrasings are missing.

5 / 5

Distinctiveness Conflict Risk

Clear academic-research niche with distinct multilingual and alias triggers, but broad words like "writing" and "drafts" leave minor overlap risk with general writing skills, keeping it below the minimal-conflict anchor.

4 / 5

Total

18

/

20

Passed

Validation

68%

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

Validation — 11 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (669 lines); consider splitting into references/ and linking

Warning

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

metadata_field

'metadata' should map string keys to string values

Warning

relative_links

Relative link issues: 1 missing

Warning

referenced_paths_exist

Referenced path issues: 7 missing

Warning

Total

11

/

16

Passed

Repository

Imbad0202/academic-research-skills-codex

Path

skills/academic-research-suite/SKILL.md

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.