CtrlK
BlogDocsLog inGet started
Tessl Logo

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/.

57

Quality

72%

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 ./plugins/ars-codex/skills/academic-research-suite/SKILL.md

The canonical home for this skill is academic-research-suite in Imbad0202/academic-research-skills-codex

SKILL.md
Quality
Evals
Security

Quality

Content

42%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 is a well-conceived router with genuinely concrete routing tables and explicit fail-closed rules, but as a SKILL.md it is severely overweight: dense versioned contract lists and boundary prose that belong in reference files are inlined, and every operational pointer targets vendored files absent from this bundle. The routing core is the strong core; most of the rest adds tokens without adding executable guidance at the router level.

Suggestions

Move the ARS v3.22.x caller-contract and contract-honesty boundary lists into a dedicated reference file (e.g., ars/shared/references/) and keep only a one-line pointer plus the few rules that affect routing decisions.

Compress the Codex Runtime Mapping table to the rows that change routing behavior; the environment-variable transport details (ARS_CROSS_MODEL_TRANSPORT, cache settings, API keys) belong in codex/model-runtime-policy.md.

Trim the duplicated sr-screener boundary statements (they appear in the routing core, the router table, and a dedicated section) into one authoritative statement plus cross-references, and ship the referenced ars/ and codex/ files with the bundle so the one-level-deep pointers resolve.

DimensionReasoningScore

Conciseness

The ~575-line body inlines enormous policy sections that should live in separate reference files: the multi-hundred-word Codex Runtime Mapping table rows (e.g., the `ARS_CROSS_MODEL_TRANSPORT=codex` row), the 'ARS v3.22.0 Contract-Honesty Boundaries' list, and the sr-screener boundary paragraphs. It does not explain concepts Claude already knows, so it avoids the score-1 'padded with basics' anchor, but a router this token-heavy loaded on every activation is noticeably verbose with several sections that could be trimmed or moved.

2 / 5

Actionability

There is genuinely concrete guidance — the alias table ('read `ars/commands/ars-plan.md`, route to `ars/academic-paper/WORKFLOW.md` in `plan` mode'), the intent-to-WORKFLOW routing table, and canonical agent filename lists — but the executable detail of each mode is deferred to vendored files not present in this bundle, and large portions (Contract-Honesty Boundaries, Bibliographic Network Routing) are abstract policy rather than executable steps. This lands between 'mostly executable with minor gaps' (4) and 'minimal concrete guidance' (2).

3 / 5

Workflow Clarity

The routing core gives a real sequence (Step 0 escape hatch, then classify as explicit intent / cross-phase materials / ambiguous) with some explicit checkpoints ('If a workflow or required supporting file cannot be loaded, report the loading failure and stop that workflow'), but the many overlapping exception carve-outs ('only when', 'unless', 'never') and stage validation deferred to absent WORKFLOW.md files leave the overall procedure with implicit checkpoints and gaps, fitting the score-3 anchor.

3 / 5

Progressive Disclosure

Section structure and one-level-deep references are present and mostly clearly signaled, but the body inlines large contract and boundary content that clearly belongs in separate files, and none of the referenced bundle files (ars/, codex/) exist in the package as provided, so the pointers cannot be verified. This fits 'some structure but could be better organized; content that should be separate is inline' better than the score-4 'most content appropriately placed'.

3 / 5

Total

11

/

20

Passed

Description

96%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.

The description is a strong, explicit trigger surface: it states concrete capabilities, gives an explicit 'Use for' clause with rich natural trigger phrases in English, Chinese, Korean, and Spanish, and enumerates the slash aliases it emulates. Its only weakness is that a few broad terms (research, writing, drafts) could contend with adjacent skills.

Suggestions

Tighten broad words like 'research, writing, drafts' toward academic-specific phrasing (e.g., 'academic manuscript writing') to reduce overlap with general writing/research skills.

Consider adding the most common plain-English user phrasings (e.g., 'review my paper', 'write my abstract') alongside the multilingual triggers.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions across the full suite: "research, writing, manuscript review, study screening, and experiments" plus "meta-analysis, research questions, drafts, revisions, roadmaps, abstracts, citations, integrity checks, peer review, research-to-paper". Coverage is comprehensive across writing, review, screening, and pipeline phases, matching the score-5 anchor rather than the score-4 anchor with 'minor gaps'.

5 / 5

Completeness

It explicitly answers both questions: the 'what' in the opening sentence ("ARS-Codex research, writing, manuscript review, study screening, and experiments") and the 'when' via "Use for deep research, literature or systematic reviews, meta-analysis, research questions, drafts, revisions..." plus "Also use for ARS aliases". Concrete trigger phrases and an explicit 'Use for' clause match the score-5 anchor; a missing 'Use when' clause would have capped it at 3.

5 / 5

Trigger Term Quality

Natural trigger phrases are covered comprehensively with synonyms and multilingual equivalents: "check citations, look over the refs, 檢查引用, 檢查參考文獻, 인용 확인, 인용 형식 검사", "논문 심사, 논문 수정, 초록 작성, 체계적 문헌고찰", "revisión de literatura, revisar artículo, enmendar mi artículo, escribir resumen", plus slash aliases like "/ars-plan, /ars-abstract, /ars-lit-review". This matches the anchor for comprehensive natural-term coverage including synonyms; it is not merely the score-4 'good coverage with a few missing'.

5 / 5

Distinctiveness Conflict Risk

The academic-research niche is clear with distinct triggers (ARS aliases, sr-screener screening boundary, multilingual manuscript phrases), but generic words like "research", "writing", "drafts", and "revisions" create minor overlap risk with general writing or code-research skills. This fits 'mostly distinct; minor overlap risk with closely related skills' rather than the score-5 'minimal conflict risk'.

4 / 5

Total

19

/

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 (596 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
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.