CtrlK
BlogDocsLog inGet started
Tessl Logo

academic-pipeline

Orchestrator for the full academic research pipeline: research -> write -> integrity check -> review -> revise -> re-review -> re-revise -> final integrity check -> finalize. Coordinates deep-research, academic-paper, and academic-paper-reviewer into a seamless 10-stage workflow with mandatory, coverage-bounded integrity checks, two-stage peer review, and auditable quality-assurance artifacts. Triggers on: academic pipeline, research to paper, full paper workflow, paper pipeline, end-to-end paper, research-to-publication, complete paper workflow, 연구부터 논문까지, 연구 주제 설정부터 논문 완성까지, 논문 전체 워크플로.

66

Quality

81%

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

66%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 excels at workflow clarity — a fully sequenced 10-stage state machine with mandatory integrity gates, feedback loops, and checklists — and structures detail well across 16 reference files. Its weakness is conciseness: several dense opt-in engineering sections are inlined that would fit better in references, and a number of referenced paths lie outside the shipped bundle.

Suggestions

Move the dense opt-in advisory blocks (#660 tortured-phrase, #672 cross-document consistency, #673 adjudication activity, #743 inquiry-branch ledger) into dedicated reference files, leaving a one-line summary plus a link in SKILL.md.

Trim or consolidate repeated IRON RULE statements and integrity-check descriptions that reappear across the Adaptive Checkpoint, Integrity Review, Quality Standards, and Anti-Patterns sections.

Resolve or clearly mark the body's references to non-shipped paths (agents/*.md, scripts/*.py, shared/*.md, docs/design/*.md, templates/, examples/) so the bundle structure matches what SKILL.md points to.

DimensionReasoningScore

Conciseness

At 736 lines the body is noticeably verbose, with several padded opt-in engineering sections (the #660 tortured-phrase, #672 cross-document, #673 adjudication, and #743 inquiry-ledger blocks) dense with ticket references, SHA-256 binding detail, and schema row counts that read like inlined design-doc summaries rather than execution guidance Claude needs.

2 / 5

Actionability

Provides mostly executable guidance: a stage table mapping skills/modes/deliverables, concrete env flags and script paths ('ARS_PASSPORT_RESET=1', 'resume_from_passport=<hash>', 'scripts/check_re_review_synthesis.py'), checkpoint templates, and an intake/mode-recommendation decision logic, with only minor gaps in the advisory prose.

4 / 5

Workflow Clarity

Clear 10-stage sequence with an explicit state machine, MANDATORY integrity gates that cannot be auto-skipped, fix→re-verify feedback loops with 3-round caps and recorded user decisions, plus self-check questions and an anti-pattern checklist — fully meeting the anchor-5 validation/feedback-loop bar.

5 / 5

Progressive Disclosure

Good structure with a 16-entry reference table and well-signaled one-level-deep '> See references/...' links (all referenced reference files exist), but several dense opt-in sections are inlined that could move to references, and many body paths (agents/, scripts/, shared/, docs/design/) are not present in the provided bundle.

4 / 5

Total

15

/

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.

A strong, third-person description that concretely names the pipeline stages and capabilities and pairs them with an explicit, comprehensive 'Triggers on' clause in two languages. The only soft spot is minor overlap risk with the three sub-skills it coordinates.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions with comprehensive coverage: the full 8-step stage sequence ('research -> write -> integrity check -> review -> revise -> re-review -> re-revise -> final integrity check -> finalize'), 'coverage-bounded integrity checks', 'two-stage peer review', and 'auditable quality-assurance artifacts'.

5 / 5

Completeness

Explicitly answers both 'what' (orchestrates a 10-stage workflow coordinating deep-research, academic-paper, and academic-paper-reviewer with integrity checks, two-stage review, and QA artifacts) and 'when' ('Triggers on: ...' with concrete trigger phrases), matching the anchor-5 example.

5 / 5

Trigger Term Quality

Comprehensive coverage of natural trigger terms including synonyms and file-style phrasings ('academic pipeline, research to paper, full paper workflow, paper pipeline, end-to-end paper, research-to-publication, complete paper workflow') plus Korean equivalents, matching the anchor-5 example of synonyms and extensions.

5 / 5

Distinctiveness Conflict Risk

Clear niche as the full-pipeline orchestrator over three named sub-skills, but a few triggers ('research to paper', 'complete paper workflow') could plausibly also surface the closely-related sub-skills, giving minor overlap risk rather than minimal.

4 / 5

Total

19

/

20

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (737 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
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.