CtrlK
BlogDocsLog inGet started
Tessl Logo

paper-sprint-review

Scrum-inspired paper review, revision, and R&R workflow. Handles docx/tex/md/PDF in English or Chinese. Auto-detects manuscript stage, estimates sprint count, runs multi-lens review (Contribution/Rigor/Writing/Editor), generates prioritized revision backlog, exports MD/DOCX/PDF/HTML reports. Use when asked to review a paper, revise based on reviewer comments, handle R&R, respond to peer review, plan paper revision sprints, or when user types /ps or /papersprint.

72

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

81%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.

A well-organized, lean instruction skill with a clear gated workflow and concrete commands and response templates. Its main weakness is bundle completeness: the detection/ and templates/ directories referenced from the body are absent, breaking navigation for those sections.

Suggestions

Add the missing bundle files referenced in the body: detection/stage_detector.md, detection/quality_checker.md, and the nine templates/*.md files (sprint_brief, process_log, backlog_item, review_memo, amendment_summary, sprint_review, retrospective, human_finalization, export_report), or remove/inline those references.

De-duplicate the disclaimer text that appears in both the Input Validation and Escape Hatches sections, and consolidate the repeated 'PaperSprint v2.2' version string to a single location.

For the Sprint Estimation, Critical Decision Flowchart, and Workflow sections that currently only say '→ Full details: <reference>', add a one-line summary inline so the body remains useful even before the reference is loaded.

DimensionReasoningScore

Conciseness

The body is largely lean and assumes Claude's competence (no explanations of what sprints/backlogs are), but the disclaimer is duplicated in both Input Validation and Escape Hatches and the version string repeats, which are minor instances of over-padding.

4 / 5

Actionability

Concrete actionable guidance throughout — specific slash commands (/ps intake, /ps review, /ps backlog, /ps gate check, /ps export), an exact quoted out-of-scope reply, and explicit escape-hatch responses — but the executable detail for each phase is deferred to reference files.

4 / 5

Workflow Clarity

A clear sequenced flow (INTAKE → PLANNING → REVIEW → AMENDMENT → BACKLOG → SPRINT REVIEW & RETRO → GATE) with explicit validation checkpoints (Quality Gates), feedback loops (gate fail → fix), and a human-finalization checklist; risky/batch revision operations are guarded by gates and the 'never auto-submit' principle.

5 / 5

Progressive Disclosure

Excellent one-level-deep structure with per-file 'When to load' triggers and 'Contents' summaries, but 11 of 19 referenced paths are broken — both detection/*.md files and all 9 templates/*.md files do not exist in the bundle, so navigation fails for those entries.

4 / 5

Total

17

/

20

Passed

Description

100%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 enumerates capabilities, formats, and languages, and pairs them with an explicit, natural-language 'Use when...' trigger clause plus slash commands. It is concise without padding and answers both what and when clearly.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Auto-detects manuscript stage, estimates sprint count, runs multi-lens review (Contribution/Rigor/Writing/Editor), generates prioritized revision backlog, exports MD/DOCX/PDF/HTML reports' — with comprehensive coverage and supported formats (docx/tex/md/PDF).

5 / 5

Completeness

Explicitly answers both what (the full capability list) and when ('Use when asked to review a paper... or when user types /ps or /papersprint') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Covers natural phrases users would say ('review a paper', 'revise based on reviewer comments', 'respond to peer review', 'plan paper revision sprints') plus synonyms ('R&R') and explicit slash triggers ('/ps', '/papersprint').

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (Scrum-inspired academic paper review/revision/R&R) with distinct triggers; the R&R and sprint framing minimizes overlap with generic review or writing skills.

5 / 5

Total

20

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 11 missing

Warning

Total

14

/

16

Passed

Repository
aipoch/medical-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.