CtrlK
BlogDocsLog inGet started
Tessl Logo

systematic-review

Orchestrates a systematic review and meta-analysis workflow following PRISMA 2020 guidelines, from protocol development through multi-database search, screening, data extraction, and evidence synthesis. Use when conducting evidence-based reviews, meta-analyses, or scoping revi...

58

Quality

73%

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

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Academic Writing/systematic-review/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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-structured orchestrator skill with a coherent seven-step PRISMA workflow and domain-specific tool selection, but it reads as a high-level plan rather than executable guidance: no commands or code, no validation checkpoints inside the workflow, and dependent sub-skills referenced without paths. The truncated checklist-mapping section promises detail it does not contain.

Suggestions

Add concrete, executable anchors: example database-specific search string patterns and the meta-analysis tool or code approach (e.g., a Python/R snippet for pooled estimates and forest plots), plus paths or invocation syntax for the literature-search, scienceclaw-ie, and paper-writing sub-skills.

Insert validation checkpoints between steps, e.g., reconcile PRISMA flow counts after deduplication, verify inter-rater kappa before full-text screening, and confirm heterogeneity assumptions before choosing fixed vs. random effects.

Either inline a compact step-to-checklist-item mapping or move the full 27-item PRISMA 2020 checklist mapping into a reference file (e.g., references/prisma-checklist.md) and link it from the Checklist Reference section.

DimensionReasoningScore

Conciseness

The body is lean and directive without explaining concepts Claude already knows, but minor trims are possible: the PICO acronym expansion and the "PRISMA 2020 Checklist Reference" section, which promises a step-to-item mapping without delivering it, add tokens without actionable content.

4 / 5

Actionability

The guidance names concrete domain tools and statistics ("RoB 2 for RCTs, ROBINS-I", "Cohen's kappa", "SMD, OR, RR, HR", "I-squared", "trim-and-fill") but includes no commands, code, or search-string templates, and the three sibling skills it depends on are referenced by name only with no paths or invocation details — concrete guidance that remains incomplete to execute.

3 / 5

Workflow Clarity

Seven steps are clearly and logically sequenced from protocol registration through PRISMA reporting, and an input-validation guardrail exists, but there are no in-workflow checkpoints such as PRISMA count reconciliation after deduplication, kappa thresholds for screening agreement, or stop/verify rules before synthesis — validation is left implicit.

3 / 5

Progressive Disclosure

Sections are well organized for a single-file skill, but no bundle files exist; the Integration Points reference sibling skills without links or paths, and the 27-item PRISMA checklist mapping is described but neither inlined nor moved to a reference file, so navigation and content placement could be substantially better.

3 / 5

Total

13

/

20

Passed

Description

78%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 with a specific capability pipeline and an explicit "Use when..." clause occupying a distinct niche. Its main defects are a mid-word truncation of the final trigger phrase and a few missing natural synonyms.

Suggestions

Fix the truncated trigger clause so the full phrase (e.g., "scoping reviews") fits within the description length limit, shortening the capability list if needed.

Add commonly voiced synonyms such as "literature review" and "PRISMA" to the trigger clause to improve natural-language matching.

DimensionReasoningScore

Specificity

The description lists several concrete pipeline stages — "protocol development through multi-database search, screening, data extraction, and evidence synthesis" — but omits risk-of-bias assessment and PRISMA reporting that the body itself covers, leaving minor gaps in coverage rather than the comprehensive coverage of a 5.

4 / 5

Completeness

Both a clear "what" (orchestrates a PRISMA 2020 systematic review and meta-analysis workflow with named stages) and an explicit "Use when conducting evidence-based reviews, meta-analyses, or scoping revi..." clause are present; the truncated final trigger phrase keeps it just below the fully explicit 5 anchor.

4 / 5

Trigger Term Quality

Natural user phrases like "systematic review", "meta-analyses", "evidence-based reviews", and "scoping revi..." are present, but the last trigger term is truncated mid-word in the source file and common synonyms such as "literature review" or "PRISMA" are missing, so coverage is good but not comprehensive.

4 / 5

Distinctiveness Conflict Risk

The description carves out a clear niche — PRISMA 2020-guided evidence synthesis with named methodology stages — with trigger terms unlikely to fire for unrelated skills, matching the minimal-conflict-risk anchor.

5 / 5

Total

17

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

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.