CtrlK
BlogDocsLog inGet started
Tessl Logo

systematic-review

Structured methodology for comprehensive literature review following PRISMA guidelines. Use during literature search and screening stages.

63

Quality

73%

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

Fix and improve this skill with Tessl

tessl review fix ./researchclaw/skills/builtin/experiment/systematic-review/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is concise and well-organized as a clear numbered workflow for a simple single-purpose skill. Its main weaknesses are the absence of concrete examples/templates for full actionability and the lack of validation checkpoints in a batch screening workflow.

Suggestions

Add concrete worked examples — sample broad/narrow search query strings, an inclusion/exclusion criteria template, and an extraction table template — to make the guidance fully actionable.

Insert validation/verification checkpoints in the screening steps (e.g., re-screen borderline papers, verify criteria applied consistently, check for missed relevant work) to add error-recovery feedback loops.

DimensionReasoningScore

Conciseness

The body is a lean eight-item checklist with no padded explanations of what a literature review or PRISMA is; it assumes Claude's competence and every line carries an instruction, matching the score-3 "lean and efficient; every token earns its place" anchor.

3 / 3

Actionability

It provides concrete named elements ("Semantic Scholar, arXiv, OpenAlex"; "Extract: method, dataset, metrics, key findings"), but offers no copy-paste-ready specifics such as sample search query strings, an inclusion/exclusion criteria template, or an extraction table, fitting the score-2 anchor of "some concrete guidance but incomplete" rather than fully executable examples.

2 / 3

Workflow Clarity

The eight steps are clearly sequenced (1–8), but screening is a batch operation and no validation/verification checkpoint is present (e.g., re-screening borderline papers, consistency checks), so per the capping rule workflow clarity is held at the score-2 anchor rather than reaching the score-3 explicit-validation anchor.

2 / 3

Progressive Disclosure

This is a single-purpose skill under 50 lines with no bundle files; the content is well-organized under a clear heading with a numbered list, so under the simple-skills scoring note progressive disclosure earns a 3 without external file references.

3 / 3

Total

10

/

12

Passed

Description

75%Weight 40%Scale 1-3

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 third-person, non-generic, and clearly pairs a what-statement with an explicit 'Use during' trigger, scoring well on completeness and distinctiveness. It is held back by limited concrete action enumeration and narrow trigger-term coverage.

Suggestions

Add concrete actions to the description (e.g., "search multiple databases, screen papers by title/abstract, extract methods and findings, synthesize research gaps") to lift specificity from 2 to 3.

Broaden trigger terms with natural variations users actually say (e.g., "related work", "prior work", "research survey", "systematic survey") to improve trigger-term coverage.

DimensionReasoningScore

Specificity

Quotes "Structured methodology for comprehensive literature review following PRISMA guidelines" and "literature search and screening stages" name the domain and a couple of actions (search, screening), but no enumerated concrete actions like "search databases, screen papers, extract findings, synthesize gaps", matching the score-2 anchor rather than the multi-action score-3 example.

2 / 3

Completeness

It states the "what" ("Structured methodology for comprehensive literature review following PRISMA guidelines") and an explicit "when" trigger ("Use during literature search and screening stages"), satisfying the score-3 anchor requiring both what and when with an explicit 'Use when'-equivalent clause.

3 / 3

Trigger Term Quality

Phrases "literature review" and "literature search" are natural terms a user would say, but coverage is thin — common variations like "related work", "prior work", "research survey", or "systematic survey" are absent, fitting the score-2 anchor of "some relevant keywords but missing common variations".

2 / 3

Distinctiveness Conflict Risk

The PRISMA-guided systematic literature review niche with "literature search and screening stages" triggers is a well-defined, distinct domain unlikely to fire for unrelated skills, matching the score-3 "clear niche with distinct triggers" anchor.

3 / 3

Total

10

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
aiming-lab/AutoResearchClaw
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.