CtrlK
BlogDocsLog inGet started
Tessl Logo

notion-research-documentation

Research across Notion and synthesize into structured documentation; use when gathering info from multiple Notion sources to produce briefs, comparisons, or reports with citations.

71

Quality

88%

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

77%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 skill body is well-organized, concise, and provides concrete Notion MCP orchestration guidance with a clear sequenced workflow and useful operational guardrails. Its main weakness is that the `reference/` templates and `examples/` walkthroughs it repeatedly directs Claude to load do not exist in the bundle, breaking progressive disclosure and parts of actionability.

Suggestions

Create the referenced `reference/` bundle files (`format-selection-guide.md`, `citations.md`, and the brief/summary/comparison/comprehensive templates) — steps 2–4 instruct Claude to load and adapt them, but no `reference/` directory exists, so those steps cannot be completed.

Either add the advertised `examples/` walkthroughs (e.g., `competitor-analysis.md`, `technical-investigation.md`) or remove the `examples/` reference line so there are no dangling pointers.

Inline a minimal concrete example (a `Notion:search` call payload and a `Notion:notion-create-pages` call with parent/pages) so the core steps remain actionable even before the bundle files are added.

DimensionReasoningScore

Conciseness

The body is lean and operational throughout — it never explains concepts Claude already knows (no "what Notion is" or "what a citation is"), and the tool-call guardrails capture non-obvious operational gotchas that earn their tokens. The Quick-start/Workflow pairing is a reasonable overview-then-detail structure rather than padding.

3 / 3

Actionability

It names concrete MCP tools with argument shapes (Notion:search with filters:{}, notion-create-pages with parent/pages, update_content with search-and-replace pairs), but core steps 2–4 redirect to a `reference/` directory and templates that do not exist, leaving those steps incomplete and not executable as written.

2 / 3

Workflow Clarity

A clear numbered pipeline (Quick start 1–5 and Workflow 0–5) is present with explicit checkpoints — "confirm scope with the user", the tool-not-found guardrail ("Do not retry it"), and the Step 0 fallback when tools are unavailable — giving a sequenced flow with error-handling feedback for the risky tool-availability case.

3 / 3

Progressive Disclosure

References are well-signaled and one-level-deep in structure (e.g., "capture citations (`reference/citations.md`)" and a labeled References section), but per the rubric's guideline to score against the actual bundle, the referenced `reference/` and `examples/` directories do not exist — only `assets/` is present — so every signaled reference path is dangling and cannot be navigated.

2 / 3

Total

10

/

12

Passed

Description

100%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 concise, third-person, and clearly answers both what the skill does and when to use it, with concrete output types and a Notion-specific trigger. It is a strong, low-conflict description.

DimensionReasoningScore

Specificity

"Research across Notion and synthesize into structured documentation" names the domain, and "produce briefs, comparisons, or reports with citations" lists multiple concrete output actions, matching the score-3 anchor of multiple specific concrete actions.

3 / 3

Completeness

It states both what it does ("Research across Notion and synthesize into structured documentation") and an explicit "use when gathering info from multiple Notion sources to produce briefs, comparisons, or reports with citations" trigger, satisfying both what and when.

3 / 3

Trigger Term Quality

Natural terms a user would say appear throughout — "Notion", "briefs", "comparisons", "reports", "citations", "multiple Notion sources" — giving good coverage rather than technical jargon.

3 / 3

Distinctiveness Conflict Risk

The Notion-scoped niche with "multiple Notion sources" triggers is clearly distinct from generic research/documentation skills and unlikely to fire for the wrong skill.

3 / 3

Total

12

/

12

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

metadata_version

'metadata.version' is missing

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

14

/

16

Passed

Repository
openai/plugins
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.