CtrlK
BlogDocsLog inGet started
Tessl Logo

notion-spec-to-implementation

Turn Notion specs into implementation plans, tasks, and progress tracking; use when implementing PRDs/feature specs and creating Notion plans + tasks from them.

92

1.49x
Quality

90%

Does it follow best practices?

Impact

97%

1.49x

Average score across 3 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

80%

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 highly actionable with a clear sequenced workflow and the right progressive-disclosure pattern, but it loses points because batch creation lacks an explicit validation feedback loop and the referenced reference/examples files are missing from the bundle.

Suggestions

Add an explicit verification step after creating plan/tasks (e.g., re-fetch the created page to confirm properties and relations resolved) so the batch-create workflow has a validate-then-fix feedback loop.

Ship the referenced reference/*.md files (spec-parsing.md, standard-implementation-plan.md, task-creation.md, task-creation-template.md, progress-tracking.md, progress-update-template.md, milestone-summary-template.md) and examples/*.md so the inline references resolve to real bundle files.

In Step 3, after creating tasks, add a brief checklist confirming each task links to both plan and spec and has status/priority set, turning the linking step into an explicit checkpoint.

DimensionReasoningScore

Conciseness

The body is lean and action-oriented — numbered Quick start plus a sequenced Workflow — and assumes Claude's knowledge of Notion rather than explaining what specs or tasks are; every line earns its place.

3 / 3

Actionability

Concrete, copy-paste-ready guidance throughout: exact tool calls ("Notion:notion-search", "Notion:notion-fetch", "Notion:notion-create-pages"), shell commands ("codex mcp add notion --url ...", "codex mcp login notion"), and specifics like sizing tasks to "1–2 days" and which properties to set.

3 / 3

Workflow Clarity

Steps 0–5 are clearly sequenced with some checkpoints ("if multiple hits, ask the user", "confirm the data source and required properties"), but task/plan creation is a batch operation with no explicit verify-after-create feedback loop, which caps workflow clarity at 2 per the batch-operations guideline.

2 / 3

Progressive Disclosure

References are well-signaled and one-level-deep inline and in a References section, but the actual bundle only contains assets/ — the referenced reference/*.md and examples/*.md files do not exist, so the signaled navigation does not resolve to real files.

2 / 3

Total

10

/

12

Passed

Description

100%

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 specific, uses third-person imperative voice, includes explicit trigger guidance, and carves out a clear niche. It hits all the good-example patterns without padding or over-claims.

DimensionReasoningScore

Specificity

"Turn Notion specs into implementation plans, tasks, and progress tracking" names three concrete deliverables (plans, tasks, tracking), matching the anchor that lists multiple specific concrete actions rather than vague language.

3 / 3

Completeness

It states what ("Turn Notion specs into implementation plans, tasks, and progress tracking") and explicitly when ("use when implementing PRDs/feature specs and creating Notion plans + tasks from them"), with an explicit "Use when" clause, so it is not capped at 2.

3 / 3

Trigger Term Quality

Natural terms a user would say are well covered — "Notion specs", "PRDs", "feature specs", "implementation plans", "tasks" — giving good coverage of common phrasings rather than technical jargon.

3 / 3

Distinctiveness Conflict Risk

The Notion-spec-to-implementation niche with PRD/feature-spec triggers is clearly distinguishable from other skills and unlikely to trigger for the wrong skill.

3 / 3

Total

12

/

12

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
openai/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.