CtrlK
BlogDocsLog inGet started
Tessl Logo

granola-local-dev-loop

Access Granola meeting data programmatically for developer workflows. Use when reading notes from the local cache, building MCP integrations, extracting action items into code, or syncing meeting outcomes to dev tools. Trigger: "granola dev workflow", "granola MCP", "granola local cache", "granola developer", "granola programmatic".

62

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

50%

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

The body is concrete and well-structured with mostly executable code and a good error table, but it loses points for duplicated cache-loading logic, a simplified (incomplete) action-item extraction step, missing validation checkpoints before destructive/batch operations, and a monolithic layout with no bundle references.

Suggestions

Make Step 3's action-item extraction genuinely executable: implement real ProseMirror node-to-text parsing instead of the acknowledged-simplified json.dumps placeholder.

Add explicit validation checkpoints before batch/destructive operations — e.g., dry-run or confirm before `gh issue create`, and verify synced files after Step 4's writes.

De-duplicate the cache-loading logic (reuse the Step 1 `load_granola_cache()` helper in Step 4 instead of re-implementing it inline), and consider moving the full Python scripts into a scripts/ bundle to slim the SKILL.md overview.

DimensionReasoningScore

Conciseness

Mostly executable code with little generic concept explanation, but the cache-loading logic is duplicated across Step 1 (Python) and Step 4 (inline python3 -c) and could be tightened into one shared snippet.

2 / 3

Actionability

Steps 1, 2, 4, 5 are copy-paste ready, but the headline Step 3 action-item pipeline is explicitly incomplete ("text = json.dumps(content) # simplified — parse nodes for production"), leaving the core extraction task not truly executable.

2 / 3

Workflow Clarity

Five steps are clearly sequenced with a useful Error Handling table, but workflows that create GitHub issues, write files, and make git commits lack explicit validation/verification checkpoints before proceeding.

2 / 3

Progressive Disclosure

Well-organized into clear sections, but it is a single ~200-line monolithic file with full inline scripts that could be split into scripts/ or references/ bundles; no bundle files are present.

2 / 3

Total

8

/

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.

A strong, well-formed description: it names concrete capabilities, includes an explicit Use-when clause plus dedicated trigger terms, and occupies a distinct Granola-specific niche. Only minor nit is one slightly jargon-y trigger ("granola programmatic").

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "reading notes from the local cache", "building MCP integrations", "extracting action items into code", "syncing meeting outcomes to dev tools" — matching the multi-action anchor.

3 / 3

Completeness

Explicitly answers both what ("Access Granola meeting data programmatically for developer workflows") and when ("Use when reading notes from the local cache, building MCP integrations...") with an explicit trigger clause.

3 / 3

Trigger Term Quality

Provides an explicit Trigger clause with several natural variations ("granola dev workflow", "granola MCP", "granola developer") giving good coverage of terms a user would say, though "granola programmatic" leans slightly technical.

3 / 3

Distinctiveness Conflict Risk

Scoped to Granola meeting data with Granola-specific triggers, a clear niche unlikely to collide with other skills.

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

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

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

Warning

Total

14

/

16

Passed

Repository
jeremylongshore/claude-code-plugins-plus-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.