CtrlK
BlogDocsLog inGet started
Tessl Logo

scaffold-snowflake-connector

Use when adding a new snowflake-connector data source to crowd.dev — a new platform or a new source within an existing platform that needs buildSourceQuery, transformer, activity types, migration, and all associated type registrations scaffolded.

69

Quality

85%

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

SKILL.md
Quality
Evals
Security

Quality

Content

77%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 highly actionable, well-sequenced scaffolding workflow with strong validation checkpoints for a batch file-writing task. Its main weaknesses are repetitive reinforcement of critical rules across sections and a monolithic single-file structure with no progressive disclosure for a skill this large.

Suggestions

Consolidate the repeated identity/lfUsername rules and 'read before modifying' guidance into a single authoritative section (e.g., the Anti-Hallucination Rules) and reference it from the phases instead of restating, to reduce token cost.

Move the per-touch-point code/SQL templates (touch points 2, 5, 7, 8) and an example transformer into a references/ file (e.g., TEMPLATES.md or an example transformer) with one-level-deep links, keeping SKILL.md as an overview plus the decision logic.

Trim the restated anti-hallucination items that already appear verbatim in their respective phases, keeping only the cross-cutting rules in the final list.

DimensionReasoningScore

Conciseness

Largely efficient and earned given the 11 touch points, but critical rules are restated multiple times (identity/lfUsername guidance in §3a and touch point 9, 'read before modifying' and anti-hallucination rules duplicating phase-level instructions), which could be tightened.

3 / 5

Actionability

Provides concrete file paths, executable SQL/TypeScript templates with explicitly justified placeholders, exact MCP tool names, and specific commands (pnpm run format/lint, date +%s, git clone) — copy-paste ready guidance covering the common cases.

5 / 5

Workflow Clarity

A clearly sequenced five-phase process with a dot graph, explicit validation diamonds ('All mappings confirmed?', 'User approves each file?'), feedback loops (dry-run loop-back to Phase 3, re-run lint until clean), and a completion checklist for this batch/file-writing operation.

5 / 5

Progressive Disclosure

Well-organized with clear section headers, but the ~700-line skill is entirely monolithic with no bundle files (references/, scripts/, assets/ absent); per-touch-point templates and example transformers that would benefit from one-level-deep reference files are inlined.

3 / 5

Total

16

/

20

Passed

Description

92%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, specific description that clearly states both the triggering scenarios and the concrete artifacts it scaffolds, with minimal conflict risk. Slightly narrow trigger-term vocabulary keeps it just short of a perfect score on keyword coverage.

DimensionReasoningScore

Specificity

Lists multiple concrete scaffolded artifacts — 'buildSourceQuery, transformer, activity types, migration, and all associated type registrations' — giving comprehensive coverage of the skill's actions rather than vague language.

5 / 5

Completeness

Explicitly answers both 'what' (scaffolds buildSourceQuery, transformer, activity types, migration, type registrations) and 'when' via a concrete 'Use when adding a new snowflake-connector data source ... a new platform or a new source within an existing platform' trigger clause.

5 / 5

Trigger Term Quality

Natural trigger phrases ('adding a new snowflake-connector data source', 'a new platform', 'a new source within an existing platform') map well to what a user would say, though it stays within one specialized vocabulary and omits broader synonyms or file extensions.

4 / 5

Distinctiveness Conflict Risk

The 'snowflake-connector data source to crowd.dev' niche is highly specific with distinct triggers, making accidental activation by unrelated skills very unlikely.

5 / 5

Total

19

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (700 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
linuxfoundation/crowd.dev
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.