CtrlK
BlogDocsLog inGet started
Tessl Logo

seeding

Fill a PostgreSQL database with realistic, relationally valid test data using Seedfast. Use when the user wants to seed, populate, or fill a database, needs test/demo/staging data, has empty tables to work against, wants a dev database that behaves like production, or says "seed the database", "seed my database", "populate my postgres with test data", "fill the staging database", "generate test data for these tables", "my dev database is empty", "I need demo data", or mentions Seedfast, fixtures, or synthetic data.

76

Quality

95%

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

92%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.

The body is a strong, lean instruction skill: a sequenced 7-step workflow with explicit validation checkpoints and feedback loops for a destructive batch operation (row-count verification, no premature success reading), concrete MCP tool guidance, and clean sectioning with one-level references. Minor actionability limits come only from the inherent dependency on live schema output, which is justified.

DimensionReasoningScore

Conciseness

Lean and efficient throughout: it assumes Claude's competence (no 'what is a database' filler), each sentence earns its place, and the prose stays tight even across the safety/guardrails sections. The only near-padding is the brief 'work happens on Seedfast's backend' framing, which is genuinely useful context.

5 / 5

Actionability

Gives concrete, specific MCP tool names with their arguments and behaviors (idempotencyKey, planId vs scope, answer.human_answer) — highly actionable for an MCP-orchestration skill. It stops just short of fully copy-paste-ready invocations because exact argument payloads depend on live schema output, a justified gap for this skill type.

4 / 5

Workflow Clarity

A clearly sequenced 7-step loop with an explicit diagram, and strong validation/feedback loops for the destructive batch operation: 'Never read success out of the run response', 'Counted rows are the only real evidence' with a SELECT count(*) verification step, and a failure-recovery sequence. This satisfies the destructive-operation feedback-loop requirement.

5 / 5

Progressive Disclosure

Well-organized single-file skill with clear section headers (loop, scopes, safety, guardrails, plans, resources, failures); one-level references are cleanly signaled (the scope-examples and seed-production-db server prompts, and the seedfast:// resource URIs in a table). No bundle files exist to verify, but the in-file structure is appropriately organized with no nested references.

5 / 5

Total

19

/

20

Passed

Description

95%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.

The description is exemplary: it clearly states what the skill does, gives an exhaustive and natural set of trigger phrases, and is tightly scoped to Seedfast/PostgreSQL test-data generation with low conflict risk. It earns the top of the scale on completeness, trigger quality, and distinctiveness, with only minor specificity gaps.

DimensionReasoningScore

Specificity

Names the domain (PostgreSQL) and several concrete actions ('seed, populate, or fill a database', 'relationally valid test data', 'dev database that behaves like production') with only minor coverage gaps around what the skill reads/does not do.

4 / 5

Completeness

Explicitly answers both 'what' ('Fill a PostgreSQL database with realistic, relationally valid test data using Seedfast') and 'when' (a long explicit 'Use when...' clause with concrete trigger phrases).

5 / 5

Trigger Term Quality

Comprehensive natural trigger phrases users would actually say ('seed the database', 'seed my database', 'populate my postgres with test data', 'fill the staging database', 'generate test data for these tables', 'my dev database is empty', 'I need demo data') plus synonyms (fixtures, synthetic data, Seedfast).

5 / 5

Distinctiveness Conflict Risk

Clear niche — Seedfast test-data generation against PostgreSQL — with distinct triggers ('Seedfast', 'seed the database', 'fixtures', 'synthetic data') and minimal overlap risk with other skills.

5 / 5

Total

19

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
seedfast-ai/claude-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.