CtrlK
BlogDocsLog inGet started
Tessl Logo

create-readonly-db-role

Provision a hardened SELECT-only Postgres role so AI agents can safely read a production database. Works on Supabase and any Postgres. Use when the user wants agents to query prod data, says "read-only role", "safe prod DB access for agents", or is tired of running SQL by hand for agents. Differentiator: this skill CREATES the role and wiring; day-to-day querying belongs in a project-local skill.

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

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

100%

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

An excellent self-contained skill: executable SQL and verification commands, a clearly sequenced workflow with validation checkpoints and a feedback loop, and tight, well-organized prose that assumes competence. No bundle files are present, but none are needed at this scope.

DimensionReasoningScore

Conciseness

Lean and dense: every section (3-layer pattern, RLS trap, workflow, SQL template, verification, failure modes, maintenance) earns its place and assumes Claude's competence, only touching domain-specific gotchas rather than explaining basic Postgres concepts. A single light marketing line ('the human stops being the SQL bottleneck') does not rise to verbosity.

3 / 3

Actionability

Provides a complete, copy-paste-ready SQL template (with a clearly marked REPLACE_ME password placeholder) and an executable psql verification loop with concrete commands and expected outputs, rather than pseudocode.

3 / 3

Workflow Clarity

A clearly sequenced 7-step workflow opens with a state-check, and the verification loop enforces an explicit checkpoint ('all must pass before declaring done') with a feedback loop ('If any check fails, fix the grants and re-run ALL checks') plus a failure-modes section for recovery — appropriate for database operations.

3 / 3

Progressive Disclosure

No bundle files exist (references/scripts/assets absent), and the self-contained body is organized into clearly labeled sections with no nested references; per the rubric's simple-skill note, well-organized sections with no need for external references score 3.

3 / 3

Total

12

/

12

Passed

Description

90%

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-targeted description that clearly states what it does and when to use it, with natural trigger terms and an explicit scope differentiator. Its only relative weakness is specificity, since it describes one core action rather than a list of several.

DimensionReasoningScore

Specificity

Names a concrete action and domain ('Provision a hardened SELECT-only Postgres role so AI agents can safely read a production database'), but it centers on a single provisioning action rather than enumerating multiple distinct concrete actions, matching the 'names domain and some actions' anchor rather than the 'lists multiple specific concrete actions' anchor.

2 / 3

Completeness

Explicitly answers what (provision a hardened SELECT-only Postgres role) and when via a clear 'Use when the user wants agents to query prod data, says ...' clause, satisfying both halves.

3 / 3

Trigger Term Quality

Includes natural phrases a user would say — 'read-only role', 'safe prod DB access for agents', 'query prod data', 'tired of running SQL by hand' — giving good coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

A clear niche (creating the role + wiring) with distinct triggers, and an explicit differentiator ('this skill CREATES the role and wiring; day-to-day querying belongs in a project-local skill') makes conflict with adjacent skills unlikely.

3 / 3

Total

11

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
mishatojk/davidskills
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.