runtime-sql-review
Mandatory write→review loop for runtime-/live-only fixes the test suite cannot catch — raw SQL via SQLAlchemy text() / asyncpg, migrations, queries, any…
Skill by Roflochinsky
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/roflochinsky-runtime-sql-review
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: backend, testing, writing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/runtime-sql-review
What's inside
- Skill name
runtime-sql-review- Description
- Mandatory write→review loop for runtime-/live-only fixes the test suite cannot catch — raw SQL via SQLAlchemy text() / asyncpg, migrations, queries, any live-DB path. Use BEFORE declaring such a fix done; a green author run is NOT done.
- License
- MIT
- Instructions
- 34 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Runtime-only SQL/migration fixes — write→review loop Our backend tests are mostly SQL-text/mocks with no live DB, so failures in raw SQL (SQLAlchemy `text()` / asyncpg), migrations, and live-DB query paths only manifest at runtime. For these fixes a green author run is NOT "done". ## The loop (author never self-approves) 1. Track via `bd` (issue or child issue of the current epic). 2. **Write** the fix. 3. **Independent review pass**: a separate `code-reviewer`/`verifier` sub-agent (Opus) reviews the diff specifically for runtime SQL hazards (bind params, casts, transaction scope, migration reversibility). 4. Approved? proceed. Rejected? fix → review again. Loop until the reviewer is clean. 5. The author never approves their own pass, and never in the same context as the write. ## Mandatory unit guard Always add a unit test that catches the failure class WITHOUT a live DB: - Compile `text(SQL)` and assert the **exact bind-parameter set** the statement exposes. - Assert null-guarded params are **explicitly cast** to their type. ## Known footguns (caught in this repo) - SQLAlchemy `text()` parses `:name` **anywhere** — including inside `--` comments. A stray `:name` / `::` in a comment becomes an unbound bind and fails at execute time with `A value is required for bind parameter ...`. - asyncpg raises `AmbiguousParameterError` on a bare `:param is null` — cast the param to its type (`:param::int is null` / `CAST(:param AS int) IS NULL`). - Prod smoke is required before declaring schema/sync/migration work done (see _Environment and safety_ in `AGENTS.md`): single prod environment, no separate stage.
From Roflochinsky/workshopskills, MIT.
More from Roflochinsky/workshopskills
- 0.474score
classifying-tasks
Roflochinsky
Use when receiving any new work request, before writing code or choosing an approach — especially multi-item requests, vague one-liners, "quick" asks, or work…
SkillCFreshness: CClaude Code +9 - 0.474score
decomposing-to-issues
Roflochinsky
Use when breaking a spec or plan into tracker issues for execution — especially when different agents or sessions will pick the pieces up independently.
SkillCFreshness: CClaude Code +9 - 0.474score
delivering-heavy-features
Roflochinsky
Use when a task is classified heavy — a new feature with its own business logic, work spanning several layers with a new or changed contract, or anything…
SkillCFreshness: CClaude Code +9 - 0.474score
doctor
Roflochinsky
Use before running heavy composite workflows (delivering-heavy-features etc.), when a required skill or tool is missing, when setting up a new machine or…
SkillCFreshness: CClaude Code +9 - 0.474score
fixing-incidents
Roflochinsky
Use when production is down or degraded, users are reporting errors, or the user demands an urgent fix ("prod is down", "fix it now", "clients are calling") —…
SkillCFreshness: CClaude Code +9 - 0.474score
getting-second-opinion
Roflochinsky
Use when about to approve, merge, or sign off on non-trivial work you authored yourself — especially when feeling confident, when the user says "I trust your…
SkillCFreshness: CClaude Code +9 - 0.474score
codifying-learnings
Roflochinsky
Use when the user corrects you, repeats an instruction they gave before, or you notice you've made the same mistake or received the same feedback more than…
SkillCFreshness: CClaude Code +9 - 0.474score
shipping-a-release
Roflochinsky
Use when implementation is complete and the user explicitly asks to wrap up, ship, release, merge, or publish the work.
SkillCFreshness: CClaude Code +9 - 0.474score
onboarding-codebase
Roflochinsky
Use when working in a repository for the first time, or in an unfamiliar area of a large repo — before making any edit, especially when the task "should be…
SkillCFreshness: CClaude Code +9 - 0.474score
upgrading-dependencies
Roflochinsky
Use when asked to update, upgrade, or bump dependencies, fix dependency vulnerabilities, or when CI flags outdated/vulnerable packages — before running any…
SkillCFreshness: CClaude Code +9 - 0.471score
heavy-task-pipeline
Roflochinsky
Use for Tier 2 / heavy Workwatch tasks — a new dashboard section with its own business logic, anything spanning API + DB migrations + UI, or any ADR-gate…
SkillCFreshness: CClaude Code +9 - 0.445score
grill-me
Roflochinsky
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jun 16, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Roflochinsky/workshopskills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Roflochinsky
- 0.474score
classifying-tasks
Roflochinsky
Use when receiving any new work request, before writing code or choosing an approach — especially multi-item requests, vague one-liners, "quick" asks, or work…
SkillCFreshness: CClaude Code +9 - 0.474score
decomposing-to-issues
Roflochinsky
Use when breaking a spec or plan into tracker issues for execution — especially when different agents or sessions will pick the pieces up independently.
SkillCFreshness: CClaude Code +9 - 0.474score
delivering-heavy-features
Roflochinsky
Use when a task is classified heavy — a new feature with its own business logic, work spanning several layers with a new or changed contract, or anything…
SkillCFreshness: CClaude Code +9 - 0.474score
doctor
Roflochinsky
Use before running heavy composite workflows (delivering-heavy-features etc.), when a required skill or tool is missing, when setting up a new machine or…
SkillCFreshness: CClaude Code +9 - 0.474score
fixing-incidents
Roflochinsky
Use when production is down or degraded, users are reporting errors, or the user demands an urgent fix ("prod is down", "fix it now", "clients are calling") —…
SkillCFreshness: CClaude Code +9 - 0.474score
getting-second-opinion
Roflochinsky
Use when about to approve, merge, or sign off on non-trivial work you authored yourself — especially when feeling confident, when the user says "I trust your…
SkillCFreshness: CClaude Code +9
Cite this page
runtime-sql-review skill. Agent Mart. https://agentmart.dev/skills/roflochinsky-runtime-sql-review (last updated 2026-10-24)