agentleFS
Sign inStart free
matejformanekmatejformanek/postgres-claude/.claude/skills/pg-feature-brainstorm/SKILL.md

pg-feature-brainstorm

Skill1 starsChanged 6 months agoPostgreSQLView on GitHub

Brainstorm a half-formed PostgreSQL backend feature idea before it's worth a heavy plan — Phase 1 of the two-phase PG planner, the open-design-space stage that comes BEFORE pg-feature-plan. Frame the problem, name the relevant PG subsystems (parser / planner / executor / heap-AM / index-AM / WAL / replication / catalog / autovac / extensions), sketch 2-3 candidate approaches with explicit tradeoffs, run a "has this been tried?" check against CommitFest entries + git log + the local corpus, surface DECISION: questions only the user can answer before Phase 2, and output a short ~150-300-line brainstorm doc (NOT a file:line-cited implementation plan — that's pg-feature-plan's job). **Use this skill proactively whenever the user says "let's brainstorm a PG idea", "i have an idea for PG", "rough idea: [PG thing]", "what if we let PG [do X]", "what would it take to add [X] to PG", "could we do [Y] in PG", "explore the design space for [Z]", "i want PG to support [...]", "what are the 2-3 candidate approaches for [PG feature]", invokes \`/pg-brainstorm\`, or names a still-fuzzy half-formed PG-backend feature — even when they don't use the literal word "brainstorm". The signal is: the design space is still open, no approach is locked yet, the user wants to scope the problem before committing to file:line cites.** Skip when an approach is already picked and the user wants the heavy implementation plan (use pg-feature-plan or /pg-plan), the brainstorm is for product / SaaS / UX / marketing / business / sprint / roadmap (non-PG), the feature is for a different database engine (MongoDB / Redis / MySQL / SQLite / Snowflake / DuckDB / Cassandra / Kafka), the user is at the design-review stage of an already-written plan (use pg-patch-review or review-checklist), or the question is about already-committed PG features ("how does X work" — that's a corpus / explanation question, not a brainstorm).

The file

Show its rules and text

We split this skill into the rules it gives an agent

29 rules. About 0 are common, 22 are distinctive, and 7 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈22

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 7

    Very specific

    Tied to their project's names, files or tools. Probably skip.

Licensed with conditions — read it at the source. We count its rules but don't quote them. Read them on GitHub.

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free