agentleFS
Sign inStart free
gerard-labsgerard-labs/superpowers-api-platform/skills/using-symfony-superpowers/SKILL.md

using-symfony-superpowers

Skill2 starsChanged 6 months agoMITView on GitHub

Entry point and command map for the gerard plugin. Lists the 7 agents (3 architecture personas + implementer + tdd-coach + reviewer + doctrine-architect utility), the 7 pipeline commands (/architect, /dev, /test, /review, /api-resource-pipeline, /api-resource-ship, /self-audit-api), the 53 skills, the state-files protocol, and the authority order (CLAUDE.md > stage personas > project skills layer > plugin canon). Use to onboard a new project, choose between pipeline vs atomic skill invocation, or locate a specific doctrine.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 0 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read this skill (gerard:using-symfony-superpowers) — entry point.

    line 42
  2. Very specific:

    If pipeline → /api-resource-pipeline or /api-resource-ship.

    line 44
  3. Very specific:

    If atomic → use the relevant /symfony-api-* command or invoke the skill/agent directly.

    line 45
  4. Very specific:

    Skill dispatch theatre is rejected: every claimed skill dispatch must have an actual Skill() / Task() call in the tool stream.

    line 65

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Using gerard plugin

Use when

  • Onboarding a project to the plugin
  • Choosing between pipeline (chained stages, state files, REQUEST_CHANGES loop) and atomic skill invocation (single skill, no orchestration)
  • Locating a specific skill / agent / command
  • Setting up the project skills layer (<project>:X overrides)

Two modes of operation

A. Pipeline mode (recommended for non-trivial features)

Use one of:

  • /api-resource-pipeline <story> — chains the 4 stages (architect → dev → test → review) with REQUEST_CHANGES loop (cap 3), stops before commit so you can inspect.
  • /api-resource-ship <story> — same as pipeline but commits + pushes + opens PR autonomously with garde-fous (refuses dirty tree, explicit git add, skips secrets, no --force/--no-verify).

State files in .claude/last-api-*.md track stage handoffs (gitignored).

B. Atomic mode (for quick edits or hors-pipeline)

Invoke a single skill or agent directly:

  • Skill({ skill: "gerard:api-platform-filters" })
  • Task(subagent_type="api-platform-implementer", ...)

Or use one of the legacy/utility commands:

  • /brainstorm (pre-architecture brainstorming)
  • /write-plan, /execute-plan (manual plan/execute hors pipeline)
  • /symfony-check (quality gates)
  • /symfony-api-filters, /symfony-api-mcp, etc. (skill-specific)

Default workflow

  1. Read this skill (gerard:using-symfony-superpowers) — entry point.
  2. Decide pipeline vs atomic (see below).
  3. If pipeline → /api-resource-pipeline or /api-resource-ship.
  4. If atomic → use the relevant /symfony-api-* command or invoke the skill/agent directly.
  5. Refer to docs/symfony/pipeline-overview.md for full Mermaid.

When to use which mode

SituationRecommended
New API resource end-to-end/api-resource-pipeline
Refactor an existing resource (medium complexity)/api-resource-pipeline
Fix a bug (single file, one line)Atomic skill or direct edit
Bump a dependencyAtomic
Migrate from #[ApiFilter] to parameters: [QueryParameter]Skill({ skill: "gerard:api-platform-upgrade" }) then atomic edits
Ship a feature on a Friday evening, hands-off/api-resource-ship
Critical change you want to inspect/api-resource-pipeline (stops before commit)

Guardrails

  • /api-resource-ship only with passing prerequisites: clean working tree, .claude/settings.json denying --force/--no-verify.
  • State files are runtime, not source: .claude/last-api-*.md are gitignored.
  • Authority order: project CLAUDE.md > stage personas > project skills layer (<project>:X) > plugin canon (gerard:*).
  • Skill dispatch theatre is rejected: every claimed skill dispatch must have an actual Skill() / Task() call in the tool stream. The reviewer enforces.

Progressive disclosure

  • This file for the entry-point map
  • docs/symfony/pipeline-overview.md for the full pipeline architecture (Mermaid)
  • docs/symfony/agentic-personas.md for the 7 agents detailed
  • docs/symfony/state-files-protocol.md for .claude/last-api-*.md convention
  • docs/symfony/marker-protocol.md for ===STAGE-BEGIN=== format
  • docs/symfony/project-skills-pattern.md for the project skills layer pattern
  • docs/symfony/forensic-audit-template.md for the ship → measure → tighten loop
  • docs/symfony/api-platform-anti-patterns.md for the canonical anti-pattern catalog
  • skills-map.md for the full index of the 53 gerard:* skills (grouped by domain)
  • docs/complexity-tiers.md to adapt verbosity and granularity to project tier (Simple / Medium / Complex)

Output contract

  • A user that runs /architect "<story>" for the first time understands the next step.
  • A team adopting the plugin can configure their <project>:X overrides and .claude/settings.json correctly.

References

  • All docs/symfony/*.md
  • docs/complexity-tiers.md (project-tier playbook)
  • skills-map.md / skills-map-lite.md (skill index)
  • README.md (user-facing entry point)

Download now (ZIP)

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