Claude Skills by event4u-app

Run the skill-improvement pipeline after a learning was detected — capture, classify, create, validate, apply; explicit request only.

Use when condensing, decondenseing, refactoring, or improving existing skills. Covers the full skill lifecycle from verbose → sharp → maintained.

Use when reviewing, auditing, or optimizing skills — validates against the 7 Skill Killers checklist and produces fix recommendations.

Use when deciding 'should this be a skill or a rule?', creating/improving/reviewing agent skills, SKILL.md frontmatter, or procedure sections — even without saying 'skill-writing'.

Turn an audio track into a timed `## Scene N` script: song sections → per-scene durations, auto mode adds mood + lip-sync lines. Triggers 'music video', 'from the song', 'cut to the beat'.

Use BEFORE planning/coding against a DB schema, API/GraphQL shape, DTO/Model/Entity, or vendor package — read the real source, emit an Evidence Report, stop inventing fields.

Use when building or editing a spreadsheet or model — formulas over hardcoded values, read-back after writes, official-source data, pivot-first charts. Triggers on 'spreadsheet', 'build a model'.

Use when writing raw SQL — MariaDB/MySQL syntax, parameterization, raw migrations, seeders with `DB::statement`; fires even on a pasted query asking 'why is this slow'.

Use when stakeholders pull a decision in different directions — frames each lens, builds a trade-off matrix, surfaces the cost of every choice — even if the user just says 'PO and ops disagree'.

Use when you need this project's coding standards (line length, quotes, import order, naming, commit format) — derive them from the REAL tooling config as a pointer + digest, never a guessed claim.

Use when a component library needs a workshop — one story per concept, JSDoc summaries the manifest can carry, stories run as tests, and an opt-in MCP channel that replaces guessing with querying.

Use when orchestrating implementer/judge subagents — form gate + nine modes (do-and-judge ±two-stage, steps/parallel/worktrees, competitively, debate, live-app-judge, adversarial-council).

Before adding/installing any dependency the agent named — verify the package exists (slopsquatting: ~1 in 5 AI suggestions are hallucinated), isn't typo-adjacent, is pinned + locked, and CVE-scanned

Writes Symfony PHP — DI container, bundles, Doctrine, Messenger, Security voters, console commands. For Laravel / Eloquent / Artisan use `laravel`. For framework-free PHP use `php-coder`.

Use on a bug, test failure, crash, or unexpected behavior — enforce reproduce → isolate → hypothesize → verify before any fix; fires even on 'this is broken' / 'quick fix'.

Use when writing or reviewing Tailwind CSS — utility-first, design-token discipline, no inline-style drift, responsive variants, dark mode — even on 'style this' or 'mach das hübsch'.

Use when the user says \"write a spec\", \"create RFC\", \"write a PRD\", or \"document this decision\". Writes technical specifications, PRDs, RFCs, and ADRs with clear structure.

Use when writing Terraform — AWS modules, resources, variables, outputs, remote state — even when the user just says 'provision this infra' or 'add an S3 bucket' without naming Terraform.

Use when working with Terragrunt — DRY multi-env configs, module dependencies, remote state orchestration — even when the user just says 'deploy this to staging and prod' without naming Terragrunt.

Use BEFORE writing any test — enumerate cases per behavior (happy / boundary / error / abuse), prioritize by likelihood × impact, cross-check via subagent — even if the user just says 'add tests'.

Implementing a feature, fixing a bug, refactoring — failing test first, then the code. For a WRONG test, `testing-anti-patterns` wins.

BEFORE writing/changing tests, mocks, or test-only methods on production classes — mocking-the-mock, production pollution, overfit assertions; for order, `test-driven-development` wins.

Use when adding auth, webhooks, uploads, queues, secrets, tenant boundaries, or public endpoints — produces trust boundaries + abuse cases mapped to files, BEFORE implementation.

Use BEFORE any verbose CLI run, large file read, doc conversion, or near-context handoff — decision tree keyed by intent citing the canonical token-saving asset.

Derive a type system from a style constraint — font pairings, scale/line-height/weights, DTCG tokens via design-tokens. Use to choose fonts or build a typographic scale.

Use when implementing a UI brief on a stack with no framework executor — Svelte, Astro, Angular, plain HTML. Carries the stack-independent contract; idiom comes from the stack corpus.

Use when shaping a UI component tree — composition vs inheritance, slot patterns, prop API design, controlled vs uncontrolled, polymorphic — even on 'split this component'.

Deep multi-pass codebase audit — orchestrates project-analysis-core plus the framework-specific project-analysis-*; explicit request only. Single-pass scan → project-analyzer.

Use when a learning, new skill, rule improvement, or bug fix from a consumer project should be contributed back to the shared agent-config package.

When starting parallel work in isolation from the current branch — spawn a git worktree with ignore-safety checks and a clean test baseline — even when the user says 'try this on the side'.

Validate whether a feature request fits the existing codebase — check for duplicates, contradictions, scope creep, and architectural misfit

Use when claiming 'done', suggesting a commit, push, or PR — runs the evidence gate so completion claims come from fresh output in this message, not memory or earlier runs.

Use to iterate a change until tests/quality checks pass — bounded run→revise→re-run gated by a numeric threshold, then a judge confirms. Triggers 'iterate to green', 'keep fixing until tests pass'.

Use when a live-action beat becomes the 11-block cinematic prompt — lens, lighting, negatives. Triggers 'cinematic prompt', 'film-grade scene'. Animated → pixar-storyteller; 12-block → scene-expander.

Explore a flow or layout with 3+ disposable lo-fi greyscale wireframes on a named axis, before any hi-fi work. Use when the user wants to sketch directions or explore structure.

Use when a cross-workspace import will not resolve — cannot find module @org/*, TS2307 — to link the packages properly with the workspace: protocol instead of patching tsconfig paths.

Use when governing a worktree across its whole life — scope-lock declaration, merge-readiness status, scoped verification, and safe cleanup that refuses while unique unmerged commits exist.

Links that must all be legal: - same pack: [helper](../fx-alpha-helper/SKILL.md) - declared requires (fx-alpha -> fx-beta): [tool](../fx-beta-tool/SKILL.md) - always-installed core: [shared](../fx-core-shared/SKILL.md)

Leaf. No outbound links, so it cannot create a boundary violation of its own.

Leaf. No outbound links, so it cannot create a boundary violation of its own.

Leaf. No outbound links, so it cannot create a boundary violation of its own.

Seeds exactly one violation. The overlay drops the `fx-alpha -> fx-beta` requires edge from `packs.yml` (see the twin's `packs.yml`), so the link below now crosses a boundary the source pack does not declare — dead the moment a consumer installs `fx-alpha` without `fx-beta`. - still legal, same pack: [helper](../fx-alpha-helper/SKILL.md) - still legal, always installed: [shared](../fx-core-shared/SKILL.md) - **the seeded violation**: [tool](../fx-beta-tool/SKILL.md)

The cross-pack link is REMOVED here so this twin does not also red `lint_pack_boundaries` — the requires edge it drops would otherwise make the conformant link illegal too, and the twin would red two gates instead of one. - same pack: [helper](../fx-alpha-helper/SKILL.md) - always installed: [shared](../fx-core-shared/SKILL.md)