FX-Studio-AI

v8.19.3 (2026-07-01, PATCH — arm-classifier: keyword-inferred read-only runs no longer arm [recurring phantom-arm deadlock fix]): a natural-language review/audit/analysis request ('faça revisão adversarial', 'faça uma auditoria', 'análise') was classified FULL/Audit and armed the pipeline-arm-pending marker — but read-only work never opens an exec window, so it hit INLINE_WORK_BLOCKED, aborted, and left an orphan marker that bricked the next task with PIPELINE_NOT_ARMED (observed live in interview-coach 2026-06-30 and 07-01). FIX: lib/pipeline-arm.cjs::writeArmPending now also skips arming for the read-only TYPES (Audit, UX Simulation) when they were INFERRED FROM KEYWORDS (source kw:), while an EXPLICIT --audit/--ux flag stays a deliberate governed run and still arms (preserving the STEP_1_7 direct-entry evidence, v8.16.0). Safe direction per the documented arm trade-off: a missed arm is recoverable (re-invoke); a phantom arm deadlocks. TDD tests/regression/v8.19.3/F1-readonly-types-no-arm (RED 4-fail → GREEN); 2 deliberate v8.7.0 pins updated to the --audit-flag path. Iron Law: only lib/pipeline-arm.cjs + tests/ touched; Gates/Registry UNTOUCHED; no .codex mirror. Suite 252/5 (5 pre-existing Langfuse/env/F4). Lockstep across all version surfaces. v8.19.2 (2026-07-01, PATCH — edit-guard-hook robustness [Cursor-crash hardening, Claude-Code-scoped]): the PreToolUse edit-guard no longer crashes into the opaque external catch ('edit-guard-hook internal error — failing closed') when .pipeline/sessions is present-but-unreadable (a file where a dir is expected → ENOTDIR/EACCES) — getActiveLock + getActiveExecWindow now guard readdirSync and return null instead of throwing, and the CLI external catch surfaces the REAL sanitized error (single-line, printable-ASCII, capped 200) instead of the opaque message, so a genuine failure stays fail-closed but debuggable. Posture UNCHANGED (still deny when the guard cannot evaluate); NO foreign tool-name vocabulary added — cross-runti

45 skills · 15 commands · hooks

Claude Code Swiss Army Knife — diagnose, configure, and build your Claude Code environment. Meta-skill /cc with triage menu + 9 specialized skills for context audit, MCP, hooks, agents, prompts, security, setup, and skill building.

11 skills · 1 command · hooks

Intelligent toolchain orchestrator for Claude Code — recommends skills, plugins, MCPs, and agents for any task with dependency-aware ordering. v0.5.1: dependency bump (@huggingface/transformers ^4.0.1 → ^4.1.0) + README polish. v0.5.0: architectural overhaul closing 10-finding audit. Hot-path hook 387→85 lines via lib/advisor-nudge-core extraction; 4 architectural guards CI-enforced (DI-1 module-load purity, DI-2 layered dependency direction, DI-3 manifest version coherence, vault env single source); module-scoped mtime+size cache for embeddings/graph; unified filesystem walker; 812 tests (+24% from 654). BREAKING (restorable): default prompt-length threshold 5→12 chars; restore via ADVISOR_PROMPT_LENGTH=5. Deprecation runway through 0.6.0 for SKILL_ADVISOR_VAULT (use SKILL_ADVISOR_VAULT_PATH) and build-index.inferCategory re-export.

3 skills · 7 commands · 2 agents · hooks

Generates mandatory engineering rules, architecture contracts, anti-pattern catalogs, and validation tests adapted to any project's stack. 6 focused skills: setup, detect-stack, map-architecture, generate-rules, mine-anti-patterns, validate-context.

6 skills · 6 commands

Text-to-speech offline em portugues do Brasil para Claude Code. Hook Stop sintetiza audio do output do agente via Kokoro local (neural, voz feminina pf_dora) com pre-processamento que strippa codigo, paths e markdown antes de virar fala. Sem API key, sem limite (apos setup inicial). Windows 11 + PowerShell 7. Changelog completo em CHANGELOG.md no repo.