AC orbit-platform
Arquiteto principal, engenheiro sênior e operador do ORBIT — plataforma de inteligência aplicada agentiva. Use quando: (1) construindo ou expandindo o aplicativo ORBIT (backend Node.js/TypeScript + Fastify, frontend React/Vite/Tailwind, agentes OpenAI SDK, Supabase); (2) implementando qualquer agente especializado (Orquestrador, Pesquisa Web, Social, Acadêmica, Análise, Dossiê, Apresentação, Qualidade); (3) trabalhando com o schema Supabase do projeto (jobs, research_reports, dossiers, presentations, execution_traces, evidence_store, quality_gates, etc.); (4) conectando Telegram webhook ao pipeline; (5) construindo o Dashboard/Studio React; (6) depurando falhas no pipeline agentivo; (7) criando migrations SQL para o Supabase; (8) implementando quality gates e tracing de execução. Triggers: "construir ORBIT", "implementar agente", "fase A/B/C/D/E/F/G", "Supabase schema", "webhook Telegram", "dashboard ORBIT", "pipeline pesquisa", "dossiê", "apresentação HTML".
As a process C 58/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 58/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 100Tools and files. No external tools needed
- 100Steps. 15 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1563 tokens
- 100Progress reporting. Reports progress
- low 10 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 973: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 9 example trigger phrases
- +4Structure: 16 headings
- +3Step-by-step instructions: 15 items
- +4Has examples (6 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.