Skill · em Construir backend e dados

pudu-task-telemetry

Measure local AI task latency, token usage, errors and verified outcomes using Pudu AI hardware evidence and installed Ollama models. Use when comparing local task runs, choosing a local model for a bounded subtask, or recording reproducible task telemetry.

Procedência

Origem: davila7/claude-code-templates
Caminho: cli-tool/components/skills/development/pudu-task-telemetry
Versão fixada: 57f899e5394bb8ca166f38eacae8f0853cbfe033
Licença: MIT
Espelhado em 25/09/2026
nenhum download no Claude Code Templates (lido em 25/09/2026)

Antes de instalar

14 arquivos · 73,4 KB · inclui 8 scripts que executam: scripts/lib/common.mjs, scripts/lib/model-selection.mjs, scripts/lib/ollama-adapter.mjs, scripts/lib/pudu-adapter.mjs, scripts/lib/report.mjs, scripts/lib/task-store.mjs, scripts/lib/telemetry.mjs, scripts/pudu-task.mjs

Instalar na sua CLI

O comando baixa a versão fixada (commit 57f899e) direto da origem, para a pasta que a CLI lê. Precisa de curl (macOS e Linux); no Windows não há comando, porque o Rook Labs é para macOS.

Claude Code

Neste projeto: instala em .claude/skills/pudu-task-telemetry/.

d=".claude/skills/pudu-task-telemetry"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/development/pudu-task-telemetry"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/references/examples.md" "$u/references/examples.md" \
  -o "$d/references/model-selection.md" "$u/references/model-selection.md" \
  -o "$d/references/setup.md" "$u/references/setup.md" \
  -o "$d/references/task-schema.json" "$u/references/task-schema.json" \
  -o "$d/references/telemetry-contract.md" "$u/references/telemetry-contract.md" \
  -o "$d/scripts/lib/common.mjs" "$u/scripts/lib/common.mjs" \
  -o "$d/scripts/lib/model-selection.mjs" "$u/scripts/lib/model-selection.mjs" \
  -o "$d/scripts/lib/ollama-adapter.mjs" "$u/scripts/lib/ollama-adapter.mjs" \
  -o "$d/scripts/lib/pudu-adapter.mjs" "$u/scripts/lib/pudu-adapter.mjs" \
  -o "$d/scripts/lib/report.mjs" "$u/scripts/lib/report.mjs" \
  -o "$d/scripts/lib/task-store.mjs" "$u/scripts/lib/task-store.mjs" \
  -o "$d/scripts/lib/telemetry.mjs" "$u/scripts/lib/telemetry.mjs" \
  -o "$d/scripts/pudu-task.mjs" "$u/scripts/pudu-task.mjs"

Global: instala em ~/.claude/skills/pudu-task-telemetry/.

d="$HOME/.claude/skills/pudu-task-telemetry"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/development/pudu-task-telemetry"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/references/examples.md" "$u/references/examples.md" \
  -o "$d/references/model-selection.md" "$u/references/model-selection.md" \
  -o "$d/references/setup.md" "$u/references/setup.md" \
  -o "$d/references/task-schema.json" "$u/references/task-schema.json" \
  -o "$d/references/telemetry-contract.md" "$u/references/telemetry-contract.md" \
  -o "$d/scripts/lib/common.mjs" "$u/scripts/lib/common.mjs" \
  -o "$d/scripts/lib/model-selection.mjs" "$u/scripts/lib/model-selection.mjs" \
  -o "$d/scripts/lib/ollama-adapter.mjs" "$u/scripts/lib/ollama-adapter.mjs" \
  -o "$d/scripts/lib/pudu-adapter.mjs" "$u/scripts/lib/pudu-adapter.mjs" \
  -o "$d/scripts/lib/report.mjs" "$u/scripts/lib/report.mjs" \
  -o "$d/scripts/lib/task-store.mjs" "$u/scripts/lib/task-store.mjs" \
  -o "$d/scripts/lib/telemetry.mjs" "$u/scripts/lib/telemetry.mjs" \
  -o "$d/scripts/pudu-task.mjs" "$u/scripts/pudu-task.mjs"

Codex

Neste projeto: instala em .agents/skills/pudu-task-telemetry/.

d=".agents/skills/pudu-task-telemetry"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/development/pudu-task-telemetry"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/references/examples.md" "$u/references/examples.md" \
  -o "$d/references/model-selection.md" "$u/references/model-selection.md" \
  -o "$d/references/setup.md" "$u/references/setup.md" \
  -o "$d/references/task-schema.json" "$u/references/task-schema.json" \
  -o "$d/references/telemetry-contract.md" "$u/references/telemetry-contract.md" \
  -o "$d/scripts/lib/common.mjs" "$u/scripts/lib/common.mjs" \
  -o "$d/scripts/lib/model-selection.mjs" "$u/scripts/lib/model-selection.mjs" \
  -o "$d/scripts/lib/ollama-adapter.mjs" "$u/scripts/lib/ollama-adapter.mjs" \
  -o "$d/scripts/lib/pudu-adapter.mjs" "$u/scripts/lib/pudu-adapter.mjs" \
  -o "$d/scripts/lib/report.mjs" "$u/scripts/lib/report.mjs" \
  -o "$d/scripts/lib/task-store.mjs" "$u/scripts/lib/task-store.mjs" \
  -o "$d/scripts/lib/telemetry.mjs" "$u/scripts/lib/telemetry.mjs" \
  -o "$d/scripts/pudu-task.mjs" "$u/scripts/pudu-task.mjs"

Global: instala em ~/.agents/skills/pudu-task-telemetry/.

d="$HOME/.agents/skills/pudu-task-telemetry"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/development/pudu-task-telemetry"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/references/examples.md" "$u/references/examples.md" \
  -o "$d/references/model-selection.md" "$u/references/model-selection.md" \
  -o "$d/references/setup.md" "$u/references/setup.md" \
  -o "$d/references/task-schema.json" "$u/references/task-schema.json" \
  -o "$d/references/telemetry-contract.md" "$u/references/telemetry-contract.md" \
  -o "$d/scripts/lib/common.mjs" "$u/scripts/lib/common.mjs" \
  -o "$d/scripts/lib/model-selection.mjs" "$u/scripts/lib/model-selection.mjs" \
  -o "$d/scripts/lib/ollama-adapter.mjs" "$u/scripts/lib/ollama-adapter.mjs" \
  -o "$d/scripts/lib/pudu-adapter.mjs" "$u/scripts/lib/pudu-adapter.mjs" \
  -o "$d/scripts/lib/report.mjs" "$u/scripts/lib/report.mjs" \
  -o "$d/scripts/lib/task-store.mjs" "$u/scripts/lib/task-store.mjs" \
  -o "$d/scripts/lib/telemetry.mjs" "$u/scripts/lib/telemetry.mjs" \
  -o "$d/scripts/pudu-task.mjs" "$u/scripts/pudu-task.mjs"

Antigravity

Neste projeto: instala em .agents/skills/pudu-task-telemetry/.

d=".agents/skills/pudu-task-telemetry"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/development/pudu-task-telemetry"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/references/examples.md" "$u/references/examples.md" \
  -o "$d/references/model-selection.md" "$u/references/model-selection.md" \
  -o "$d/references/setup.md" "$u/references/setup.md" \
  -o "$d/references/task-schema.json" "$u/references/task-schema.json" \
  -o "$d/references/telemetry-contract.md" "$u/references/telemetry-contract.md" \
  -o "$d/scripts/lib/common.mjs" "$u/scripts/lib/common.mjs" \
  -o "$d/scripts/lib/model-selection.mjs" "$u/scripts/lib/model-selection.mjs" \
  -o "$d/scripts/lib/ollama-adapter.mjs" "$u/scripts/lib/ollama-adapter.mjs" \
  -o "$d/scripts/lib/pudu-adapter.mjs" "$u/scripts/lib/pudu-adapter.mjs" \
  -o "$d/scripts/lib/report.mjs" "$u/scripts/lib/report.mjs" \
  -o "$d/scripts/lib/task-store.mjs" "$u/scripts/lib/task-store.mjs" \
  -o "$d/scripts/lib/telemetry.mjs" "$u/scripts/lib/telemetry.mjs" \
  -o "$d/scripts/pudu-task.mjs" "$u/scripts/pudu-task.mjs"

Global: instala em ~/.gemini/antigravity-cli/skills/pudu-task-telemetry/.

d="$HOME/.gemini/antigravity-cli/skills/pudu-task-telemetry"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/development/pudu-task-telemetry"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/references/examples.md" "$u/references/examples.md" \
  -o "$d/references/model-selection.md" "$u/references/model-selection.md" \
  -o "$d/references/setup.md" "$u/references/setup.md" \
  -o "$d/references/task-schema.json" "$u/references/task-schema.json" \
  -o "$d/references/telemetry-contract.md" "$u/references/telemetry-contract.md" \
  -o "$d/scripts/lib/common.mjs" "$u/scripts/lib/common.mjs" \
  -o "$d/scripts/lib/model-selection.mjs" "$u/scripts/lib/model-selection.mjs" \
  -o "$d/scripts/lib/ollama-adapter.mjs" "$u/scripts/lib/ollama-adapter.mjs" \
  -o "$d/scripts/lib/pudu-adapter.mjs" "$u/scripts/lib/pudu-adapter.mjs" \
  -o "$d/scripts/lib/report.mjs" "$u/scripts/lib/report.mjs" \
  -o "$d/scripts/lib/task-store.mjs" "$u/scripts/lib/task-store.mjs" \
  -o "$d/scripts/lib/telemetry.mjs" "$u/scripts/lib/telemetry.mjs" \
  -o "$d/scripts/pudu-task.mjs" "$u/scripts/pudu-task.mjs"

Peça ao Rook

Já usa o Rook Labs? Cole no chat do Rook: instale a skill https://rooklabs.sh/marketplace/cct.pudu-task-telemetry

Prévia do SKILL.md

---
name: pudu-task-telemetry
description: Measure local AI task latency, token usage, errors and verified outcomes using Pudu AI hardware evidence and installed Ollama models. Use when comparing local task runs, choosing a local model for a bounded subtask, or recording reproducible task telemetry.
license: MIT
tags: [pudu-ai, ollama, local-models, task-telemetry, benchmarking]
---

# Pudu Task Telemetry

Use Pudu AI to inspect hardware and benchmark evidence, execute a bounded text
subtask through local Ollama, and report measurements with their provenance.
This skill captures its own local calls; it does not observe all activity or
change the model of the host assistant.

## 1. Diagnose

Locate this skill's `scripts/pudu-task.mjs` relative to this file. Examples assume
project installation under `.claude/skills/pudu-task-telemetry/`. Run from the
project root, or supply `--repo` explicitly.

```bash
node .claude/skills/pudu-task-telemetry/scripts/pudu-task.mjs doctor --repo . --json
```

Requires Node.js >=20, Pudu AI on PATH, and a running Ollama server. Diagnose
missing dependencies without installing packages, downloading models, or changing
global settings. Read [setup.md](references/setup.md) for configuration and the
separate server-side local-only prerequisite. A loopback URL alone does not
prove that the server cannot forward a request to cloud inference.

## 2. Select a model

```bash
node .claude/skills/pudu-task-telemetry/scripts/pudu-task.mjs recommend --repo . --task-kind code-summary --context-budget 4096 --json
```

Prefer installed models that fit the task's context and hardware. A Pudu hardware
score is not a quality score. Without a comparable verified suite, recommendations
return `needs_selection`; select a model explicitly for a pilot. Read
[model-selection.md](references/model-selection.md) before using `--model auto`
…

Ver todo o marketplace