DQIII8: Skill for Claude Code

.claude/skills/intl-reports/SKILL.md

intl-reports is a skill for Claude Code from senda-labs/DQIII8. It costs 53 tokens per session (2,349 once invoked), scanned A, original, MIT.

A Spanish-language batch workflow for producing internationalisation reports for small and medium-sized Spanish businesses. Internationalisation here means assessing how a business could expand into markets outside its home country.

In plain words
What is it for?
Use it to crawl company information and generate diagnostic and planning reports for international expansion.
Why use it?
It organizes a multi-stage reporting process across many companies and can resume unfinished work, reducing manual coordination in a large batch.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Claude Code.

This is senda-labs/DQIII8's own configuration. It tells Claude Code how to work on DQIII8 itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything DQIII8 configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is bash scripts/batch_run_tanda3.sh data/tanda3_run_ready.txt.

Part of the dqiii8 plugin — 22 skills, 14 commands, 17 agents shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to senda-labs/DQIII8. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/senda-labs/DQIII8/main/.claude/skills/intl-reports/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/senda-labs/DQIII8

Made for: Claude Code.

Or install dqiii8, the plugin that ships this one along with the rest of its 22 skills, 14 commands, 17 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for intl-reports

README.md
[![agentmods](https://agentmods.dev/badge/skills/senda-labs/dqiii8/intl-reports/github.svg)](https://agentmods.dev/skills/senda-labs/dqiii8/intl-reports)
Your own site
<a href="https://agentmods.dev/skills/senda-labs/dqiii8/intl-reports"><img src="https://agentmods.dev/badge/skills/senda-labs/dqiii8/intl-reports/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for intl-reports

Your own site · 80×15
<a href="https://agentmods.dev/skills/senda-labs/dqiii8/intl-reports"><img src="https://agentmods.dev/badge/skills/senda-labs/dqiii8/intl-reports.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,349 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00053 $0.02349
Opus 5 $0.00026 $0.01175
Sonnet 5 $0.00011 $0.00470
Haiku 4.5 $0.00005 $0.00235

Measured 12d ago against content hash edddf6c8e4e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

intl-reports scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/intl-reports/SKILL.md · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/intl-reports — Orquestador de Informes de Internacionalización

Proyecto en /root/dqiii8/my-projects/intl-reports/. CSV tanda3: data/3a tanda empresas 201 P&L 28 abril.csv (201 empresas).

Arquitectura

Orchestrator v4 (core.cli) = pipeline completo por empresa, vía claude --print subprocess. NUNCA lanzar desde Claude Code activo (CLAUDECODE=1 bloquea con error explícito). Siempre desde terminal/tmux externo:

env -u CLAUDECODE python3 -m core.cli run --slug {slug} --concurrency 6

Pipeline batch (modo producción)

# Batch secuencial desde tmux externo — NO desde Claude Code
bash scripts/batch_run_tanda3.sh data/tanda3_run_ready.txt

El script:

  1. Salta empresas con ambos DOCXs ya existentes (>500 KB c/u)
  2. Detecta estado parcial → resume; empresa fresh → run
  3. Para en exit 2 si detecta rate limit (reanudar después)
  4. Flags: --concurrency 6 --skip-brief

Waves del Orchestrator v4

Wave -2  crawler auto          skip si dossier < 30d
Wave -1  implications_brief    auto [Haiku], --skip-brief lo omite si ya existe
Wave  0  strategic + diag_intro + diag_areas×6   [8 en paralelo]
Wave  1  market_signals_layer + diag_conclusions
Wave  2  plan_body_org + plan_body_financial
Wave  3  plan_body_governance + plan_body_entry
Wave  4  plan_body_marketing
Wave  5  markets + plan_body_recommendations
Post     QA → auto_qa_fixer → DOCX → Telegram

Prerrequisitos por empresa (gate real del pipeline)

A. SABI_Export_*.xls         info-origin/              financiero (empleados, revenue)
B. raw_survey_data.json      info-origin/              cuestionario ANOVA (auto USIL)
C. ssot.json                 data/                     fuente canónica (reemplaza content_brief.json, eliminado en B7)
D. company_intelligence.json data/                     REQUERIDO para pasar ACIS gate (completeness ≥85%)
   └── generado por cobrowsing session:
       python3 scripts/cobrowsing_batch.py --slug-list data/tanda3_no_acis.txt
       (Chrome human-in-the-loop, CDP :9222, TUI interactiva)

Read the full file on GitHub · 201 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 201 lines · 53 tokens per session scan A edddf6c8e4e6

Subscribe to this mod's changes

intl-reports is a skill published in the GitHub repository senda-labs/DQIII8 (11 stars, last pushed 23d ago), licensed MIT. It adds 53 tokens to every session and 2,349 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories