Ejecuta cualquier Skill en Manus
con un clic

Ejecuta cualquier Skill en Manus con un clic

smaqit-utils-read-pdf

Estrellas2

Forks1

Actualizado20 de julio de 2026 a las 13:03

Extracts text from a PDF file, writes a sidecar .extracted.txt file, reads it, and continues with the caller's original goal. Use when the user references a .pdf file path and requests any content-based action: review, summarize, analyze, benchmark extraction, or similar.

Instalación

Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.

Ejecutar en Manus

Fuente

ruifrvaz

ruifrvaz/smaqit

Abrir repositorio de GitHub Ver repositorios del creador

Descarga

Ejecutar en Manus

Ocupaciones relacionadasSOC

Basado en la clasificación ocupacional SOC

Editores de escritorioOficina y apoyo administrativo·SOC 43-9031

Explorador de archivos

2 archivos

SKILL.md

readonly

name	smaqit.utils.read-pdf
description	Extracts text from a PDF file, writes a sidecar .extracted.txt file, reads it, and continues with the caller's original goal. Use when the user references a .pdf file path and requests any content-based action: review, summarize, analyze, benchmark extraction, or similar.

Read PDF

When to use this skill

User references a .pdf file path and requests a content-based action (review, summarize, analyze, benchmark extraction, or similar)
Agent detects a .pdf path in the conversation and the task requires reading its content

Steps

Step 1: Run extraction script

Run scripts/extract.sh <pdf-path> via terminal:

bash .claude/skills/smaqit.utils.read-pdf/scripts/extract.sh "<pdf-path>"

If pdftotext is not installed, the script prints sudo apt install poppler-utils and exits 1. Surface this instruction to the user and stop.
If the PDF is not found, the script exits 1 with the attempted path. Report the error to the user and stop.
If the extracted text is empty, the script exits 1 with the message Extracted text is empty — PDF may be image-only or protected. Report this to the user and stop.
On success, the script prints the sidecar path to stdout (e.g., /path/to/file.extracted.txt).

Step 2: Read the sidecar path from terminal output

Read the last line of stdout from Step 1. That line is the absolute or relative path to the sidecar file.

Step 3: Read the sidecar file

Read the file at the path captured in Step 2 in full, without truncation.

Step 4: Continue with the caller's original goal

Apply the user's intent (review, summarize, analyze, etc.) to the extracted content. Do not stop after extraction — extraction is a pipeline step, not the final output.

Output

<pdf-basename>.extracted.txt — plain text sidecar written next to the source PDF
Continuation of the caller's original task using the extracted content

Scope

Single file only — multi-PDF support is out of scope for v0.1.0
Sidecar is always written next to the source PDF (no /tmp/ unless user specifies)
The skill does not post-process or format the extracted text — it surfaces it for the caller's goal
Does not create agents, framework files, or templates

Completion Criteria

extract.sh ran without error
Sidecar .extracted.txt file exists next to the source PDF
Sidecar file content was read in full
Caller's original goal was addressed using the extracted content

Failure Handling

Situation	Action
`pdftotext` not installed	Script prints `sudo apt install poppler-utils` and exits 1; surface install instruction to user and stop
PDF file not found	Script exits 1 with the attempted path; report error to user and stop
PDF is unreadable or corrupted	Script exits 1; report failure to user and stop
Sidecar output is empty	Script exits 1 with message "Extracted text is empty — PDF may be image-only or protected"; report to user and stop
Sidecar file already exists	Overwrite silently (idempotent re-runs)

Más de este repositorio

mismo repositorio

smaqit-create-agent

ruifrvaz/smaqit

Creates a new agent for this project. Use when the user asks to create, define, or build a new custom agent.

2026-07-232

smaqit-create-skill

ruifrvaz/smaqit

Use when the user wants to create, define, build, or package a new skill — including when they ask to turn a workflow into a reusable command, wrap domain knowledge into a slash-command, or describe a repeatable procedure they want Copilot to follow. Gathers name and purpose, infers a complete specification, writes a definition file, and invokes smaqit.L2 to compile a SKILL.md file.

2026-07-232

smaqit-feature-deploy

ruifrvaz/smaqit

Use when deploying a feature to an existing project's production environment through its already-proven CI/CD pipeline. Reads specs to identify the stack, target, and provisioning mode before any infrastructure work. Handles all three provisioning_mode branches (provision, existing-owned, existing-shared) with infrastructure readiness, CI/CD-triggered deploy, verification, amendment gate, and optional release tagging. No dev-VM sweep, no deploy-rsync skills — the Nth deploy on infrastructure already proven. Also use when the user says "deploy this", "push to production", "ship this feature", or asks to deploy to a project that already has CI/CD workflows from its initial greenfield run.

2026-07-232

smaqit-infrastructure-vault-loader

ruifrvaz/smaqit

Use before any local deployment or credential operation that requires secrets from a local HashiCorp Vault instance. Verifies Vault is running, unsealed, and authenticated on 127.0.0.1:8200. Also runs an interactive credential loader script that prompts for all project secrets and writes them to Vault. Use for first-time setup, adding a new project's credentials, or when a Vault path is missing. Also use when setting up Vault for the first time on a new machine, or when a caller cannot reach Vault and needs troubleshooting guidance.

2026-07-232

smaqit-infrastructure-provision-cyso

ruifrvaz/smaqit

Use when provisioning cloud infrastructure for a project's target application on Cyso Cloud (OpenStack) using Terraform. Covers application credential sourcing, Object Storage backend initialization, SSH keypair variable configuration, `terraform init/plan/apply`, and fixed IP retrieval. Produces a running Cyso VM accessible via SSH, with Cinder data volume attached and security group configured on ports 22/80/443. Also use when re-running Terraform after infrastructure changes or when an operator invokes `/provision.cyso`.

2026-07-232

smaqit-infrastructure-repo-config

ruifrvaz/smaqit

Use when configuring a GitHub repository with the secrets and variables required for CI/CD workflows. Covers Actions secrets (VM_SSH_KEY, Terraform backend credentials, cloud provider credentials, GH_TERRAFORM_TOKEN) and Actions variables (VM_HOST, DEMO_MODE). Uses the `gh` CLI. Prevents GITHUB_TOKEN reserved-name collisions and SSH key trailing-newline drift. Also use when setting up a new deployment repository, rotating CI/CD credentials, or verifying that all required repository secrets and variables are present.

2026-07-232

name	smaqit.utils.read-pdf
description	Extracts text from a PDF file, writes a sidecar .extracted.txt file, reads it, and continues with the caller's original goal. Use when the user references a .pdf file path and requests any content-based action: review, summarize, analyze, benchmark extraction, or similar.

Read PDF

When to use this skill

User references a .pdf file path and requests a content-based action (review, summarize, analyze, benchmark extraction, or similar)
Agent detects a .pdf path in the conversation and the task requires reading its content

Steps

Step 1: Run extraction script

Run scripts/extract.sh <pdf-path> via terminal:

bash .claude/skills/smaqit.utils.read-pdf/scripts/extract.sh "<pdf-path>"

If pdftotext is not installed, the script prints sudo apt install poppler-utils and exits 1. Surface this instruction to the user and stop.
If the PDF is not found, the script exits 1 with the attempted path. Report the error to the user and stop.
If the extracted text is empty, the script exits 1 with the message Extracted text is empty — PDF may be image-only or protected. Report this to the user and stop.
On success, the script prints the sidecar path to stdout (e.g., /path/to/file.extracted.txt).

Step 2: Read the sidecar path from terminal output

Read the last line of stdout from Step 1. That line is the absolute or relative path to the sidecar file.

Step 3: Read the sidecar file

Read the file at the path captured in Step 2 in full, without truncation.

Step 4: Continue with the caller's original goal

Apply the user's intent (review, summarize, analyze, etc.) to the extracted content. Do not stop after extraction — extraction is a pipeline step, not the final output.

Output

<pdf-basename>.extracted.txt — plain text sidecar written next to the source PDF
Continuation of the caller's original task using the extracted content

Scope

Single file only — multi-PDF support is out of scope for v0.1.0
Sidecar is always written next to the source PDF (no /tmp/ unless user specifies)
The skill does not post-process or format the extracted text — it surfaces it for the caller's goal
Does not create agents, framework files, or templates

Completion Criteria

extract.sh ran without error
Sidecar .extracted.txt file exists next to the source PDF
Sidecar file content was read in full
Caller's original goal was addressed using the extracted content

Failure Handling

Situation	Action
`pdftotext` not installed	Script prints `sudo apt install poppler-utils` and exits 1; surface install instruction to user and stop
PDF file not found	Script exits 1 with the attempted path; report error to user and stop
PDF is unreadable or corrupted	Script exits 1; report failure to user and stop
Sidecar output is empty	Script exits 1 with message "Extracted text is empty — PDF may be image-only or protected"; report to user and stop
Sidecar file already exists	Overwrite silently (idempotent re-runs)