Pp Firecrawl — Workflow

Overview

How the pp-firecrawl skill works, step by step.

Source Workflow

Codex skill workflow.

Step-by-step Workflow

Firecrawl — Printing Press CLI

Prerequisites: Install the CLI

This skill drives the firecrawl-pp-cli binary. You must verify the CLI is installed before invoking any command from this skill. If it is missing, install it first:

1. Install via the Printing Press installer:

   npx -y @mvanhorn/printing-press install firecrawl --cli-only
   

2. Verify: firecrawl-pp-cli --version
3. Ensure $GOPATH/bin (or $HOME/go/bin) is on $PATH.

If the npx install fails (no Node, offline, etc.), fall back to a direct Go install (requires Go 1.26.3 or newer):

go install github.com/mvanhorn/printing-press-library/library/developer-tools/firecrawl/cmd/firecrawl-pp-cli@latest

If --version reports "command not found" after install, the install step did not put the binary on $PATH. Do not proceed with skill commands until verification succeeds.

Command Reference

batch — Manage batch

• firecrawl-pp-cli batch cancel-scrape — Cancel a batch scrape job
• firecrawl-pp-cli batch get-scrape-errors — Get the errors of a batch scrape job
• firecrawl-pp-cli batch get-scrape-status — Get the status of a batch scrape job
• firecrawl-pp-cli batch scrape-and-extract-from-urls — Scrape multiple URLs and optionally extract information using an LLM

crawl — Manage crawl

• firecrawl-pp-cli crawl cancel — Cancel a crawl job
• firecrawl-pp-cli crawl get-active — Get all active crawls for the authenticated team
• firecrawl-pp-cli crawl get-status — Get the status of a crawl job
• firecrawl-pp-cli crawl urls — Crawl multiple URLs based on options

deep-research — Manage deep research

• firecrawl-pp-cli deep-research get-status — Get the status and results of a deep research operation
• firecrawl-pp-cli deep-research start — Start a deep research operation on a query

extract — Manage extract

• firecrawl-pp-cli extract data — Extract structured data from pages using LLMs
• firecrawl-pp-cli extract get-status — Get the status of an extract job

firecrawl-search — Manage firecrawl search

• firecrawl-pp-cli firecrawl-search — Search and optionally scrape search results

llmstxt — Manage llmstxt

• firecrawl-pp-cli llmstxt generate-llms-txt — Generate LLMs.txt for a website
• firecrawl-pp-cli llmstxt get-llms-txt-status — Get the status and results of an LLMs.txt generation job

map — Manage map

• firecrawl-pp-cli map — Map multiple URLs based on options

scrape — Manage scrape

• firecrawl-pp-cli scrape — Scrape a single URL and optionally extract information using an LLM

team — Manage team

• firecrawl-pp-cli team get-credit-usage — Get remaining credits for the authenticated team
• firecrawl-pp-cli team get-token-usage — Get remaining tokens for the authenticated team (Extract only)

Finding the right command

When you know what you want to do but not which command does it, ask the CLI directly:

firecrawl-pp-cli which "<capability in your own words>"

which resolves a natural-language capability query to the best matching command from this CLI's curated feature index. Exit code 0 means at least one match; exit code 2 means no confident match — fall back to --help or use a narrower query.

Auth Setup

Store your access token:

firecrawl-pp-cli auth set-token YOUR_TOKEN_HERE

Or set FIRECRAWL_BEARER_AUTH as an environment variable.

Run firecrawl-pp-cli doctor to verify setup.

Agent Mode

Add --agent to any command. Expands to: --json --compact --no-input --no-color --yes.

• Pipeable — JSON on stdout, errors on stderr

• Filterable — --select keeps a subset of fields. Dotted paths descend into nested structures; arrays traverse element-wise. Critical for keeping context small on verbose APIs:

  firecrawl-pp-cli batch cancel-scrape mock-value --agent --select id,name,status
  

• Previewable — --dry-run shows the request without sending

• Offline-friendly — sync/search commands can use the local SQLite store when available

• Non-interactive — never prompts, every input is a flag

Response envelope

Commands that read from the local store or the API wrap output in a provenance envelope:

{
  "meta": {"source": "live" | "local", "synced_at": "...", "reason": "..."},
  "results": <data>
}

Parse .results for data and .meta.source to know whether it's live or local. A human-readable N results (live) summary is printed to stderr only when stdout is a terminal — piped/agent consumers get pure JSON on stdout.

Agent Feedback

When you (or the agent) notice something off about this CLI, record it:

firecrawl-pp-cli feedback "the --since flag is inclusive but docs say exclusive"
firecrawl-pp-cli feedback --stdin < notes.txt
firecrawl-pp-cli feedback list --json --limit 10

Entries are stored locally at ~/.firecrawl-pp-cli/feedback.jsonl. They are never POSTed unless FIRECRAWL_FEEDBACK_ENDPOINT is set AND either --send is passed or FIRECRAWL_FEEDBACK_AUTO_SEND=true. Default behavior is local-only.

Write what surprised you, not a bug report. Short, specific, one line: that is the part that compounds.

Output Delivery

Every command accepts --deliver <sink>. The output goes to the named sink in addition to (or instead of) stdout, so agents can route command results without hand-piping. Three sinks are supported:

Unknown schemes are refused with a structured error naming the supported set. Webhook failures return non-zero and log the URL + HTTP status on stderr.

Named Profiles

A profile is a saved set of flag values, reused across invocations. Use it when a scheduled agent calls the same command every run with the same configuration - HeyGen's "Beacon" pattern.

firecrawl-pp-cli profile save briefing --json
firecrawl-pp-cli --profile briefing batch cancel-scrape mock-value
firecrawl-pp-cli profile list --json
firecrawl-pp-cli profile show briefing
firecrawl-pp-cli profile delete briefing --yes

Explicit flags always win over profile values; profile values win over defaults. agent-context lists all available profiles under available_profiles so introspecting agents discover them at runtime.

Exit Codes

Argument Parsing

Parse $ARGUMENTS:

1. Empty, help, or --help → show firecrawl-pp-cli --help output
2. Starts with install → ends with mcp → MCP installation; otherwise → see Prerequisites above
3. Anything else → Direct Use (execute as CLI command with --agent)

MCP Server Installation

1. Install the MCP server:

   go install github.com/mvanhorn/printing-press-library/library/other/firecrawl-pp-cli/cmd/firecrawl-pp-mcp@latest
   

2. Register with Claude Code:

   claude mcp add firecrawl-pp-mcp -- firecrawl-pp-mcp
   

3. Verify: claude mcp list

Direct Use

1. Check if installed: which firecrawl-pp-cli If not found, offer to install (see Prerequisites at the top of this skill).
2. Match the user query to the best command from the Unique Capabilities and Command Reference above.
3. Execute with the --agent flag:

   firecrawl-pp-cli <command> [subcommand] [args] --agent
   

4. If ambiguous, drill into subcommand help: firecrawl-pp-cli <command> --help.

Execution Logic

The skill executes when its trigger fires (slash command, natural-language match, or direct invocation). It reads its references, applies its rules, and produces the documented outputs.

Edge Cases

See the source skill's references/ and scripts/ folders for edge-case handling.

Failure Handling

A skill failure surfaces as a tool error or a partial output; never a silent skip. Re-run with --verbose (where applicable) for diagnostics.

Integration Notes

• Claude — invoked via the Skill tool with skill: "pp-firecrawl".
• Codex — referenced from AGENTS.md if mirrored.
• Antigravity — referenced from the workspace agent rules if mirrored.
• HQ Project — listed on the landing page Skills section + post-login sidebar.
• MD Project (md.sgnk.ai) — file rendered from Skills/Pp Firecrawl/workflow.md.
• Obsidian — file rendered with frontmatter + tags.

Usage Examples

Invoke via slash command or natural language matching the skill description.

Source: (none)