Allow scraping multiple URLs concurrently and save each result to .firecrawl/. Adds handleMultiScrapeCommand and urlToFilename helper in src/commands/scrape.ts to run concurrent scrapes, write outputs to .firecrawl/, emit progress/errors, and exit non-zero if all fail. Update CLI in src/index.ts to accept multiple positional URLs and --url, deduplicate inputs, infer formats from positional args or flags, and route single-URL requests to the existing handler. Update README.md and skills/firecrawl-cli/SKILL.md to document multiple-URL usage and examples.
Introduce a new CLI command to pull the authenticated FIRECRAWL_API_KEY into a local .env file. Adds src/commands/env.ts which implements handleEnvPullCommand(options) — it gets the API key (via getApiKey or ensureAuthenticated), and creates/updates/appends the FIRECRAWL_API_KEY line in the target env file, with an --overwrite flag to replace an existing key. Also registers the command in src/index.ts with options (-f/--file and --overwrite). This provides a convenient way for developers to sync their API key into project .env files.
Bump plugin version to 1.0.7 and overhaul the firecrawl CLI skill docs to emphasize minimizing tool calls. Add a new “Core Principle: Minimize Tool Calls” section recommending default stdout output (no -o) and show good/bad examples; introduce a Quick research workflow that recommends using search --scrape for one-call results; clarify when to use -o (large outputs, persistence, batch jobs) and update numerous command examples accordingly. Also reorganize guidance for reading saved files (use grep/incremental reads for large files), recommend --scrape for most searches, and clean up various sample commands and file-naming suggestions.
Introduce a new CLI init command to install Firecrawl integrations. Adds src/commands/init.ts which implements handleInitCommand with subcommands 'skills' and 'mcp' (installSkills and installMcp). Both flows invoke npx helpers via execSync and accept --global and --agent options; installMcp requires an API key (getApiKey / FIRECRAWL_API_KEY) and injects it into the environment. Registers the command in src/index.ts and updates README.md with usage examples for `firecrawl init skills` and `firecrawl init mcp` (including the npx add-mcp invocation). Exits on failures to propagate errors to the caller.
Bump firecrawl plugin version to 1.0.5 and expand the firecrawl-cli documentation. Clarifies that `search --scrape` already retrieves full page content (so avoid redundant scraping), adds a research-task example, warns against re-scraping URLs or using `--html` to re-extract metadata, and emphasizes reading existing scraped files before fetching more data. Changes in .claude-plugin/plugin.json and skills/firecrawl-cli/SKILL.md.
Instead of auto-bumping on every skill change, the workflow now only
triggers when plugin.json version is explicitly changed. The CLI repo
is the source of truth for versioning.
- Add sync-plugin.yml workflow that triggers on changes to skills/ or
.claude-plugin/ on main, copies files to firecrawl-claude-plugin,
bumps the patch version, and opens a PR
- Update plugin.json version to 1.0.3 to match the plugin repo
Developers Digest