skills/firefox-cookies/SKILL.md
Extract cookies from Firefox for authenticated web scraping. Reads cookies.sqlite for a specific domain. macOS only.
npx skillsauth add RonanCodes/ronan-skills firefox-cookiesInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Extract cookies from Firefox's local storage for a given domain. Used by other skills (like ingest-linkedin) for authenticated fetching.
Prefer
ro:browser-cookies— the generalized sibling that also handles Brave, Chrome, Arc, Edge (Chromium browsers via macOS Keychain). This skill stays for back-compat and for Firefox-only setups. On macOS where Firefox isn't installed (e.g., Brave-only), this skill will error out — usero:browser-cookiesinstead.
Called by other skills with a target domain. Returns a Cookie: header string.
Locate the Firefox profile directory on macOS:
PROFILES_DIR="$HOME/Library/Application Support/Firefox/Profiles"
# Find the most recently modified profile with a cookies.sqlite
PROFILE_DIR=$(ls -td "$PROFILES_DIR"/*/ 2>/dev/null | while read dir; do
[ -f "$dir/cookies.sqlite" ] && echo "$dir" && break
done)
If no Firefox profile or cookies.sqlite is found:
Firefox locks cookies.sqlite while running. Copy to a temp location:
cp "$PROFILE_DIR/cookies.sqlite" /tmp/llm-wiki-firefox-cookies.sqlite
# Also copy the WAL file if it exists (contains recent writes)
[ -f "$PROFILE_DIR/cookies.sqlite-wal" ] && \
cp "$PROFILE_DIR/cookies.sqlite-wal" /tmp/llm-wiki-firefox-cookies.sqlite-wal
Extract cookies for the requested domain:
sqlite3 /tmp/llm-wiki-firefox-cookies.sqlite \
"SELECT name, value FROM moz_cookies
WHERE host LIKE '%<domain>%'
AND expiry > strftime('%s','now')
ORDER BY name;"
The expiry > strftime('%s','now') filter skips expired cookies.
Build a standard Cookie: header string from the results:
Cookie: name1=value1; name2=value2; name3=value3
If the query returns zero rows:
Remove the temp copy:
rm -f /tmp/llm-wiki-firefox-cookies.sqlite /tmp/llm-wiki-firefox-cookies.sqlite-wal
macOS only. Firefox profile path: ~/Library/Application Support/Firefox/Profiles/.
For Linux, the path would be ~/.mozilla/firefox/ — not currently supported but straightforward to add.
testing
--- name: linear-pipeline description: The Fable orchestrator for a single dispatched Linear ticket. Holds almost no context itself; it receives `--issue <ID> --detached`, decides the stage sequence, and fans out a sub-agent per stage, passing forward only each stage's artifact (never re-derived, never inlined into its own context). Step zero, before any planning or stage routing, is a boundary triage against `canon/security-boundary.md` (#199): a match tags Ronan Connolly and stops the run, no
development
--- name: in-your-face description: Capture a chat-only answer into a durable artifact (markdown + HTML, PDF when cheap) and launch it automatically so the user cannot miss it. Use when user says "in your face", "don't let me lose this", "save that answer", "make that durable", or right after answering a substantive side question (a recipe, comparison, how-to, or generated prompt) that would otherwise die with the context. category: workflow argument-hint: [--no-open] [--vault <short>] [hint of
tools
One-shot headless OpenAI Codex CLI calls for background/admin AI tasks — summaries, classification, extraction, admin glue. The default engine for anything that runs AI constantly in the background (daemon-driven, per-event), because it bills the flat ChatGPT subscription instead of Claude usage or per-token API spend, and it keeps working while Claude is rate-limited. NEVER for coding — coding stays Claude. Use when a skill or daemon needs a cheap always-on AI call, when the user says "use codex", "ask codex", "codex as backup", or when building a background summarizer/classifier into a listener or loop. Reads auth from ~/.codex/auth.json (ChatGPT account, no API key).
research
Turn a warranty rejection, repair quote, or RMA email into a cited decision brief — legal read (NL/EU consumer law), is the part user-serviceable, live part and new-unit prices, repair-vs-DIY-vs-new economics, before-you-send-it checklist, deadlines. Use when the user pastes or screenshots a repair quote, warranty rejection, "not covered" email, onderzoekskosten fee, or asks "should I repair or replace this".