Install, list, or uninstall optional vendor skill packs not bundled by default — "add the Databricks pack", "what packs are available", "is there a pack for X", "get me the Databricks skills".
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
Packs are skill collections 100xprism does not ship by default because they only matter to some projects. They are opt-in: nothing installs until you ask.
Scope:
/packinstalls skills you don't have. To authenticate a CLI you already have, use/connect.
/pack — list every pack, its install state, and anything detected here/pack detect — only what matches the current project/pack add databricks — install a pack/pack remove databricks — reverse what 100xprism installedAll decisions live in the helper script. Do not reimplement them here.
PACKS=""
for candidate in \
"$HOME/100xprism/adapters/lib/packs.py" \
"$(npm root -g 2>/dev/null)/100xprism/adapters/lib/packs.py"; do
if [ -f "$candidate" ]; then PACKS="$candidate"; break; fi
done
if [ -z "$PACKS" ]; then
echo "100xprism installation not found — reinstall with: npm i -g 100xprism"
exit 1
fi
Pass the user's words through this case statement verbatim. Do not invent a subcommand: anything unrecognised is a usage error, not a guess.
ARG1="${1:-}"
SLUG="${2:-}"
case "$ARG1" in
"") SUB="status" ;;
detect) SUB="detect" ;;
add) SUB="add" ;;
remove) SUB="remove" ;;
*) echo "Usage: /pack [detect | add <slug> | remove <slug>]"; exit 1 ;;
esac
if [ "$SUB" = "add" ] || [ "$SUB" = "remove" ]; then
if [ -z "$SLUG" ]; then
echo "Usage: /pack $SUB <slug> (run /pack to list available slugs)"
exit 1
fi
fi
"$SLUG" stays quoted so a slug can never split into extra arguments or inject a
flag into the helper.
python3 "$PACKS" "$SUB" "$SLUG" --settings "$HOME/.claude/settings.json"
Print the helper's output verbatim. It already says which platforms were handled and which need a manual step.
If any pack was added or removed, finish with: restart your agent to pick up the change.
Two things to pass along honestly rather than paper over:
manual was not installed. Give the user the exact command
the helper printed./pack remove reverses only what 100xprism wrote. A pack installed by an upstream
CLI leaves its skill files on disk — say so; do not delete them.No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Act as a Senior Accessibility Engineer to audit a page, component, or design against WCAG 2.2 AA. Produces a triaged finding list (critical/serious/moderate), focus-order map, contrast report, ARIA decision tree, and a screen-reader test plan. Use when shipping new UI, hardening an existing flow, or preparing for VPAT/accessibility conformance.
The English summary is being prepared. Showing the original description.
When the user wants to plan, design, or implement an A/B test or experiment — "split test," "variant copy," "multivariate test," "hypothesis," "statistical significance," "how long should I run this test," or comparing two versions. For tracking implementation, see analytics-tracking. For page-level conversion optimization, see page-cro.
The English summary is being prepared. Showing the original description.
When the user wants to generate, iterate, or scale ad creative — headlines, descriptions, primary text, full variations — for any paid platform; 'ad copy variations,' 'RSA headlines,' 'bulk ad copy,' 'creative testing,' 'write me some ads.' For campaign strategy and targeting, see paid-ads. For landing page copy, see copywriting.
The English summary is being prepared. Showing the original description.
When the user wants content cited by LLMs or surfaced in AI-generated answers — 'AI SEO,' 'AEO,' 'GEO,' 'LLMO,' 'answer engine optimization,' 'AI Overviews,' 'optimize for ChatGPT/Perplexity/Claude,' 'AI citations,' 'zero-click search.' For traditional technical/on-page audits, see seo-audit. For structured data, see schema-markup.
The English summary is being prepared. Showing the original description.
When the user wants to set up, improve, or audit analytics tracking and measurement — "GA4," "conversion tracking," "event tracking," "UTM parameters," "tag manager," "GTM," "tracking plan," "attribution," "Mixpanel," "Segment," "are my events firing," or how to measure marketing results. For A/B test measurement, see ab-test-setup.
The English summary is being prepared. Showing the original description.
Architectural decision advisor for cloud, data, and SaaS distributed systems. Use when the user asks "should we use X or Y", weighs a tradeoff, or needs a decision matrix, scaling analysis, cost-at-scale review, data-tier design, multi-tenancy model, or API/resilience guidance. For full technical blueprints, use enterprise-design.
The English summary is being prepared. Showing the original description.