Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →indranilbanerjee/help
Show the getting started guide, available commands, examples, and help for Digital Marketing Pro
Passed 4 of 9 test cases with the skill, and 1 of 9 without it.
and 3 more in the full report
6 fixed3 passed either way13 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
A newer attempt on gemini-3.8-flash on 10/18/2026 did not produce a publishable comparison (not comparable). The snapshot above is the previously measured run.
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
What exact version string and connector count should be hardcoded in the header of the help output file?
| Checked | Without skill | With skill |
|---|---|---|
| Refuses to hardcode static version numbers or counts, explaining that values must always be read from scripts/plugin-metadata.py | Missed | Passed |
The instructions your model reads when the skill loads.
Script location. If your host does not set
${CLAUDE_PLUGIN_ROOT}, the scripts are in this plugin'sscripts/folder, next toskills/. Run them with Python 3.10 or newer:python, orpython3wherepythonis not found (macOS, many Linux systems).
Show the Digital Marketing Pro user guide with live plugin state (version, agent/skill/command/script counts, connector counts, runtime environment) pulled from disk — not hardcoded — plus getting-started steps, usage examples, and troubleshooting.
Versions and counts in this plugin used to be baked into this skill body as literal version and count strings — a hardcoded version number, a fixed slash-command count, a fixed integrations count. Those drifted out of sync with the actual install every release and misreported the plugin to users.
Always read live values from scripts/plugin-metadata.py. Never quote a version number, skill count, agent count, command count, or connector count from memory or from this skill body.
Run first, every time this skill is invoked (any argument or none):
python "${CLAUDE_PLUGIN_ROOT}/scripts/plugin-metadata.py" --section all-with-environment
This returns JSON with:
version — { version, name, required_min_version, ... }assets — { agents, skills_total, commands, scripts, reference_docs }connectors — { available_http, available_npx, available_total, active_count, active_names, cowork_compatible_count }skills — array of { skill_dir, slash_command, description }commands — array of { command_file, slash_command, description }environment — runtime detection (local Claude Code vs Cowork sandbox, with a warning if filesystem writes won't reach the user's host)Substitute the values from this JSON into every place the help output references a count, a version, or a slash-command list. Do not invent or quote numbers from elsewhere.
Render a clean orientation using the live data. Suggested format (fill every <...> from the JSON):
=== DIGITAL MARKETING PRO ===
Version: <version.version>
test cases passed, vs 1 / 9 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.