From bolster
Data verification hierarchy and quality standards — never fabricate, use placeholders over invented data
How this skill is triggered — by the user, by Claude, or both
Slash command
/bolster:data-verificationThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
1. **Direct tool outputs** — run the tool, use what it returns
[METRIC NEEDED], [URL TBC], [DATE]Do this:
* **LLM Gateway usage** — [data unavailable — run `uv run scripts/manage.py usage-summary --lookback 7` or check [dashboard](https://...)]
Not this:
* **LLM Gateway usage** — ~4,200 requests this week, up ~12% from last week
If you don't have the data, say so explicitly and provide the command or link to get it. Never simulate what the output "would probably look like."
git log[URL TBC] as a placeholdermcp__atlassian__searchConfluenceUsingCql to find the real URLgit log or gh CLIdate -j -v-$(($(date +%u) - 1))d +%Y-%m-%d[TBC]npx claudepluginhub bd-vitalstatistix/claude-marketplace --plugin bolsterProvides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.