Install
pip install. The plugin adds
~104 tokens to a session and ships no hooks and no MCP server — three command prompts, and nothing
runs until you type one.
The three commands
/decimalai:search <query>
Searches the public registry and ranks by measured effectiveness. Each row carries a SkillScore, the
verified lift with the model and case count it was measured on, the safety band, and how many agents
currently have it installed.
Searching for sql injection surfaces detecting-sql-injection-via-waf-logs — +54.6 points over 22
cases on gemini-3.6-flash, safety Passed.
/decimalai:install <url_slug>
Writes .claude/skills/<slug>/SKILL.md plus the skill’s attachments, stamped with source and
source_sha256 provenance frontmatter so you can tell later exactly what you installed and from
which version.
Pass the url_slug that search printed, not the name — a registry name may be namespaced
(owner/skill), and a / is neither a URL path segment nor a directory name.
/decimalai:check
Writes the two files behind the regression-check Action: the
manifest-extraction entry point scripts/init_for_decimal.py, and the workflow
.github/workflows/decimal-regression-check.yml, with your repo’s real agent_name filled in.
The workflow it writes needs a DECIMAL_API_KEY repo secret — the check runs against your own
production traces — and adding that secret is still yours to do.
The command that refuses
The registry indexes skills scraped from public repositories, and some of them are hostile. Search forsql injection and one of the matches is performing-second-order-sql-injection.
That skill is the reason the two checks are separate. Its pattern scan came back clean — no
secrets, no reverse shell, no exfiltration step. The intent review rejected it anyway, with the
summary “provides actionable instructions and commands for performing second-order SQL injection
attacks, including database exploitation and credential extraction.” Scan passed; judge caught it.
/decimalai:search lists it last, under a heading saying it will not install, with the reason —
visible, never pickable. Listing it rather than hiding it is deliberate: you searched for something,
and you are entitled to know a match exists and why it is withheld. /decimalai:install refuses it
outright, and asks before writing anything banded Caution or Not yet reviewed.
What leaves your machine
The search query and the skill slug, as anonymous GETs toapi.decimal.ai. No account is created and
nothing is stored against you; those requests appear in server logs as described in §1.4 of the
privacy policy.
The plugin sends no telemetry of its own. DecimalAI has no record that you installed anything — which
is also why a local install never feeds the effectiveness numbers you just used to choose the skill.
In this registry’s vocabulary that makes it an Export, whatever the command
is called.
Not using Claude Code?
This is one of five routes from the registry to disk, and the only one that is Claude Code-specific —/decimalai:install writes to .claude/skills/. Web copy-paste, decimalai skills pull, raw URLs
and the MCP server all work anywhere, and the MCP server in particular serves Cursor, Windsurf and
anything else that speaks MCP.
Side-by-side comparison of all five: Use skills without the
SDK.
Source
decimal-labs/decimalai-claude-plugins —
MIT, and the command prompts are readable markdown, so you can see exactly what each one instructs
Claude to do before you install it.