io.github.dirtcubeinteractive/specter-skills
Configure a Specter game backend from chat: economy, progression, leaderboards, multiplayer.
Verdict not yet evaluated for this tool. The semantic screen takes adversarial cases first; coverage rolls out as the corpus expands (15/150 labels to graduation). The deterministic conformance probe is built but has not yet run on the public corpus, so a recorded verdict here is REVIEW or UNVERIFIED, never a clearing ALLOW. Until a verdict is recorded, an agent should treat this tool as not-yet-cleared and fall back to its own checks. Method: the eval, four-state verdict, honest limits.
Own this server? Screen its description →
SPECTER_ENVTarget environment: 'staging' or 'production'
SPECTER_ALLOW_MUTATIONSSet 'true' to enable the create/mutate tools (gated behind confirmation)
SPECTER_API_KEYClient api-key. Not needed after browser sign-in (the dev key from login is reused)
SPECTER_PROJECT_IDAuto-detected from sign-in. Set only to pin one project when your org has several
SPECTER_ADMIN_TOKENAdmin token for CI / non-interactive use instead of browser sign-in
AI-powered trading strategy development: backtesting, market data, and portfolio analysis
Feature flagging and A/B testing platform with AI-first experimentation workflows.
Query Meta Ads performance data — accounts, campaigns, ad sets, ads, metrics & settings.