giovanni

Plugin giovanni from marketplace giovanni in jaroslavsoucek-art/Giovanni. Commands read from the repo's manifest — 4 days ago.

Skills (11)

• branch-out

  Active predictive simulation for a specific situation — routes to prediction-runtime in branch-out mode. Hard-stops on shallow actors.

• calibration-report

  Monthly calibration report — routes to prediction-runtime in calibration-report mode. Aggregates per-actor + per-tier accuracy, updates actor-scores.yaml.

• consistency-check

  Run semantic consistency checks across memory, constitution, agent roster, decision records, the decided-terms registry, knowledge↔knowledge cross-doc drift, and externally published pages. Routes to consistency-checker agent. Read-only — proposes diffs, never applies them.

• consistency-review

  Manual per-finding triage of a /giovanni:consistency-check report — accept-diff / reject / defer / false-positive verdicts, precision tally update. Interactive main-thread workflow, no agent spawn.

• digest

  Run the daily digest — parallel source pull, synthesis, drift detection, brief generation, shadow lookback, render to chat.

• init

  Scaffold the Giovanni layers into the current repo — memory/, knowledge/, deliverables/, docs/governance.config.yaml, the permission half of .claude/settings.json and the CLAUDE.md operating contract — from the plugin's skeleton. Idempotent; never overwrites a file you have filled.

• market-radar

  Proactive external competitive / market intelligence scan. Routes to market-radar agent. Default = periodic sweep; focused = topic / market / competitor deep-dive.

• pulse

  Weekly read of what is actually getting built or done, per work-block — from the tracker, the code, and the docs. State of the work, not the stream of events. Distinct from the digest, which is signal since the last run.

• redline

  Adversarial review variant emphasizing verbatim strike list — same agent as /giovanni:review, prompt biased toward line-level redlines. Returns SHIP / REWRITE / KILL.

• review

  Adversarial review of a draft. Routes to adversarial-reviewer agent. Returns SHIP / REWRITE / KILL verdict + prioritized issues + strongest counter-case. Read-only.

• shadow-review

  Quarterly audit of recent shadow hypotheses — routes to prediction-runtime in shadow-review mode. Enforces adversarial lookback discipline.

Subagents (8)

• adversarial-reviewer

  Adversarial / red-team review of a draft (deliverable, decision record, position paper, fundraise narrative, board material, public communication, predictive forecast, constitution patch). Default mode is critical, not advisory. Trigger on `[REVIEW]` tags in draft, "review this", "redline", "before

• consistency-checker

  Run semantic consistency checks across memory, constitution, agent roster, decision records, and the decided-terms registry. Surfaces contradictions and drift that deterministic lint can't catch (e.g. memory blocker contradicts constitution claim; agent roster description doesn't match agent file ca

• deliverable-reviewer

  Pre-share QA pass on a deliverable (file in deliverables/ or proposed external message). Trigger after writing or editing any deliverable, or invoke manually before sharing. Checks consistency vs repo state, diff vs prior version, missing provenance, broken cross-references, factual claims unverifia

• market-radar

  Proactive external competitive / market intelligence scan. Default mode = periodic sweep of competitor space (markets × layers per scope config). Focused mode = topic / market / competitor deep-dive on demand. Returns structured memo with material shifts + framework implications + action verdict. St

• prediction-runtime

  Executes the predictive-layer slash commands in isolated context — /giovanni:branch-out (active simulation), /giovanni:shadow-review (quarterly verdict pass with adversarial lookback), /giovanni:calibration-report (monthly accuracy aggregation). Carries prediction-architect's 8 binding principles ve

• profile-bootstrap

  Bootstrap a new stakeholder profile OR refresh an existing one in `memory/stakeholders/<slug>.md`. Trigger phrases — "bootstrap stakeholder X", "refresh profile X", "who is X" (when asked about a person not yet profiled). Pulls cross-source signals (chat / email / calendar / project tracker / versio

• researcher

  Investigate an external topic via web search + fetch, then return a structured memory note + optional constitution patch proposal. Use when the question requires sources outside the repo (regulation, market data, vendor capability, competitor moves, pricing). Trigger phrases — "investigate X", "rese

• source-puller

  Pull a SINGLE source for a specified time window and return structured findings. Use for parallel fan-out in digest workflows. Caller specifies source_type + identifier + window. Returns plain markdown bullets — no synthesis, no prioritization, no recommendation. Generic over source_type enum (chat-

Hooks (9)

• SessionStart

  ${CLAUDE_PLUGIN_ROOT}/hooks/session-start-digest.sh

• SessionStart

  ${CLAUDE_PLUGIN_ROOT}/hooks/session-start-audit-check.sh

• PreToolUse

  ${CLAUDE_PLUGIN_ROOT}/hooks/check-decision-records.sh

• PreToolUse

  ${CLAUDE_PLUGIN_ROOT}/hooks/block-external-writes.sh

• PostToolUse

  ${CLAUDE_PLUGIN_ROOT}/hooks/post-constitution-edit-check.sh

• PostToolUse

  ${CLAUDE_PLUGIN_ROOT}/hooks/post-knowledge-edit.sh

• PostToolUse

  ${CLAUDE_PLUGIN_ROOT}/hooks/post-memory-edit.sh

• Stop

  ${CLAUDE_PLUGIN_ROOT}/hooks/check-unmerged-claude-branches.sh

• Stop

  ${CLAUDE_PLUGIN_ROOT}/hooks/stop-ephemeral-commit-guard.sh

Similar plugins