Y4NN777

How Baruch records the terminal output of a research run — the contract-bound research-log shape, when to write a Cognee node and when not to, the curated-library-match short circuit, and the discipline of being a faithful carrier. Invoke when emitting a research-log entry, when the Cognee write decision is in scope, or when an upstream stage returned malformed input.

Promote knowledge into Cognee by blast radius. Routes a learning to the right tier — agent-private (stays in MEMORY.md), team-level (team rules + topic files, Team Lead decides), or cross-harness (Cognee project graph, Nehemiah + Bezalel at sprint close). Use when an agent has a learning worth keeping.

How Ezra turns clarified intent into a research brief — the curated-library-first rule, the sub-question decomposition, source prioritisation, acceptance criteria for "good answer," and the short-circuit when the curated library already holds the answer. Invoke as the second stage of the research pipeline after Jakin clarifies.

How Shemaiah judges the summarised research for signal vs noise — the cross-reference against the curated library, the verdict shape (resolved / partial / blocked), confidence calibration anchored to source quality and coverage, gap identification, and the rule that an evaluation never produces new content. Invoke as the fifth stage of the research pipeline.

Set up Cognee for MISHKAN — choose the install path, create a clean Python env, configure LLM/embedding providers and (optionally) PostgreSQL/Neo4j backends, and wire it to the harness. Use before first bringing up the knowledge graph, or when Cognee setup hits friction (Python version, venv, API keys, optional extras). Mirrors Cognee's official LLM quickstart skill.

Initialise a project under MISHKAN. Runs the SWE-BASICS-BEFORE-CODE sequence through the right specialists (PRD → SRS → CONTRACT → ARCHITECTURE → THREAT_MODEL → C4 → docs scaffold), seeds Cognee, writes the project CLAUDE.md, and begins Sprint S0. Use once per project, triggered by /mishkan-init.

Selectively ingest specific documents into the project's cognee work store. Use to deliberately add docs to memory instead of bulk-ingesting a whole tree — the default is "nothing enters memory unless tagged or invoked", which prevents PII bleed (e.g. real addresses in incident reports) and oversized-doc embedding failures. Walks ./docs/ filtered by a `mishkan: ingest` YAML frontmatter tag, or accepts explicit paths. Always runs cognify → memify after adding.

How the six Team Leads (aholiab, huram, zerubbabel, phinehas, eliashib, jehoshaphat) lead a team without imploding it — the routing-within-team discipline, the planning-before-handoff rule, the do-not-implement-yourself rule, and the seams to other teams. Same shape; six team-specific notes per Lead. Invoke when leading team work, planning a cross-team handoff, or routing within a team.

Use for changes to REST, GraphQL, RPC, protobuf, OpenAPI, AsyncAPI, webhooks, SDK-facing structs, HTTP status semantics, pagination, idempotency, retry behavior, request/response schemas, and event payloads. This skill detects contract drift, backward-incompatible behavior, unsafe defaults, and missing contract tests.

Use for database migrations, schema changes, data model updates, persistence logic, query behavior, cache invalidation, backfills, retention changes, and durable memory writes. This skill reviews rolling deploy safety, reversibility, locking, data integrity, tenant isolation, migration ordering, and operational recovery.

Use when implementation must be checked against explicit design intent: PRD/SRS, acceptance criteria, architecture contracts, ADRs, component ownership, API/UI/data contracts, invariants, guarantees, prohibitions, and generated project wiki sections. Finds behavior that is locally correct but violates the intended system design.

Use to enforce an engineering method before judging code: problem intent, PRD/product scope, SRS/verifiable requirements, system contract/invariants, responsibility assignment, architecture/modeling, then implementation review. Also enforces the agent review lifecycle when the target system is a review automation service. Prevents shortcut reviews that let code or model output invent missing context.

Use for changes touching goroutines, workers, queues, retries, timeouts, context cancellation, HTTP clients, external APIs, Docker sidecars, streaming, memory stores, file handles, locks, schedulers, idempotency, or observability. This skill finds production failure modes such as leaks, hangs, duplicate work, lost work, retry storms, and silent partial failure.

Use when code changes must be traced to requirements, invariants, architecture decisions, threat controls, API contracts, process gates, or design sources. Enforces links between changed files and identifiers such as FR, NFR, INV, GAR, PRO, LAW, OPC, ADR, CMP, DSO, CTRL, and threat-model controls.

Use for dependency, build, CI, Docker, environment variable, feature flag, permission, runtime config, release packaging, and supply-chain changes. This skill reviews reproducibility, secret safety, least privilege, unsafe scripts, rollout defaults, version pinning, and deployment drift.

Use to enforce repository-specific engineering framework rules, architectural boundaries, coding conventions, language idioms, lifecycle hooks, package ownership, local helpers, deterministic gates, and documented guardrails. This skill resolves local rules from AGENTS.md, CLAUDE.md, rules directories, nearby code patterns, and framework docs without turning style preference into findings.