Skip to content

Snoozer10/synthesize-skills / .agents/skills/gemini-context-engineer

gemini-context-engineer

Unverified

Use when creating, updating, auditing, or federating GEMINI.md workspace context files, detecting architectural reality drift between code and architecture docs, compiling token-bounded task slices, or verifying workstream proof commands

evals/evals.json

View on GitHub
{
  "evals": [
    {
      "id": "eval-1-polyglot-create",
      "description": "Runs indexing and template synthesis on a synthetic polyglot repo fixture",
      "assertions": {
        "latency_ms": "< 1500",
        "token_count": "< 2500",
        "exit_code": "== 0",
        "deep_modules_found": ">= 1"
      }
    },
    {
      "id": "eval-2-federation-repair",
      "description": "Tests --federate creating pointer shims for CLAUDE.md and AGENTS.md",
      "assertions": {
        "pointer_shim": "== True",
        "split_brain_warnings": "== 0"
      }
    },
    {
      "id": "eval-3-dag-cycle-detection",
      "description": "Tests Section 5 cyclical workstream detection via graphlib.TopologicalSorter",
      "assertions": {
        "error_detected": "ERR_DAG_CYCLE",
        "exit_code": "== 1"
      }
    },
    {
      "id": "eval-4-reality-drift-detection",
      "description": "Tests --reality detecting missing component links on disk",
      "assertions": {
        "warning_detected": "WARN_REALITY_DRIFT"
      }
    },
    {
      "id": "eval-5-jit-compiler-slicing",
      "description": "JIT context compiler AST dependency slicing under tight budget",
      "assertions": {
        "exit_code": "== 0",
        "latency_ms": "< 1500",
        "token_count": "<= 500",
        "invariants_preserved": "== True"
      }
    },
    {
      "id": "eval-6-vcs-daemon-diff",
      "description": "VCS daemon staged public signature drift detection and auto-patch healing",
      "assertions": {
        "exit_code": "== 0",
        "latency_ms": "< 2500",
        "signature_drift_detected": "== True",
        "auto_patch_success": "== True"
      }
    },
    {
      "id": "eval-7-workstream-proofs",
      "description": "Executable workstream proof execution, dependency gating, and atomic transition",
      "assertions": {
        "exit_code": "== 0",
        "latency_ms": "< 3000",
        "dependency_blocked_verified": "== True",
        "task_transitioned_done": "== True",
        "downstream_unlocked": "== True"
      }
    }
  ]
}
rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.Stars: 194kUpdated Claude CodeCodexVerifiedInstall