@jaggerxtrm/specialists 3.14.1 → 3.15.0

package/config/benchmarks/executor-benchmark-matrix.json

@@ -1,25 +0,0 @@
-{
-  "id": "unitAI-gc2a",
-  "replicate": 1,
-  "reviewerModel": "openai-codex/gpt-5.4-mini",
-  "models": [
-    "openai-codex/gpt-5.3-codex",
-    "openai-codex/gpt-5.4-mini",
-    "dashscope/qwen3.5-plus",
-    "zai/glm-5"
-  ],
-  "tasks": [
-    {
-      "id": "bug-fix",
-      "seedBead": "unitAI-y4ia"
-    },
-    {
-      "id": "refactor",
-      "seedBead": "unitAI-22tq"
-    },
-    {
-      "id": "implementation",
-      "seedBead": "unitAI-8zui"
-    }
-  ]
-}

package/config/mandatory-rules/debugger-trace-first.md

@@ -1,5 +0,0 @@
----
-name: debugger-trace-first
-kind: mandatory-rule
----
-Trace from symptom to cause before editing. Pinpoint suspects, then patch and verify.

package/config/skills/using-specialists/evals/evals.json

@@ -1,68 +0,0 @@
-{
-  "skill_name": "specialists-usage",
-  "evals": [
-    {
-      "id": 1,
-      "eval_name": "bug-investigation",
-      "prompt": "I'm seeing intermittent failures where specialist jobs show status 'done' in `specialists feed` but `specialists result` says they're still running. Can you investigate what's causing this inconsistency in the job lifecycle?",
-      "expected_output": "Agent delegates to a specialist (e.g. bug-hunt) rather than diving into the source code themselves. Should create a bead first, then run the specialist with --bead.",
-      "assertions": [
-        {
-          "name": "invokes_specialist",
-          "description": "Agent runs `specialists run` or calls use_specialist/start_specialist instead of reading source files directly"
-        },
-        {
-          "name": "creates_bead_first",
-          "description": "Agent creates a tracking bead before invoking the specialist"
-        },
-        {
-          "name": "does_not_self_investigate",
-          "description": "Agent does not read supervisor.ts, status.json, or other source files to investigate the bug themselves"
-        }
-      ],
-      "files": []
-    },
-    {
-      "id": 2,
-      "eval_name": "code-review",
-      "prompt": "The specialist runner module at src/specialist/runner.ts is the core execution layer. Can you review it for bugs, edge cases, and code quality issues? It's about 300 lines and fairly complex.",
-      "expected_output": "Agent delegates to a specialist (e.g. parallel-review or codebase-explorer) rather than reading the file and writing a review themselves. Should create a bead first.",
-      "assertions": [
-        {
-          "name": "invokes_specialist",
-          "description": "Agent runs `specialists run` or calls use_specialist/start_specialist instead of reading runner.ts directly"
-        },
-        {
-          "name": "creates_bead_first",
-          "description": "Agent creates a tracking bead before invoking the specialist"
-        },
-        {
-          "name": "does_not_self_review",
-          "description": "Agent does not read runner.ts and write their own code review"
-        }
-      ],
-      "files": []
-    },
-    {
-      "id": 3,
-      "eval_name": "test-coverage",
-      "prompt": "src/specialist/loader.ts handles YAML file discovery and caching. Looking at the tests in tests/unit/specialist/loader.test.ts, what's missing? Can you add the coverage gaps?",
-      "expected_output": "Agent delegates to a specialist (e.g. test-runner) rather than reading the files and writing tests themselves. Should create a bead first.",
-      "assertions": [
-        {
-          "name": "invokes_specialist",
-          "description": "Agent runs `specialists run` or calls use_specialist/start_specialist instead of writing tests directly"
-        },
-        {
-          "name": "creates_bead_first",
-          "description": "Agent creates a tracking bead before invoking the specialist"
-        },
-        {
-          "name": "does_not_self_write_tests",
-          "description": "Agent does not read loader.ts and loader.test.ts and write new test cases themselves"
-        }
-      ],
-      "files": []
-    }
-  ]
-}

package/config/skills/using-specialists-v3/evals/evals.json

@@ -1,89 +0,0 @@
-{
-  "skill_name": "using-specialists-v3",
-  "evals": [
-    {
-      "id": 1,
-      "eval_name": "role-selection-implementation",
-      "prompt": "Need add one small feature in src/specialist/loader.ts, but I do not know exact path yet. Which specialist should handle discovery and implementation?",
-      "expected_output": "Agent checks live registry if needed, creates/updates complete bead contracts, selects explorer for discovery then executor for implementation, and does not self-investigate substantial work.",
-      "assertions": [
-        {
-          "name": "selects_specialist_role",
-          "description": "Agent names a specialist role appropriate for unknown implementation work"
-        },
-        {
-          "name": "uses_live_registry",
-          "description": "Agent references specialists list --full instead of a static catalog"
-        },
-        {
-          "name": "does_not_self_investigate",
-          "description": "Agent does not read source files and solve it directly"
-        }
-      ],
-      "files": []
-    },
-    {
-      "id": 2,
-      "eval_name": "role-selection-debugging",
-      "prompt": "A specialist chain started failing with a stack trace and inconsistent result state. Who should inspect it, and what command surface should I use to check available flags?",
-      "expected_output": "Agent selects debugger for root-cause analysis, may use test-runner for check execution, and points to sp help/subcommand help before relying on flags.",
-      "assertions": [
-        {
-          "name": "selects_debugging_role",
-          "description": "Agent chooses debugger or test-runner for failure analysis"
-        },
-        {
-          "name": "uses_help_surface",
-          "description": "Agent references sp help or subcommand help for command details"
-        },
-        {
-          "name": "does_not_guess_flags",
-          "description": "Agent does not invent CLI flags from memory"
-        }
-      ],
-      "files": []
-    },
-    {
-      "id": 3,
-      "eval_name": "role-selection-review",
-      "prompt": "Executor finished a change and I need final verification before merge. Which specialist next, and what should it check?",
-      "expected_output": "Agent selects reviewer with its own bead and --job <exec-job>, checks bead contract plus diff, and treats PASS as merge gate.",
-      "assertions": [
-        {
-          "name": "selects_reviewer_role",
-          "description": "Agent chooses reviewer for post-implementation verification"
-        },
-        {
-          "name": "checks_contract_and_diff",
-          "description": "Agent states reviewer checks bead contract and diff"
-        },
-        {
-          "name": "does_not_replace_reviewer_with_self",
-          "description": "Agent does not perform the review directly"
-        }
-      ],
-      "files": []
-    },
-    {
-      "id": 4,
-      "eval_name": "merge-publication-flow",
-      "prompt": "Reviewer passed an executor chain. What should the orchestrator do next to publish the specialist work?",
-      "expected_output": "Agent uses sp merge <chain-root-bead> for standalone chains or sp epic merge <epic-id> for epic-owned work, avoids manual git merge, and closes the bead only after required gates are confirmed.",
-      "assertions": [
-        {
-          "name": "uses_specialist_merge",
-          "description": "Agent names sp merge or sp epic merge as the publication path"
-        },
-        {
-          "name": "avoids_manual_git_merge",
-          "description": "Agent explicitly avoids manual git merge for specialist-owned work"
-        },
-        {
-          "name": "honors_reviewer_gate",
-          "description": "Agent publishes only after reviewer PASS or explicit operator acceptance"
-        }
-      ],
-      "files": []
-    }
-  ]
-}