@event4u/agent-config 14.10.0 → 14.12.0

package/dist/agent-src/skills/design-variations/evals/triggers.json

@@ -1,17 +0,0 @@
-{
-  "skill": "design-variations",
-  "last_eval": "2026-07-06",
-  "description": "5 should-trigger + 5 should-not-trigger. Should-trigger covers hi-fi options/alternatives requests. Should-not-trigger covers near-miss neighbors: wireframe (lo-fi structure exploration), design-intelligence (single grounded direction), design-review (review existing), image generation, and single-implementation feature work.",
-  "queries": [
-    {"q": "show me 3 different takes on this pricing page", "trigger": true},
-    {"q": "give me a few design options for the dashboard header", "trigger": true},
-    {"q": "I can't decide on the hero layout — build some alternatives I can compare", "trigger": true},
-    {"q": "make this settings screen in a safe version and a bold version", "trigger": true},
-    {"q": "let me play with color and density options on this card grid", "trigger": true},
-    {"q": "sketch a few rough layout directions for the signup flow before we style anything", "trigger": false, "note": "lo-fi structure exploration → wireframe"},
-    {"q": "pick a visual direction and palette for our new SaaS app", "trigger": false, "note": "single grounded direction → design-intelligence"},
-    {"q": "review this landing page design for issues", "trigger": false, "note": "review of existing design → design-review"},
-    {"q": "generate 3 logo images in Midjourney", "trigger": false, "note": "AI image generation → image-provider-routing / logo-generation"},
-    {"q": "build the checkout form component", "trigger": false, "note": "single implementation, no options ask → fe-design / stack executor"}
-  ]
-}

package/dist/agent-src/skills/developer-like-execution/evals/evals.json

@@ -1,16 +0,0 @@
-{
-  "skill": "developer-like-execution",
-  "_calibration": "Behavioural fixture (road-to-skill-eval-coverage Phase 2, default-surface). Deterministic assertions on a real output property where reliable; rubric pins the qualitative core as a known-limit (pass ratified in PR review, not a hidden judge). finding_floor n is a conservative floor, not a calibrated per-host number.",
-  "scenarios": [
-    {
-      "id": "execute-like-dev",
-      "prompt": "Implement this small change end-to-end the way a senior would.",
-      "assertions": [
-        {
-          "kind": "rubric",
-          "criterion": "Reads before editing, keeps the diff minimal + scoped, updates downstream callers/tests, and verifies with a real run before claiming done."
-        }
-      ]
-    }
-  ]
-}

package/dist/agent-src/skills/doc-coauthoring/evals/evals.json

@@ -1,16 +0,0 @@
-{
-  "skill": "doc-coauthoring",
-  "_calibration": "Behavioural fixture (road-to-skill-eval-coverage Phase 2, default-surface). Deterministic assertions on a real output property where reliable; rubric pins the qualitative core as a known-limit (pass ratified in PR review, not a hidden judge). finding_floor n is a conservative floor, not a calibrated per-host number.",
-  "scenarios": [
-    {
-      "id": "coauthor-prd",
-      "prompt": "Help me write the PRD for our new onboarding flow.",
-      "assertions": [
-        {
-          "kind": "rubric",
-          "criterion": "Runs the 3-stage flow — context → section-by-section → reader-test — rather than dumping a full doc; asks for the missing context first."
-        }
-      ]
-    }
-  ]
-}

package/dist/agent-src/skills/doc-coauthoring/evals/triggers.json

@@ -1,17 +0,0 @@
-{
-  "skill": "doc-coauthoring",
-  "last_eval": "2026-06-16",
-  "description": "5 should-trigger + 5 should-not-trigger queries. Should-trigger phrasings reflect real co-authoring asks for PRDs / specs / decision docs. Should-not-trigger near-misses share doc-writing vocabulary but route elsewhere (agent-docs-writing, readme-writing, adr-create, code docs, translations).",
-  "queries": [
-    {"q": "Help me draft a PRD for the new analytics feature — I have a lot of context but no structure yet", "trigger": true},
-    {"q": "We need a design doc for the OAuth migration before next week's review. Can you walk me through writing it?", "trigger": true},
-    {"q": "I have to write up a decision doc about dropping Redis. Where do we start?", "trigger": true},
-    {"q": "Need an RFC for the data-export rate-limit change before tomorrow's architecture sync", "trigger": true},
-    {"q": "Lass uns einen Spec für das neue Webhook-Verfahren zusammenstellen — du fragst, ich antworte", "trigger": true},
-    {"q": "Add a section to AGENTS.md about the new env vars we just introduced", "trigger": false},
-    {"q": "Update the README with the new install instructions for the docker variant", "trigger": false},
-    {"q": "Write an ADR for the queue-broker switch from Redis to SQS", "trigger": false},
-    {"q": "Add docstrings to all public methods on the OrderService class", "trigger": false},
-    {"q": "Translate the lang/de strings to French for the new locale rollout", "trigger": false}
-  ]
-}

package/dist/agent-src/skills/docx-authoring/evals/triggers.json

@@ -1,52 +0,0 @@
-{
-    "skill": "docx-authoring",
-    "last_eval": "2026-07-30",
-    "description": "5 should-trigger + 5 should-not-trigger queries. Should-trigger covers DE + EN phrasings for WRITING a Word .docx — create from content, fill a supplied template, surgical body-XML edit. Should-not-trigger covers the near-miss neighbours (docx→Markdown reading, PDF authoring, spreadsheets, slide decks, prose co-authoring) whose vocabulary overlaps.",
-    "queries": [
-        {
-            "q": "generate a .docx report from this content",
-            "trigger": true
-        },
-        {
-            "q": "fill this Word template with these values and save a copy",
-            "trigger": true
-        },
-        {
-            "q": "edit the heading and one table cell inside this existing .docx",
-            "trigger": true
-        },
-        {
-            "q": "erzeuge daraus ein Word-Dokument mit A4-Seitenformat und einer Tabelle",
-            "trigger": true
-        },
-        {
-            "q": "produce the contract as a Word file, not a PDF",
-            "trigger": true
-        },
-        {
-            "q": "extract the text of this .docx into Markdown so I can read it here",
-            "trigger": false,
-            "note": "reading a docx into the conversation, not writing one → markitdown"
-        },
-        {
-            "q": "merge these PDFs and fill the PDF form fields",
-            "trigger": false,
-            "note": "PDF authoring surface, different library-per-task path → pdf-tools"
-        },
-        {
-            "q": "build me a budget model with formulas in a spreadsheet",
-            "trigger": false,
-            "note": "spreadsheet/model authoring, not an OOXML text document → spreadsheet-authoring"
-        },
-        {
-            "q": "turn this into a slide deck for the pitch tomorrow",
-            "trigger": false,
-            "note": "presentation surface; pptx is gated, decks go to → html-deck"
-        },
-        {
-            "q": "help me write the PRD itself — structure the sections and stress-test the reader test",
-            "trigger": false,
-            "note": "authoring the prose/content of a spec, not producing the .docx container → doc-coauthoring"
-        }
-    ]
-}

package/dist/agent-src/skills/dpa-review/evals/triggers.json

@@ -1,17 +0,0 @@
-{
-    "skill": "dpa-review",
-    "last_eval": "2026-06-24",
-    "description": "5 should-trigger + 5 should-not-trigger. Should-trigger covers DE+EN phrasings for reviewing a Data Processing Agreement against GDPR Art. 28 (controller or processor). Should-not-trigger covers near-miss neighbours: NDA triage, generic contract review, privacy-regime read (privacy-review), legal triage.",
-    "queries": [
-        { "q": "review this DPA as processor against GDPR Art. 28", "trigger": true },
-        { "q": "check this data processing agreement, we're the controller", "trigger": true },
-        { "q": "der Kunde hat seine AVV geschickt — prüf die Art-28-Lücken", "trigger": true },
-        { "q": "gap-frame this processor agreement for sub-processor and audit clauses", "trigger": true },
-        { "q": "erfüllt dieser Auftragsverarbeitungsvertrag Art. 28 DSGVO?", "trigger": true },
-        { "q": "check this NDA — standard or not?", "trigger": false },
-        { "q": "review this vendor MSA clause-by-clause", "trigger": false },
-        { "q": "which privacy regime applies to us, GDPR or CCPA?", "trigger": false },
-        { "q": "is this a legal problem at all?", "trigger": false },
-        { "q": "set up our legal practice profile", "trigger": false }
-    ]
-}

package/dist/agent-src/skills/editorial-calendar/evals/domain-truth.json

@@ -1,16 +0,0 @@
-{
-  "skill": "editorial-calendar",
-  "domain": "content",
-  "_note": "Rubric domain-truth fixture (road-to-domain-soundness Phase 2, rubric target). The criterion names a CITED EXTERNAL practice/standard — NOT the skill's own output (blocker: domain-competence-for-answer-keys, option a). Authored as a maintainer-RATIFICATION CANDIDATE: rubric is NON-deterministic (pinned-judge known-limit); the Phase-3 run + --write-floor ratchet-pin + per-domain backed-CLAIMS remain the maintainer's gate.",
-  "cases": [
-    {
-      "id": "matches-content-pillar-practice",
-      "scenario": "Plan a content calendar for next quarter for our developer-tools blog.",
-      "source": "The content-pillar + audience-goal-cadence editorial-planning practice (standard content strategy).",
-      "check": {
-        "kind": "rubric",
-        "criterion": "Matches the content-pillar practice: themes tied to a named audience + a stated goal, an explicit publishing cadence, and pieces sequenced with dependencies - not a random list of topics."
-      }
-    }
-  ]
-}

package/dist/agent-src/skills/editorial-calendar/evals/evals.json

@@ -1,16 +0,0 @@
-{
-  "skill": "editorial-calendar",
-  "_calibration": "Behavioural fixture (road-to-skill-eval-coverage Phase 2, default-surface). Deterministic assertions on a real output property where reliable; rubric pins the qualitative core as a known-limit (pass ratified in PR review, not a hidden judge). finding_floor n is a conservative floor, not a calibrated per-host number.",
-  "scenarios": [
-    {
-      "id": "plan-content-calendar",
-      "prompt": "Plan a content calendar for next quarter for our dev-tools blog.",
-      "assertions": [
-        {
-          "kind": "rubric",
-          "criterion": "Grounds cadence + themes in a named audience + goal, sequences pieces with dependencies, not a random topic list."
-        }
-      ]
-    }
-  ]
-}

package/dist/agent-src/skills/eloquent/evals/triggers.json

@@ -1,17 +0,0 @@
-{
-  "skill": "eloquent",
-  "last_eval": "2026-06-16",
-  "description": "5 should-trigger + 5 should-not-trigger queries. A-class accepted ambiguity (e.g. 'User*' substring pulling eloquent alongside a non-Model intent) is marked with trigger=true and a note — the router loading eloquent is defensible, not a routing failure. Near-misses share Laravel/database vocabulary (migration, seeder, model, SQL) without being Model:: read/write tasks.",
-  "queries": [
-    {"q": "fetch all users with their latest order eagerly", "trigger": true},
-    {"q": "add a scope to Product that filters by active and in-stock", "trigger": true},
-    {"q": "my blog model should cast the tags column to array", "trigger": true},
-    {"q": "write a relationship from Invoice to LineItems using hasMany", "trigger": true},
-    {"q": "this N+1 is killing me — how do I eager load nested relations?", "trigger": true},
-    {"q": "create a migration for adding an index on users.email", "trigger": false},
-    {"q": "write a Pest test for the UserService", "trigger": true, "note": "A-class: 'User*' is inherently ambiguous (Model or Service). Router loading eloquent alongside pest-testing / php-service is defensible multi-skill activation, not a routing failure. Pushy 'NOT for non-Eloquent services' description tail was insufficient to override the lexical pull — see agents/reference/docs/trigger-evals-poc-findings.md #3"},
-    {"q": "phpstan says mixed return type on my model method", "trigger": false},
-    {"q": "run the seeder with --class=ProductSeeder", "trigger": false},
-    {"q": "what SQL does chunk() generate under the hood?", "trigger": false}
-  ]
-}

package/dist/agent-src/skills/estimate-ticket/evals/evals.json

@@ -1,16 +0,0 @@
-{
-  "skill": "estimate-ticket",
-  "_calibration": "Behavioural fixture (road-to-skill-eval-coverage Phase 2, default-surface). Deterministic assertions on a real output property where reliable; rubric pins the qualitative core as a known-limit (pass ratified in PR review, not a hidden judge). finding_floor n is a conservative floor, not a calibrated per-host number.",
-  "scenarios": [
-    {
-      "id": "estimate-ticket",
-      "prompt": "Estimate this ticket: add CSV export to the reports page.",
-      "assertions": [
-        {
-          "kind": "rubric",
-          "criterion": "Estimates from decomposed work + named unknowns/risks; gives a range or points, and does NOT invent a wall-clock duration."
-        }
-      ]
-    }
-  ]
-}

package/dist/agent-src/skills/estimate-ticket/evals/output-schema.yml

@@ -1,20 +0,0 @@
-# Output-schema contract for `estimate-ticket`.
-#
-# Locks the frozen three-section shape of the `## Output template`
-# block so refactors cannot silently drift the estimate output away
-# from what consumers copy-paste into Jira / sprint tooling. Enforced
-# by `scripts/skill_linter.py` (`lint_output_schema`) — a drift is a
-# hard error.
-#
-# `Split points` is intentionally omitted — it is conditional on
-# `Split: Yes` and not part of the always-present base shape.
-#
-# Governed by: road-to-trigger-evals.md Phase 3.5 (originally deferred
-# from archive/road-to-ticket-refinement.md Phase 1 per Q26).
-
-version: 1
-
-required_headers:
-  - "Estimate"
-  - "Sizing rationale"
-  - "Persona voices (sizing-focused)"

package/dist/agent-src/skills/estimate-ticket/evals/triggers.json

@@ -1,19 +0,0 @@
-{
-  "skill": "estimate-ticket",
-  "last_eval": "2026-06-16",
-  "version": 1,
-  "should_trigger": [
-    "estimate PROJ-123",
-    "how big is this ticket?",
-    "should we split this?",
-    "wie groß ist das Ticket?",
-    "sollen wir das splitten?"
-  ],
-  "should_not_trigger": [
-    "refine this ticket",
-    "plan this feature",
-    "is PROJ-123 a duplicate of anything we already have?",
-    "threat-model this change",
-    "investigate this bug"
-  ]
-}

package/dist/agent-src/skills/evaluate-llm-feature/evals/triggers.json

@@ -1,52 +0,0 @@
-{
-    "skill": "evaluate-llm-feature",
-    "last_eval": "2026-07-30",
-    "description": "5 should-trigger + 5 should-not-trigger queries. Should-trigger covers DE + EN phrasings for black-box evaluation of a SHIPPED consumer LLM feature — hallucination, prompt-injection and cost-runaway probes against stated expectations. Should-not-trigger covers the near-miss neighbours (this suite's own agent config red-team, LLM app-building/RAG, prompt authoring, the single-response injection judge, code security audit) whose vocabulary overlaps.",
-    "queries": [
-        {
-            "q": "review my support chatbot before launch — does it hallucinate or leak its system prompt?",
-            "trigger": true
-        },
-        {
-            "q": "is my summariser safe to ship? probe it for prompt injection through the documents it retrieves",
-            "trigger": true
-        },
-        {
-            "q": "evaluate my deployed AI assistant against what it claims to do and its token budget",
-            "trigger": true
-        },
-        {
-            "q": "teste meinen ausgelieferten KI-Assistenten adversarial auf Halluzinationen und Kosten-Runaway",
-            "trigger": true
-        },
-        {
-            "q": "our doc-QA feature invents API names — run adversarial probes and give me a ship / do-not-ship verdict",
-            "trigger": true
-        },
-        {
-            "q": "red-team my own agent setup — my CLAUDE.md, hooks and MCP servers",
-            "trigger": false,
-            "note": "config-layer red/blue review of this suite's agents, not a shipped consumer feature → agent-security-review"
-        },
-        {
-            "q": "what chunk size and embedding model should I use for my RAG pipeline?",
-            "trigger": false,
-            "note": "building an LLM app (explicitly out of mission for this skill); provider facts → llm-provider-knowledge, prompt design → prompt-engineering-patterns"
-        },
-        {
-            "q": "make this system prompt better — add few-shot examples and self-verification",
-            "trigger": false,
-            "note": "authoring/optimising a prompt, not evaluating a running feature → prompt-engineering-patterns / prompt-optimizer"
-        },
-        {
-            "q": "score whether this single agent response resisted the injected instruction",
-            "trigger": false,
-            "note": "one-response injection-resistance scoring on an axis, not a feature-wide probe campaign → judge-injection-defense"
-        },
-        {
-            "q": "audit the source code of our chat backend for vulnerabilities",
-            "trigger": false,
-            "note": "white-box code vulnerability hunt; this skill is black-box only → security-audit"
-        }
-    ]
-}

package/dist/agent-src/skills/existing-ui-audit/evals/triggers.json

@@ -1,47 +0,0 @@
-{
-    "skill": "existing-ui-audit",
-    "last_eval": "2026-07-10",
-    "description": "5 should-trigger + 5 should-not-trigger queries for the resource-first context gate (road-to-design-artifact-fidelity Phase 2). Should-trigger covers the four Phase-2 cases — redesign with code present, screenshot-only, no-assets/owned-UI, and an inaccessible referenced source — plus an improve-existing case; all require inventorying project context BEFORE styling rather than starting from aesthetic memory. Should-not-trigger covers near-miss neighbours whose vocabulary overlaps (backend/API, non-UI, general design knowledge, a genuinely trivial one-line UI edit) that must NOT force a full audit.",
-    "queries": [
-        {
-            "q": "redesign our dashboard — the React components are in src/components, make it cleaner",
-            "trigger": true
-        },
-        {
-            "q": "here is a screenshot of our current app, recreate this screen for us",
-            "trigger": true
-        },
-        {
-            "q": "rebuild our landing page in the same style as the rest of the product",
-            "trigger": true
-        },
-        {
-            "q": "match our Figma file at this link and rebuild the settings page (you may not be able to open it)",
-            "trigger": true
-        },
-        {
-            "q": "improve the UI of our existing checkout flow",
-            "trigger": true
-        },
-        {
-            "q": "add a rate limiter to the /orders API endpoint",
-            "trigger": false
-        },
-        {
-            "q": "write the SQL migration that adds a status column to the orders table",
-            "trigger": false
-        },
-        {
-            "q": "what is the difference between CSS flexbox and grid?",
-            "trigger": false
-        },
-        {
-            "q": "fix the typo in the README heading",
-            "trigger": false
-        },
-        {
-            "q": "explain how our CI release pipeline is structured",
-            "trigger": false
-        }
-    ]
-}

package/dist/agent-src/skills/experiment-loop/evals/output-schema.yml

@@ -1,27 +0,0 @@
-# Behavior-schema contract for `experiment-loop`.
-#
-# Locks the sections a refactor could quietly drop while the skill still
-# reads plausibly. Each one is a measured failure from spike s01
-# (agents/evidence/eval-findings/metric-loop-s01.md), not a style
-# preference:
-#
-#   The Iron Law  — `pass` sovereign over `score`; a change that improved
-#                   the metric 67% and broke behaviour was reverted only
-#                   because of it.
-#   Validation    — the both-branches-ran check; s01's revert path was
-#                   broken and four green iterations never noticed.
-#   Output format — the register-derived report; a report from memory is
-#                   the in-conversation state the register exists to replace.
-#   Do NOT        — the four keeps that must not happen.
-#
-# Enforced by `skill_linter` (`lint_output_schema`, matches `^## <header>$`) —
-# a missing section is a hard error.
-
-version: 1
-
-required_headers:
-  - "The Iron Law"
-  - "Procedure"
-  - "Validation"
-  - "Output format"
-  - "Do NOT"

package/dist/agent-src/skills/experiment-loop/evals/triggers.json

@@ -1,17 +0,0 @@
-{
-  "skill": "experiment-loop",
-  "last_eval": "2026-08-17",
-  "description": "5 should-trigger + 5 should-not-trigger. Should-trigger covers the bounded keep-or-revert loop against a SCALAR metric (direction, no destination). Should-not-trigger covers the near-miss neighbours the roadmap's gap-table names: iterate-to-a-known-end-state (verify-repair-loop), subjective craft with no scalar, a one-shot measurement, a one-shot review, and asking what a metric currently is.",
-  "queries": [
-    {"q": "minimize the bundle size, keep changes that help and revert the rest", "trigger": true},
-    {"q": "optimize this until it stops improving, bounded to ten tries", "trigger": true},
-    {"q": "drive the query count down across iterations and record what you kept", "trigger": true},
-    {"q": "run a keep-or-revert loop against the lint violation count", "trigger": true},
-    {"q": "reduce this metric as far as it goes without breaking the tests", "trigger": true},
-    {"q": "keep fixing until the tests pass", "trigger": false, "note": "a known end state, not a direction → verify-repair-loop"},
-    {"q": "iterate this change to green, run the suite each time", "trigger": false, "note": "converges toward a destination → verify-repair-loop"},
-    {"q": "is this diff clean — naming, structure, conventions?", "trigger": false, "note": "subjective craft, no scalar to optimize"},
-    {"q": "how big is the bundle right now?", "trigger": false, "note": "a single measurement, no loop"},
-    {"q": "review my changes before I open the PR", "trigger": false, "note": "one-shot review → /review-changes"}
-  ]
-}

package/dist/agent-src/skills/fe-design/evals/triggers.json

@@ -1,55 +0,0 @@
-{
-    "skill": "fe-design",
-    "last_eval": "2026-08-12",
-    "description": "Should-trigger covers BOTH halves of this skill's two modes: planning/exploration (give me directions, explore, plan the flow, pattern choice) AND — new — ad-hoc implementation, because outside a ticketed run no other artefact owns the design quality of a UI write. The implementation query used to be labelled should-not-trigger on the reasoning that it belongs to the apply step; that step only exists as a dispatch target inside the engine, so the label routed ad-hoc implementation prompts to nobody. Should-not-trigger keeps the genuine near-misses: inventorying existing UI (existing-ui-audit owns it in both modes), a ui-trivial one-line edit, and non-UI work.",
-    "queries": [
-        {
-            "q": "give me three directions for the pricing page",
-            "trigger": true
-        },
-        {
-            "q": "explore a few visual directions for the dashboard before we commit",
-            "trigger": true
-        },
-        {
-            "q": "design the multi-step onboarding flow",
-            "trigger": true
-        },
-        {
-            "q": "should this filter be a modal or an inline panel?",
-            "trigger": true
-        },
-        {
-            "q": "plan the responsive layout for the settings screen",
-            "trigger": true
-        },
-        {
-            "q": "implement the selected checkout design in React exactly as approved",
-            "trigger": true
-        },
-        {
-            "q": "build the settings page",
-            "trigger": true
-        },
-        {
-            "q": "improve this form, it feels clunky",
-            "trigger": true
-        },
-        {
-            "q": "what form components do we already have in the codebase?",
-            "trigger": false
-        },
-        {
-            "q": "change the primary button colour to green",
-            "trigger": false
-        },
-        {
-            "q": "add a database index on orders.status",
-            "trigger": false
-        },
-        {
-            "q": "fix the failing unit test in the auth module",
-            "trigger": false
-        }
-    ]
-}

package/dist/agent-src/skills/forecasting/evals/domain-truth.json

@@ -1,29 +0,0 @@
-{
-  "skill": "forecasting",
-  "domain": "finance",
-  "_note": "Deterministic domain-truth keys computed independently from cited standard forecast-construction formulas (NOT the skill's own output). Authored as maintainer-ratification candidates per road-to-domain-soundness Phase 2 (blocker: domain-competence-for-answer-keys); the Phase-3 run + --write-floor ratchet-pin remain the maintainer's gate.",
-  "cases": [
-    {
-      "id": "bottom-up-commit",
-      "scenario": "Bottom-up forecast. Commit-tagged pipeline total = $8.1M; in-window segment close rate = 78%. Compute the commit value = commit-tagged pipeline x in-window close rate. State the single figure in $M to three decimals.",
-      "source": "Bottom-up forecast construction: commit = sum(commit-tagged pipeline) x in-window close rate (standard finance/RevOps forecasting).",
-      "check": {
-        "kind": "deterministic",
-        "expected": 6.318,
-        "tolerance": 0.01,
-        "rationale": "8.1 x 0.78 = 6.318 ($M). Step 1 bottom-up: sum commit-tagged x in-window close-rate per segment."
-      }
-    },
-    {
-      "id": "top-down-arr",
-      "scenario": "Top-down forecast. Total addressable market (TAM) = $4.2B; expected penetration = 0.6%. Compute the top-down ARR = TAM x penetration. State the single figure in $M.",
-      "source": "Top-down forecast construction: ARR = TAM x penetration band (x motion band) (standard market-sizing).",
-      "check": {
-        "kind": "deterministic",
-        "expected": 25.2,
-        "tolerance": 0.05,
-        "rationale": "4,200,000,000 x 0.006 = 25,200,000 = $25.2M. Step 1 top-down: TAM x penetration band."
-      }
-    }
-  ]
-}

package/dist/agent-src/skills/forecasting/evals/evals.json

@@ -1,20 +0,0 @@
-{
-  "skill": "forecasting",
-  "_calibration": "Behavioural fixture (road-to-skill-eval-coverage Phase 2, default-surface). Deterministic assertions on a real output property where reliable; rubric pins the qualitative core as a known-limit (pass ratified in PR review, not a hidden judge). finding_floor n is a conservative floor, not a calibrated per-host number.",
-  "scenarios": [
-    {
-      "id": "reconcile-topdown-bottomup",
-      "prompt": "Top-down says $30M ARR, bottom-up commit sums to $8.1M for Q1. Build the forecast call.",
-      "assertions": [
-        {
-          "kind": "contains",
-          "value": "confidence"
-        },
-        {
-          "kind": "rubric",
-          "criterion": "States the construction shape (top-down/bottom-up/hybrid) and attaches a confidence band; when they diverge, the divergence IS the forecast — not either single number."
-        }
-      ]
-    }
-  ]
-}

package/dist/agent-src/skills/forensics-report/evals/triggers.json

@@ -1,17 +0,0 @@
-{
-    "skill": "forensics-report",
-    "last_eval": "2026-08-09",
-    "description": "5 should-trigger + 5 should-not-trigger. Should-trigger covers DE+EN phrasings for git-history release forensics (hotspot risk, change-coupling, release-review evidence). Should-not-trigger covers near-miss neighbours: security incident forensics (incident-commander), plain git log, runtime performance hotspots (performance-analysis), line blame, security audit.",
-    "queries": [
-        { "q": "which files are the riskiest hotspots in this release", "trigger": true },
-        { "q": "what files always change together", "trigger": true },
-        { "q": "run the forensics report for the release review", "trigger": true },
-        { "q": "zeig mir hotspot und coupling evidenz für das release", "trigger": true },
-        { "q": "machine-derived evidence for the release review", "trigger": true },
-        { "q": "do a forensic analysis of the security incident from last night", "trigger": false },
-        { "q": "show me the git log for the last week", "trigger": false },
-        { "q": "find the performance hotspots in production at runtime", "trigger": false },
-        { "q": "who wrote this line — run git blame on it", "trigger": false },
-        { "q": "run a security audit on the auth module", "trigger": false }
-    ]
-}

package/dist/agent-src/skills/frontend-render-security/evals/triggers.json

@@ -1,52 +0,0 @@
-{
-    "skill": "frontend-render-security",
-    "last_eval": "2026-07-09",
-    "description": "5 should-trigger + 5 should-not-trigger queries. Should-trigger covers DE + EN phrasings for client-side insecure-render / client-trust patterns (XSS, client secrets, client-only auth, CORS, localStorage tokens). Should-not-trigger covers near-miss neighbours (server-side security, generic checklist, accessibility-only, dependency intake) whose vocabulary overlaps.",
-    "queries": [
-        {
-            "q": "is it safe to render this user content with dangerouslySetInnerHTML?",
-            "trigger": true
-        },
-        {
-            "q": "review this Vue component for XSS and any secrets in the bundle",
-            "trigger": true
-        },
-        {
-            "q": "I'm storing the JWT in localStorage — is that ok?",
-            "trigger": true
-        },
-        {
-            "q": "prüf mein Frontend auf unsichere Render-Muster und Client-Secrets",
-            "trigger": true
-        },
-        {
-            "q": "my CORS is set to origin '*' with credentials — problem?",
-            "trigger": true
-        },
-        {
-            "q": "review this API controller's authorization logic",
-            "trigger": false,
-            "note": "server-side authz → authz-review / security-sensitive-stop"
-        },
-        {
-            "q": "what invisible controls did I omit across this whole diff?",
-            "trigger": false,
-            "note": "cross-surface checklist → ai-code-blindspots"
-        },
-        {
-            "q": "make this form accessible — keyboard nav and contrast",
-            "trigger": false,
-            "note": "accessibility only → accessibility-auditor"
-        },
-        {
-            "q": "is this frontend npm dependency real and safe to install?",
-            "trigger": false,
-            "note": "dependency intake → supply-chain-intake"
-        },
-        {
-            "q": "help me center this div with flexbox",
-            "trigger": false,
-            "note": "layout/styling — no security surface"
-        }
-    ]
-}

package/dist/agent-src/skills/fundraising-narrative/evals/domain-truth.json

@@ -1,16 +0,0 @@
-{
-  "skill": "fundraising-narrative",
-  "domain": "founder",
-  "_note": "Rubric domain-truth fixture (road-to-domain-soundness Phase 2, rubric target). The criterion names a CITED EXTERNAL practice/standard — NOT the skill's own output (blocker: domain-competence-for-answer-keys, option a). Authored as a maintainer-RATIFICATION CANDIDATE: rubric is NON-deterministic (pinned-judge known-limit); the Phase-3 run + --write-floor ratchet-pin + per-domain backed-CLAIMS remain the maintainer's gate.",
-  "cases": [
-    {
-      "id": "matches-venture-pitch-arc",
-      "scenario": "Draft the fundraising narrative for our seed round.",
-      "source": "The standard venture seed-pitch narrative arc (problem -> why-now -> insight/solution -> traction -> team -> ask), the widely-taught pitch-structure convention.",
-      "check": {
-        "kind": "rubric",
-        "criterion": "Matches the standard venture pitch arc: problem, why-now, insight/solution, traction evidence, team, and a specific ask; surfaces the key risk and issues NO invest/raise verdict (finance safety floor) - not a feature list or an unopposed hype narrative."
-      }
-    }
-  ]
-}

package/dist/agent-src/skills/fundraising-narrative/evals/evals.json

@@ -1,16 +0,0 @@
-{
-  "skill": "fundraising-narrative",
-  "_calibration": "Behavioural fixture (road-to-skill-eval-coverage Phase 2, default-surface). Deterministic assertions on a real output property where reliable; rubric pins the qualitative core as a known-limit (pass ratified in PR review, not a hidden judge). finding_floor n is a conservative floor, not a calibrated per-host number.",
-  "scenarios": [
-    {
-      "id": "raise-narrative",
-      "prompt": "Draft the fundraising narrative for our seed round.",
-      "assertions": [
-        {
-          "kind": "rubric",
-          "criterion": "Builds a narrative around traction + why-now + why-us with a stated ask; surfaces the risk, does not issue a raise/don't-raise verdict (finance safety floor)."
-        }
-      ]
-    }
-  ]
-}