@event4u/agent-config 14.11.0 → 14.12.0

package/dist/agent-src/skills/license-compliance-borrow-check/evals/triggers.json

@@ -1,52 +0,0 @@
-{
-    "skill": "license-compliance-borrow-check",
-    "last_eval": "2026-07-28",
-    "description": "5 should-trigger + 5 should-not-trigger queries. Should-trigger covers pasting a source URL/repo to check its license before borrowing, and asking whether a specific borrow is allowed. Should-not-trigger covers near-miss neighbours (regenerating notices, running a broad similarity scan, generic new-dependency intake, plain code review) whose vocabulary overlaps.",
-    "queries": [
-        {
-            "q": "I want to adapt this retry-loop from https://github.com/example/repo — is its license compatible with ours?",
-            "trigger": true
-        },
-        {
-            "q": "this Stack Overflow answer has the algorithm I need, check if I can use it before I write the code",
-            "trigger": true
-        },
-        {
-            "q": "can I borrow this LRU cache implementation, it's under GPL-3.0?",
-            "trigger": true
-        },
-        {
-            "q": "draft a ledger entry for the debounce helper I ported from another repo",
-            "trigger": true
-        },
-        {
-            "q": "what license does this vendored snippet carry and does it clear our policy?",
-            "trigger": true
-        },
-        {
-            "q": "regenerate the third-party notices file, the ledger just changed",
-            "trigger": false,
-            "note": "notices regeneration → license-compliance-credits"
-        },
-        {
-            "q": "run a similarity scan across the whole diff to check for copied code",
-            "trigger": false,
-            "note": "broad corpus scan, no single named source → license-compliance-audit"
-        },
-        {
-            "q": "add lodash to package.json and install it",
-            "trigger": false,
-            "note": "new dependency intake, not a code borrow → supply-chain-intake"
-        },
-        {
-            "q": "review this diff for correctness and style issues",
-            "trigger": false,
-            "note": "generic code review, no borrow involved"
-        },
-        {
-            "q": "what CVEs affect the version of this package we're pinned to?",
-            "trigger": false,
-            "note": "dependency vulnerability scanning, not licensing a borrow"
-        }
-    ]
-}

package/dist/agent-src/skills/license-compliance-credits/evals/triggers.json

@@ -1,52 +0,0 @@
-{
-    "skill": "license-compliance-credits",
-    "last_eval": "2026-07-28",
-    "description": "5 should-trigger + 5 should-not-trigger queries. Should-trigger covers regenerating THIRD-PARTY-NOTICES.md after a ledger change, and asking whether notices are in sync. Should-not-trigger covers near-miss neighbours (drafting a new ledger entry, running a similarity scan, generic changelog/readme updates) whose vocabulary overlaps.",
-    "queries": [
-        {
-            "q": "the borrows ledger just got a new entry, regenerate the notices file",
-            "trigger": true
-        },
-        {
-            "q": "are our third-party notices up to date with provenance/borrows.jsonl?",
-            "trigger": true
-        },
-        {
-            "q": "lint_provenance says NOTICES.md is out of sync, fix that",
-            "trigger": true
-        },
-        {
-            "q": "regenerate the credits file from the ledger",
-            "trigger": true
-        },
-        {
-            "q": "rebuild THIRD-PARTY-NOTICES.md after I appended to borrows.jsonl",
-            "trigger": true
-        },
-        {
-            "q": "draft a new ledger entry for this snippet I want to borrow from an MIT repo",
-            "trigger": false,
-            "note": "new borrow drafting → license-compliance-borrow-check"
-        },
-        {
-            "q": "scan this diff for copied code against known OSS",
-            "trigger": false,
-            "note": "similarity scan → license-compliance-audit"
-        },
-        {
-            "q": "update the CHANGELOG for this release",
-            "trigger": false,
-            "note": "unrelated generated doc, not the provenance ledger"
-        },
-        {
-            "q": "add a new section to the README about installation",
-            "trigger": false,
-            "note": "generic README editing, no ledger involved"
-        },
-        {
-            "q": "check whether this dependency's license is compatible with GPL",
-            "trigger": false,
-            "note": "license compatibility check on a new dep, not notices regeneration"
-        }
-    ]
-}

package/dist/agent-src/skills/llm-provider-knowledge/evals/triggers.json

@@ -1,20 +0,0 @@
-{
-  "skill": "llm-provider-knowledge",
-  "last_eval": "2026-07-14",
-  "description": "7 should-trigger + 6 should-not-trigger. Should-trigger covers specific product-fact claims (context window, pricing, rate limit, API detail, model spec, consumer-app plan limit) across OpenAI, Google, Anthropic, Mistral, DeepSeek, Cohere. Should-not-trigger covers near-misses: SDK wiring with a user-supplied model, prompt authoring (prompt-engineering-patterns), model choice for the host (model-recommendation), image-provider selection (image-provider-routing), a user-supplied fact, and a plain SDK refactor.",
-  "queries": [
-    {"q": "what's the context window of GPT-5?", "trigger": true},
-    {"q": "how much does Gemini 2.5 Pro cost per million input tokens?", "trigger": true},
-    {"q": "what are the rate limits on the Anthropic API for tier 1?", "trigger": true},
-    {"q": "does the Mistral API support function calling, and what parameter enables it?", "trigger": true},
-    {"q": "what's the max output length for DeepSeek's chat model?", "trigger": true},
-    {"q": "how many messages does ChatGPT Plus allow in the app per window?", "trigger": true},
-    {"q": "what embedding dimension does Cohere's embed model return?", "trigger": true},
-    {"q": "wire up an openai chat completions call using the model id I already gave you", "trigger": false, "note": "SDK wiring; user supplied the model — no unverified product fact asserted"},
-    {"q": "write a good prompt to make Gemini summarize this document", "trigger": false, "note": "prompt authoring → prompt-engineering-patterns"},
-    {"q": "which model should I use for this task on my current host?", "trigger": false, "note": "model choice → model-recommendation (never steer to another vendor)"},
-    {"q": "route this logo-with-text image to the right generation provider", "trigger": false, "note": "image-provider selection → image-provider-routing"},
-    {"q": "I already know Claude Sonnet has a 200k context window — just use that number", "trigger": false, "note": "user supplied the verified fact; use it, do not re-litigate"},
-    {"q": "refactor this function that calls the Anthropic SDK to add retries", "trigger": false, "note": "plain code refactor; asserts no product fact"}
-  ]
-}

package/dist/agent-src/skills/logging-monitoring/evals/evals.json

@@ -1,16 +0,0 @@
-{
-  "skill": "logging-monitoring",
-  "_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": "add-logging-endpoint",
-      "prompt": "Add logging to this login endpoint so we can debug failures.",
-      "assertions": [
-        {
-          "kind": "rubric",
-          "criterion": "Logs allowlisted structured fields (user_id, request_id, outcome) — never the raw request/credential/PII; the credential never reaches the log stream."
-        }
-      ]
-    }
-  ]
-}

package/dist/agent-src/skills/logo-generation/evals/triggers.json

@@ -1,17 +0,0 @@
-{
-  "skill": "logo-generation",
-  "last_eval": "2026-06-16",
-  "description": "5 should-trigger + 5 should-not-trigger. Should-trigger covers end-to-end logo / brand mark generation requests. Should-not-trigger covers near-miss neighbors: general image generation (image-generation), banner/social asset production (brand-asset-generation), routing-only questions (image-provider-routing), prompt-authoring-only (prompt-engineering-image), and rights checks (image-likeness-and-rights).",
-  "queries": [
-    {"q": "generate a logo for my bakery called Golden Crust", "trigger": true},
-    {"q": "create a brand mark for our SaaS startup — minimalist, dark blue, no text", "trigger": true},
-    {"q": "I need a vector SVG logo for our coffee shop", "trigger": true},
-    {"q": "design a wordmark logo for our law firm with clean sans-serif type", "trigger": true},
-    {"q": "produce a combination mark logo — icon plus company name — for our fitness app", "trigger": true},
-    {"q": "generate a hero image for our homepage", "trigger": false, "note": "general image generation → image-generation"},
-    {"q": "create a banner for our bakery's Instagram with the seasonal offer", "trigger": false, "note": "social/banner asset → brand-asset-generation"},
-    {"q": "which provider should I use for a logo with text inside?", "trigger": false, "note": "routing-only question → image-provider-routing"},
-    {"q": "write me a Recraft prompt for a minimalist geometric logo mark", "trigger": false, "note": "prompt authoring only → prompt-engineering-image"},
-    {"q": "can I use a design that looks like the Apple logo as inspiration for my mark?", "trigger": false, "note": "rights / trademark check → image-likeness-and-rights"}
-  ]
-}

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

@@ -1,16 +0,0 @@
-{
-  "skill": "messaging-architecture",
-  "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-message-house-model",
-      "scenario": "Design the messaging architecture for our product launch.",
-      "source": "The message-house framework (one core message -> supporting pillars -> proof points per pillar) + positioning-before-messaging (Dunford, 'Obviously Awesome').",
-      "check": {
-        "kind": "rubric",
-        "criterion": "Matches the message-house model: exactly one core message, a small set of supporting pillars, and concrete proof points under each pillar, grounded in a NAMED target audience - not a flat list of slogans or adjectives."
-      }
-    }
-  ]
-}

package/dist/agent-src/skills/messaging-architecture/evals/evals.json

@@ -1,16 +0,0 @@
-{
-  "skill": "messaging-architecture",
-  "_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": "design-messaging",
-      "prompt": "Design the messaging architecture for our product.",
-      "assertions": [
-        {
-          "kind": "rubric",
-          "criterion": "Produces a layered message hierarchy (core → pillars → proof) grounded in a named audience, not generic slogans."
-        }
-      ]
-    }
-  ]
-}

package/dist/agent-src/skills/monorepo-workspace/evals/triggers.json

@@ -1,17 +0,0 @@
-{
-  "skill": "monorepo-workspace",
-  "last_eval": "2026-08-23",
-  "description": "5 should-trigger + 5 should-not-trigger. Should-trigger covers structural orientation in a workspace repository: the dependency graph between workspaces, the task runner's own task list, and which workspace owns a path. Should-not-trigger covers near-miss neighbors: authoring a component (the UI lane routes on state.stack.scope_root, not on this skill), a cross-workspace edit's impact set (blast-radius-analyzer § Monorepo), an unresolved workspace import (workspace-link), single-repo dependency questions, and coding-standards questions (standards-from-config).",
-  "queries": [
-    {"q": "which packages depend on @org/ui", "trigger": true},
-    {"q": "what workspaces are in this monorepo and which package manager does it use", "trigger": true},
-    {"q": "what does the build task actually run here", "trigger": true},
-    {"q": "list the nx projects in this repo", "trigger": true},
-    {"q": "which workspace owns packages/ui/src/button.tsx", "trigger": true},
-    {"q": "add a button", "trigger": false, "note": "authoring a component; the UI lane routes on state.stack.scope_root"},
-    {"q": "what breaks if I change this shared type in packages/ui", "trigger": false, "note": "impact set of an edit → blast-radius-analyzer § Monorepo"},
-    {"q": "cannot find module @org/ui when I import it", "trigger": false, "note": "unresolved workspace import → workspace-link"},
-    {"q": "what version of react does this project use", "trigger": false, "note": "a single dependency lookup, no workspace structure involved"},
-    {"q": "what line length does this project use", "trigger": false, "note": "coding standards from tooling config → standards-from-config"}
-  ]
-}

package/dist/agent-src/skills/nda-triage/evals/triggers.json

@@ -1,17 +0,0 @@
-{
-    "skill": "nda-triage",
-    "last_eval": "2026-06-24",
-    "description": "5 should-trigger + 5 should-not-trigger. Should-trigger covers DE+EN phrasings for fast GREEN/YELLOW/RED triage of an inbound NDA. Should-not-trigger covers near-miss neighbours: full clause review (contract-review), DPA review (dpa-review), legal triage (legal-intake-triage), profile setup.",
-    "queries": [
-        { "q": "check this NDA — can we sign it as-is?", "trigger": true },
-        { "q": "triage this inbound NDA: standard-approve, counsel, or full review?", "trigger": true },
-        { "q": "ist diese Geheimhaltungsvereinbarung Standard oder muss ein Anwalt drauf schauen?", "trigger": true },
-        { "q": "quick GREEN/YELLOW/RED on this mutual NDA", "trigger": true },
-        { "q": "kriegen wir diese NDA durch oder eskalieren?", "trigger": true },
-        { "q": "do a full clause-by-clause redline of this MSA", "trigger": false },
-        { "q": "review this DPA as processor against Art. 28", "trigger": false },
-        { "q": "is this a legal problem we need counsel for at all?", "trigger": false },
-        { "q": "configure our NDA standard positions", "trigger": false },
-        { "q": "summarize this PDF for the board", "trigger": false }
-    ]
-}

package/dist/agent-src/skills/operational-readiness/evals/triggers.json

@@ -1,17 +0,0 @@
-{
-  "skill": "operational-readiness",
-  "last_eval": "2026-08-23",
-  "description": "5 should-trigger + 5 should-not-trigger. Should-trigger covers adjudicating a go/no-go from typed evidence and the one-red floor. Should-not-trigger covers the neighbours that PRODUCE the evidence rather than adjudicate it (logging-monitoring, alerting-doctrine, server-hardening), the pre-merge release checklist (launch-readiness) and an incident already running (incident-commander).",
-  "queries": [
-    {"q": "are we operationally ready to run this in production?", "trigger": true},
-    {"q": "give me a go/no-go verdict from what we know about this service", "trigger": true},
-    {"q": "four checks are green and one is red — what is the overall verdict?", "trigger": true},
-    {"q": "can we call this ready if we never inspected the host?", "trigger": true},
-    {"q": "adjudicate operational readiness for the payments service", "trigger": true},
-    {"q": "which Golden Signal is this project missing?", "trigger": false, "note": "produces the observability evidence → logging-monitoring"},
-    {"q": "should this alert wake the on-call engineer?", "trigger": false, "note": "alert classification → alerting-doctrine"},
-    {"q": "write the pre-merge checklist and rollout plan for this release", "trigger": false, "note": "pre-merge release procedure → launch-readiness"},
-    {"q": "we are in an outage right now, who does what?", "trigger": false, "note": "incident already running → incident-commander"},
-    {"q": "configure the firewall baseline on the new server", "trigger": false, "note": "host hardening execution → server-hardening"}
-  ]
-}

package/dist/agent-src/skills/pdf-tools/evals/triggers.json

@@ -1,52 +0,0 @@
-{
-    "skill": "pdf-tools",
-    "last_eval": "2026-07-30",
-    "description": "5 should-trigger + 5 should-not-trigger queries. Should-trigger covers DE + EN phrasings for PDF write/transform work the skill owns — merge / split / rotate / encrypt, AcroForm fill + flatten decision, create-from-content, structured text/table extraction and OCR of a text-layer-less scan. Should-not-trigger covers the near-miss neighbours (PDF→Markdown ingestion, image OCR, Word authoring, spreadsheet authoring, legal document triage) whose vocabulary overlaps.",
-    "queries": [
-        {
-            "q": "merge these three PDFs into one file and drop the duplicate cover page",
-            "trigger": true
-        },
-        {
-            "q": "fill this AcroForm PDF with the applicant values, then flatten it so it ships as final",
-            "trigger": true
-        },
-        {
-            "q": "split the PDF into one file per page and rotate the landscape ones",
-            "trigger": true
-        },
-        {
-            "q": "erstelle aus diesem Inhalt ein PDF und verschlüssele es mit einem Passwort",
-            "trigger": true
-        },
-        {
-            "q": "extract the tables from this PDF — OCR the pages if there is no text layer",
-            "trigger": true
-        },
-        {
-            "q": "convert this PDF to Markdown so I can read it in the repo",
-            "trigger": false,
-            "note": "PDF → Markdown ingestion, not a PDF write/transform → markitdown"
-        },
-        {
-            "q": "OCR this screenshot into text for me",
-            "trigger": false,
-            "note": "OCR of a standalone image, not of a scanned PDF's rasterized pages → markitdown"
-        },
-        {
-            "q": "generate a Word document from this template and fill in the placeholders",
-            "trigger": false,
-            "note": "Word .docx authoring / template fill → docx-authoring"
-        },
-        {
-            "q": "build me a spreadsheet model from these numbers with formulas instead of hardcoded values",
-            "trigger": false,
-            "note": "spreadsheet / model authoring → spreadsheet-authoring"
-        },
-        {
-            "q": "review this NDA PDF and flag the risky clauses",
-            "trigger": false,
-            "note": "the PDF is only the container; the ask is legal clause triage → nda-triage"
-        }
-    ]
-}

package/dist/agent-src/skills/perf-feedback-craft/evals/evals.json

@@ -1,16 +0,0 @@
-{
-  "skill": "perf-feedback-craft",
-  "_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": "perf-review-feedback",
-      "prompt": "Give this engineer performance feedback: they ship fast but skip tests.",
-      "assertions": [
-        {
-          "kind": "rubric",
-          "criterion": "Names the specific behaviour + its impact with an example, is balanced (strength + growth), and gives an actionable next step — not vague praise/blame."
-        }
-      ]
-    }
-  ]
-}

package/dist/agent-src/skills/persona-improvement/evals/triggers.json

@@ -1,52 +0,0 @@
-{
-    "skill": "persona-improvement",
-    "last_eval": "2026-07-30",
-    "description": "5 should-trigger + 5 should-not-trigger queries. Should-trigger covers DE + EN phrasings for an explicit request to refine an EXISTING persona's Unique Questions from a correction sample (≥ 3 misses the lens should have caught). Should-not-trigger covers the near-miss neighbours (new-persona authoring, the governance rule, the skill-side improvement pipeline, skill description tuning, persona scope changes) whose vocabulary overlaps.",
-    "queries": [
-        {
-            "q": "improve this persona — its review lens keeps missing the same class of bug",
-            "trigger": true
-        },
-        {
-            "q": "refine the reviewer persona's Unique Questions from the last few review misses",
-            "trigger": true
-        },
-        {
-            "q": "schärfe die Unique Questions dieser Persona anhand der letzten Korrekturen nach",
-            "trigger": true
-        },
-        {
-            "q": "the security persona missed tenant scoping three times now — tighten its questions so it fires next time",
-            "trigger": true
-        },
-        {
-            "q": "here are four corrections the architecture lens should have surfaced; sharpen that lens against them",
-            "trigger": true
-        },
-        {
-            "q": "create a new persona for a database reviewer voice",
-            "trigger": false,
-            "note": "authoring a NEW persona file (voice / focus / output expectations), not refining an existing lens → persona-writing"
-        },
-        {
-            "q": "can I add a third specialist persona to this domain, or do I have to deprecate one?",
-            "trigger": false,
-            "note": "per-domain cap / citation floor / deprecation path question → persona-governance (rule)"
-        },
-        {
-            "q": "the persona should now also cover frontend performance, widen its scope",
-            "trigger": false,
-            "note": "identity / scope change is a new-id change, explicitly out of this loop's scope → persona-governance (rule)"
-        },
-        {
-            "q": "run the skill improvement pipeline now that we captured that learning",
-            "trigger": false,
-            "note": "skill-side capture → classify → create → validate → apply loop, not the persona analog → skill-improvement-pipeline"
-        },
-        {
-            "q": "this skill's description is too vague, rewrite it so it triggers reliably",
-            "trigger": false,
-            "note": "SKILL.md description / trigger tuning, not a persona's Unique Questions → description-assist (authoring rules in skill-writing)"
-        }
-    ]
-}

package/dist/agent-src/skills/php-coder/evals/triggers.json

@@ -1,17 +0,0 @@
-{
-  "skill": "php-coder",
-  "last_eval": "2026-06-16",
-  "description": "5 should-trigger + 5 should-not-trigger queries. Multi-skill co-activation (e.g. php-coder alongside pest-testing on a test query) is accepted as TP where writing PHP code is a legitimate sub-task. Near-misses share PHP/Laravel vocabulary without being code-generation tasks.",
-  "queries": [
-    {"q": "my UserController is getting huge, split it into a service", "trigger": true},
-    {"q": "write a class for parsing CSV files with proper type hints", "trigger": true},
-    {"q": "refactor this foreach to use array_map but keep it readable", "trigger": true},
-    {"q": "add a __toString method to this DTO and make fields readonly", "trigger": true},
-    {"q": "this legacy controller mixes config and business logic, clean it up", "trigger": true},
-    {"q": "run phpstan on this file and show me all errors", "trigger": false},
-    {"q": "create a migration for adding a phone column to users", "trigger": false},
-    {"q": "set up docker-compose for this PHP project", "trigger": false},
-    {"q": "write a Pest test for the UserRepository", "trigger": true, "note": "T-class: co-activation with pest-testing is accepted — Pest tests are PHP code, loading php-coder alongside pest-testing is legitimate multi-skill support"},
-    {"q": "explain what strict_types does in PHP", "trigger": false}
-  ]
-}

package/dist/agent-src/skills/prediction-pool-optimizer/evals/triggers.json

@@ -1,21 +0,0 @@
-{
-  "skill": "prediction-pool-optimizer",
-  "last_eval": "2026-06-16",
-  "description": "9 should-trigger + 5 should-not-trigger queries. Should-trigger covers DE + EN phrasings and the core intent (pool tips, kicktipp, expected-points optimization across sports, plus answering the bonus / award questions and using bookmaker-consensus odds). Should-not-trigger covers near-miss neighbours: regulated financial advice (finance pack), plain match-result prediction with no pool, generic web research, AI video, and real-money sportsbook betting (out of scope / refuse).",
-  "queries": [
-    {"q": "optimize my kicktipp tips for the football WM 2026", "trigger": true},
-    {"q": "fill my company Tippspiel for the basketball world cup", "trigger": true},
-    {"q": "welche Tipps maximieren meine Punkte im kicktipp-Tippspiel?", "trigger": true},
-    {"q": "best picks for our office prediction pool given the scoring rules", "trigger": true},
-    {"q": "maximiere meine erwarteten Punkte im Tippspiel, nicht nur wer gewinnt", "trigger": true},
-    {"q": "predict our office kicktipp pool for the WM", "trigger": true},
-    {"q": "mach mein Tippspiel für die WM", "trigger": true},
-    {"q": "beantworte auch alle Bonusfragen im kicktipp, z.B. welche Mannschaft den Torschützenkönig stellt", "trigger": true},
-    {"q": "use the odds from the big betting sites to optimize my pool picks", "trigger": true},
-    {"q": "should we invest in this startup based on a DCF?", "trigger": false, "note": "regulated financial valuation → dcf-modeling / finance pack"},
-    {"q": "who will win tonight's match?", "trigger": false, "note": "plain result prediction, no pool / no scoring rules to optimize"},
-    {"q": "research the best running shoes for me", "trigger": false, "note": "generic web research → research / deep-research"},
-    {"q": "make a hype video for the world cup final", "trigger": false, "note": "AI video pipeline → /video"},
-    {"q": "place a €50 bet on the favourite at my bookmaker", "trigger": false, "note": "real-money sportsbook wagering — out of scope, not what this fun pool tool does"}
-  ]
-}

package/dist/agent-src/skills/prompt-engineering-image/evals/triggers.json

@@ -1,17 +0,0 @@
-{
-  "skill": "prompt-engineering-image",
-  "last_eval": "2026-06-16",
-  "description": "5 should-trigger + 5 should-not-trigger. Should-trigger covers translating a brief into provider-specific prompt grammar. Should-not-trigger covers near-miss neighbors: provider selection (image-provider-routing), direct adapter invocation, media rights checks (media-governance-routing / image-likeness-and-rights), and general image editing.",
-  "queries": [
-    {"q": "write me an Ideogram prompt for a bakery logo with the name on it", "trigger": true},
-    {"q": "how do I structure a Flux prompt for a photoreal product shot?", "trigger": true},
-    {"q": "my Recraft prompt isn't generating SVG — what params am I missing?", "trigger": true},
-    {"q": "tune this prompt for Gemini image generation: artisan bread, rustic kitchen", "trigger": true},
-    {"q": "what's the right prompt grammar for GPT Image 2 when editing a background?", "trigger": true},
-    {"q": "which image provider should I use for a logo with text?", "trigger": false, "note": "provider selection question → image-provider-routing"},
-    {"q": "run the Ideogram adapter with my prompt", "trigger": false, "note": "direct adapter invocation — not prompt authoring"},
-    {"q": "can I put a celebrity's face in this image?", "trigger": false, "note": "likeness rights question → media-governance-routing / image-likeness-and-rights"},
-    {"q": "remove the background from this photo", "trigger": false, "note": "editing request, not prompt authoring for a provider"},
-    {"q": "what lifecycle tier is the Recraft adapter?", "trigger": false, "note": "lifecycle tier query → provider-lifecycle-discipline"}
-  ]
-}

package/dist/agent-src/skills/prompt-engineering-patterns/evals/evals.json

@@ -1,16 +0,0 @@
-{
-  "skill": "prompt-engineering-patterns",
-  "_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": "apply-prompt-pattern",
-      "prompt": "Which prompting pattern should I use to get structured extraction from messy text, and why?",
-      "assertions": [
-        {
-          "kind": "rubric",
-          "criterion": "Names a concrete pattern (e.g. schema-constrained/structured-output, few-shot) matched to the extraction task, with the trade-off — not a generic tips list."
-        }
-      ]
-    }
-  ]
-}

package/dist/agent-src/skills/prompt-validator/evals/triggers.json

@@ -1,17 +0,0 @@
-{
-  "skill": "prompt-validator",
-  "last_eval": "2026-06-16",
-  "description": "5 should-trigger + 5 should-not-trigger queries. Should-trigger covers the pre-spend batch-contradiction gate (style / character / physics / lip-sync ownership). Should-not-trigger covers near-miss neighbors: single-prompt craft (video-director), LLM prompt tuning (prompt-optimizer / prompt-engineering-patterns), and vocal-map validation (validate-vocal-map.sh path).",
-  "queries": [
-    {"q": "validate the prompts before we render", "trigger": true},
-    {"q": "check the storyboard for contradictions", "trigger": true},
-    {"q": "do the scene prompts contradict each other?", "trigger": true},
-    {"q": "run the contradiction gate over the whole batch", "trigger": true},
-    {"q": "scene 5 says blue jacket but the character lock says red coat — check the full set", "trigger": true},
-    {"q": "improve this prompt for better image quality", "trigger": false, "note": "single-prompt craft — video-director / image prompting"},
-    {"q": "write the prompt for scene 3", "trigger": false, "note": "prompt authoring, not cross-scene validation"},
-    {"q": "validate the vocal map against the transcript", "trigger": false, "note": "validate-vocal-map.sh / song-to-script Step 3, not prompt contradiction"},
-    {"q": "review my ChatGPT system prompt", "trigger": false, "note": "routes to prompt-optimizer"},
-    {"q": "optimize the prompt for the LLM router", "trigger": false, "note": "routes to prompt-engineering-patterns"}
-  ]
-}

package/dist/agent-src/skills/quality-tools/evals/evals.json

@@ -1,15 +0,0 @@
-{
-  "skill": "quality-tools",
-  "_calibration": "Seed for eval-schema v2 (ecosystem-harvest skill-quality-gates Phase 2). tool-choice + trajectory assertions are trace-gated: pass:null (manual-pending) in CI until a recorded tool-trace.json exists.",
-  "scenarios": [
-    {
-      "id": "runs-project-pinned-tools",
-      "prompt": "Fix the failing lint on the changed files.",
-      "environment": "a project whose pinned quality CLI is defined in its task runner",
-      "assertions": [
-        { "kind": "tool-choice", "must_use": ["bash"], "must_not_use": [] },
-        { "kind": "trajectory_budget", "n": 8 }
-      ]
-    }
-  ]
-}

package/dist/agent-src/skills/reasoning-orchestrator/evals/triggers.json

@@ -1,17 +0,0 @@
-{
-  "skill": "reasoning-orchestrator",
-  "last_eval": "2026-06-16",
-  "description": "5 should-trigger + 5 should-not-trigger. Should-trigger covers complex / ambiguous / long-horizon work on a standard host where the reasoning steps are interdependent; should-not covers trivial / linear tasks, strong-host self-coordination, and single-discipline neighbors.",
-  "queries": [
-    {"q": "refactor the entire billing module to be cleaner and safer", "trigger": true},
-    {"q": "build this feature end to end from a vague brief — figure out the steps", "trigger": true},
-    {"q": "investigate this flaky multi-service failure and fix it properly", "trigger": true},
-    {"q": "take this ambiguous ticket and drive it to a verified implementation", "trigger": true},
-    {"q": "plan and implement the migration with checks at each stage", "trigger": true},
-    {"q": "rename this variable", "trigger": false, "note": "trivial — gate off"},
-    {"q": "format this file", "trigger": false, "note": "trivial"},
-    {"q": "just write the regex for an email", "trigger": false, "note": "single linear step"},
-    {"q": "only run the test suite and report", "trigger": false, "note": "single-discipline (verify), no chain to coordinate"},
-    {"q": "add a one-line log statement here", "trigger": false, "note": "trivial"}
-  ]
-}

package/dist/agent-src/skills/refine-prompt/evals/evals.json

@@ -1,16 +0,0 @@
-{
-  "skill": "refine-prompt",
-  "_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": "refine-a-prompt",
-      "prompt": "Improve this prompt: 'write good marketing copy'.",
-      "assertions": [
-        {
-          "kind": "rubric",
-          "criterion": "Adds role, concrete task, constraints, and success criteria; removes vague adjectives — a measurably tighter prompt, not a paraphrase."
-        }
-      ]
-    }
-  ]
-}

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

@@ -1,16 +0,0 @@
-{
-  "skill": "refine-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": "refine-ticket-dor",
-      "prompt": "Refine this ticket: 'make search better'.",
-      "assertions": [
-        {
-          "kind": "rubric",
-          "criterion": "Tightens to a bounded scope with acceptance criteria + a definition-of-ready; asks the one blocking question rather than guessing scope."
-        }
-      ]
-    }
-  ]
-}

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

@@ -1,16 +0,0 @@
-# Output-schema contract for `refine-ticket`.
-#
-# Locks the frozen three-section shape of the `## Output template`
-# block so refactors cannot silently drift the output away from what
-# consumers copy-paste into Jira. Enforced by `scripts/skill_linter.py`
-# (`lint_output_schema`) — a drift is a hard error.
-#
-# 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:
-  - "Refined ticket"
-  - "Top-5 risks"
-  - "Persona voices"

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

@@ -1,17 +0,0 @@
-{
-  "skill": "refine-ticket",
-  "last_eval": "2026-06-16",
-  "description": "5 should-trigger + 5 should-not-trigger queries. Should-trigger covers DE + EN phrasings and the four input paths (key, branch, paste, URL). Should-not-trigger covers the four near-miss neighbors (plan / estimate / duplicate / threat-model / bug-investigate) whose vocabulary overlaps with ticket refinement.",
-  "queries": [
-    {"q": "refine this ticket before I plan it", "trigger": true},
-    {"q": "tighten the AC on PROJ-123", "trigger": true},
-    {"q": "is this ticket ready for planning?", "trigger": true},
-    {"q": "verbessere das Ticket, ist das klar genug?", "trigger": true},
-    {"q": "poke holes in this Jira ticket and rewrite it", "trigger": true},
-    {"q": "plan the feature described in PROJ-123", "trigger": false, "note": "routes to /feature-plan, not refinement"},
-    {"q": "estimate how big PROJ-123 is", "trigger": false, "note": "routes to /estimate-ticket (Phase 4 sibling)"},
-    {"q": "is this feature already implemented somewhere?", "trigger": false, "note": "routes to validate-feature-fit directly"},
-    {"q": "threat-model the webhook endpoint in PROJ-123", "trigger": false, "note": "routes to threat-modeling directly"},
-    {"q": "investigate this bug — I think there's a Sentry issue linked", "trigger": false, "note": "routes to /bug-investigate"}
-  ]
-}

package/dist/agent-src/skills/release-comms/evals/evals.json

@@ -1,16 +0,0 @@
-{
-  "skill": "release-comms",
-  "_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": "write-release-note",
-      "prompt": "Write the release announcement for our v-next dashboard redesign.",
-      "assertions": [
-        {
-          "kind": "rubric",
-          "criterion": "Leads with user value + what changed, notes any migration/breaking step, and matches the product voice — not a raw changelog dump."
-        }
-      ]
-    }
-  ]
-}