@event4u/agent-config 14.11.0 → 14.13.0

package/dist/agent-src/skills/ai-code-blindspots/evals/triggers.json

@@ -1,52 +0,0 @@
-{
-    "skill": "ai-code-blindspots",
-    "last_eval": "2026-07-09",
-    "description": "5 should-trigger + 5 should-not-trigger queries. Should-trigger covers DE + EN phrasings for the pre-ship 'what invisible cross-cutting controls did the AI omit?' checklist across code surfaces. Should-not-trigger covers near-miss neighbours (deep single-surface skills, prose/docs edits, adversarial config review) whose vocabulary overlaps.",
-    "queries": [
-        {
-            "q": "I just wrote this endpoint — what invisible controls did I forget before I call it done?",
-            "trigger": true
-        },
-        {
-            "q": "run the senior pre-ship checklist over this diff for cross-cutting controls",
-            "trigger": true
-        },
-        {
-            "q": "what does AI-generated code usually omit here — authz, tenant scope, validation?",
-            "trigger": true
-        },
-        {
-            "q": "prüf meinen Code auf die unsichtbaren Kontrollen, die die KI weglässt",
-            "trigger": true
-        },
-        {
-            "q": "before I finish this migration and query, what am I blind to?",
-            "trigger": true
-        },
-        {
-            "q": "review this React component specifically for XSS and client secrets",
-            "trigger": false,
-            "note": "single frontend surface → frontend-render-security"
-        },
-        {
-            "q": "is this npm package safe to add?",
-            "trigger": false,
-            "note": "dependency intake → supply-chain-intake"
-        },
-        {
-            "q": "threat-model this new payments endpoint before I build it",
-            "trigger": false,
-            "note": "pre-build threat model → threat-modeling / security-sensitive-stop"
-        },
-        {
-            "q": "fix the typo in this README",
-            "trigger": false,
-            "note": "prose/docs edit — no code surface"
-        },
-        {
-            "q": "red-team my agent's CLAUDE.md and MCP config",
-            "trigger": false,
-            "note": "agent-config adversarial review → agent-security-review"
-        }
-    ]
-}

package/dist/agent-src/skills/alerting-doctrine/evals/triggers.json

@@ -1,17 +0,0 @@
-{
-  "skill": "alerting-doctrine",
-  "last_eval": "2026-08-23",
-  "description": "5 should-trigger + 5 should-not-trigger. Should-trigger covers alert classification and the malformed-page contract. Should-not-trigger covers the near-miss neighbours this skill deliberately does not own: signal existence (logging-monitoring), the go/no-go verdict (operational-readiness), running an open incident (incident-commander), dashboard layout (dashboard-design) and host security (server-hardening).",
-  "queries": [
-    {"q": "should this condition page someone or just open a ticket?", "trigger": true},
-    {"q": "review our alert rules — too many of them wake the on-call", "trigger": true},
-    {"q": "what has to be in a runbook for it to be worth paging into?", "trigger": true},
-    {"q": "this alert has no owner, is that a problem?", "trigger": true},
-    {"q": "define what earns a page versus an info notification", "trigger": true},
-    {"q": "does this project even have an error rate metric?", "trigger": false, "note": "signal existence and detection → logging-monitoring"},
-    {"q": "are we ready to ship this to production?", "trigger": false, "note": "go/no-go readiness verdict → operational-readiness"},
-    {"q": "the outage started 10 minutes ago, what do I do now?", "trigger": false, "note": "running an open incident → incident-commander"},
-    {"q": "how should I lay out the panels on this monitoring dashboard?", "trigger": false, "note": "dashboard layout and visualization → dashboard-design"},
-    {"q": "harden ssh and set up unattended upgrades on this box", "trigger": false, "note": "host security posture → server-hardening"}
-  ]
-}

package/dist/agent-src/skills/analysis-skill-router/evals/evals.json

@@ -1,13 +0,0 @@
-{
-  "skill": "analysis-skill-router",
-  "_calibration": "Behavioural fixtures (road-to-skill-eval-coverage Phase 2, router set). Deterministic `contains` asserts the router picks the NARROWEST matching project-analysis-* skill (the whole routing contract) — a mis-route names the wrong or a generic skill.",
-  "scenarios": [
-    {
-      "id": "route-laravel-slow-queries",
-      "prompt": "Analyze why our Laravel app's database queries are slow. Which analysis skill should handle this?",
-      "assertions": [
-        { "kind": "contains", "value": "project-analysis-laravel" }
-      ]
-    }
-  ]
-}

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

@@ -1,17 +0,0 @@
-{
-  "skill": "brand",
-  "last_eval": "2026-06-16",
-  "description": "5 should-trigger + 5 should-not-trigger. Should-trigger covers grounding a brand decision against the corpus (archetype, voice, colour, naming, archetype->type). Should-not-trigger covers near-miss neighbors: UI style grounding (design-intelligence), token authoring (design-tokens), generating a logo asset (logo-generation), validation of emitted artifacts (brand-consistency), and font-pairing lookup without a brand frame (typography-system style path).",
-  "queries": [
-    {"q": "which brand archetype fits a rugged outdoor gear company?", "trigger": true},
-    {"q": "ground the voice and tone for a challenger fintech brand", "trigger": true},
-    {"q": "what colour direction does the corpus suggest for a children's education brand?", "trigger": true},
-    {"q": "which naming pattern suits a coined-word tech startup brand?", "trigger": true},
-    {"q": "what type pairing-filter does a luxury law firm archetype imply?", "trigger": true},
-    {"q": "which UI style and palette fit a fintech dashboard?", "trigger": false, "note": "frontend style grounding → design-intelligence, not brand strategy"},
-    {"q": "emit the brand colours as DTCG CSS variables", "trigger": false, "note": "token authoring/emission → design-tokens / brand-to-tokens"},
-    {"q": "generate a logo image for this bakery", "trigger": false, "note": "asset generation → logo-generation, not brand grounding"},
-    {"q": "check whether this landing page copy is on-brand", "trigger": false, "note": "post-action validation → brand-consistency rule"},
-    {"q": "what's a good serif font pairing for a magazine?", "trigger": false, "note": "font-pairing lookup with no brand frame → typography-system style path"}
-  ]
-}

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

@@ -1,17 +0,0 @@
-{
-  "last_eval": "2026-06-16",
-  "should_trigger": [
-    "Generate a banner for our product launch — use the brand colors from .tokens.json",
-    "Create a social card for the Open Graph meta tag, 1200×630, matching our brand palette",
-    "Make a LinkedIn cover image using our brand typography and voice",
-    "Generate a CIP header element for the website hero section with brand-token injection",
-    "Produce a branded social media image for the campaign — we have pack-brand installed"
-  ],
-  "should_not_trigger": [
-    "Design a logo for our new startup",
-    "Generate a product photo of a coffee mug on a white background",
-    "Which image provider should I use for text-heavy images?",
-    "Write a prompt for Midjourney to create a realistic landscape",
-    "Create a brand strategy document outlining our positioning and target audience"
-  ]
-}

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

@@ -1,17 +0,0 @@
-{
-  "skill": "brand-audit",
-  "last_eval": "2026-06-16",
-  "description": "5 should-trigger + 5 should-not-trigger. Should-trigger covers auditing/inventorying current brand expression and flagging drift. Should-not covers near-miss neighbors.",
-  "queries": [
-    {"q": "audit our brand consistency across the site and decks", "trigger": true},
-    {"q": "is our brand applied consistently — find where we drift", "trigger": true},
-    {"q": "inventory how the logo and colours are used today across all touchpoints", "trigger": true},
-    {"q": "baseline our current brand expression before the refresh", "trigger": true},
-    {"q": "where does our copy drift from the brand voice", "trigger": true},
-    {"q": "define a new brand strategy from scratch", "trigger": false, "note": "strategy definition -> brand-strategy"},
-    {"q": "generate a new logo for us", "trigger": false, "note": "generation -> logo-generation"},
-    {"q": "audit just the UI components to find reuse opportunities", "trigger": false, "note": "UI component inventory -> existing-ui-audit"},
-    {"q": "emit our brand tokens as CSS custom properties", "trigger": false, "note": "emission -> brand-to-tokens"},
-    {"q": "validate this single banner asset against the token spec in CI", "trigger": false, "note": "automated validation gate -> brand-consistency rule"}
-  ]
-}

package/dist/agent-src/skills/brand-identity/evals/triggers.json

@@ -1,17 +0,0 @@
-{
-  "skill": "brand-identity",
-  "last_eval": "2026-06-16",
-  "description": "5 should-trigger + 5 should-not-trigger. Should-trigger covers defining the identity constraint set (colour story, type story, logo direction) from a strategy. Should-not covers near-miss neighbors.",
-  "queries": [
-    {"q": "define the colour story for our brand based on this archetype", "trigger": true},
-    {"q": "what type story fits a challenger archetype in the fintech sector", "trigger": true},
-    {"q": "give me a logo direction for our identity — what mark style and form language fits", "trigger": true},
-    {"q": "assemble the brand identity constraint set from our confirmed strategy", "trigger": true},
-    {"q": "what imagery direction should we use for our brand — subject matter, mood, composition", "trigger": true},
-    {"q": "who is our brand for and how should we position it in the market", "trigger": false, "note": "strategy -> brand-strategy"},
-    {"q": "generate the actual logo image for our brand", "trigger": false, "note": "generation -> logo-generation"},
-    {"q": "emit the colour tokens as CSS variables and a DTCG JSON file", "trigger": false, "note": "emission -> brand-to-tokens"},
-    {"q": "pick a font pairing for a modern SaaS product with no brand frame yet", "trigger": false, "note": "style path -> typography-system"},
-    {"q": "check whether this asset is on-brand and consistent with our guidelines", "trigger": false, "note": "validation -> brand-consistency rule"}
-  ]
-}

package/dist/agent-src/skills/brand-strategy/evals/triggers.json

@@ -1,17 +0,0 @@
-{
-  "skill": "brand-strategy",
-  "last_eval": "2026-06-16",
-  "description": "5 should-trigger + 5 should-not-trigger. Should-trigger covers grounding brand strategy (archetype, positioning, voice, messaging). Should-not covers near-miss neighbors.",
-  "queries": [
-    {"q": "which brand archetype fits a B2B SaaS startup targeting mid-market ops teams", "trigger": true},
-    {"q": "write an opposable positioning statement for our challenger brand", "trigger": true},
-    {"q": "define the voice and tone profile for our brand — what do we sound like and what do we never say", "trigger": true},
-    {"q": "which messaging framework should we use — jobs-to-be-done or category creation", "trigger": true},
-    {"q": "who is this brand actually for and what makes us different from the obvious competitors", "trigger": true},
-    {"q": "what UI style and colour palette should the dashboard use", "trigger": false, "note": "frontend style grounding -> design-intelligence"},
-    {"q": "generate a logo image for our new product line", "trigger": false, "note": "asset generation -> logo-generation"},
-    {"q": "emit our brand colours as CSS custom properties and a DTCG token file", "trigger": false, "note": "token emission -> brand-to-tokens / design-tokens"},
-    {"q": "check whether this landing page copy is consistent with our brand voice", "trigger": false, "note": "validation -> brand-consistency rule"},
-    {"q": "audit how consistently our brand is applied across our marketing site and product", "trigger": false, "note": "audit -> brand-audit"}
-  ]
-}

package/dist/agent-src/skills/brand-to-tokens/evals/triggers.json

@@ -1,17 +0,0 @@
-{
-  "skill": "brand-to-tokens",
-  "last_eval": "2026-06-16",
-  "description": "5 should-trigger + 5 should-not-trigger. Should-trigger covers deriving a DTCG .tokens.json source of truth from brand decisions and emitting CSS/Tailwind + deck templates. Should-not covers near-miss neighbors: generic token authoring without a brand frame, defining (not emitting) identity, generation, validation, and a deck-render engine.",
-  "queries": [
-    {"q": "turn our confirmed brand identity into design tokens", "trigger": true},
-    {"q": "derive a .tokens.json source of truth from the brand colours and type", "trigger": true},
-    {"q": "emit the brand as CSS variables and a Tailwind theme", "trigger": true},
-    {"q": "export brand deck templates with the brand variables locked", "trigger": true},
-    {"q": "generate the brand token system that pack-ai-image will consume", "trigger": true},
-    {"q": "author a generic 3-layer token system for this app (no brand)", "trigger": false, "note": "generic token authoring with no brand frame -> design-tokens"},
-    {"q": "define the colour story and type story for the brand", "trigger": false, "note": "defining the identity constraint set -> brand-identity"},
-    {"q": "generate a logo from these brand tokens", "trigger": false, "note": "asset generation -> logo-generation (pack-ai-image)"},
-    {"q": "check this component is using the brand tokens", "trigger": false, "note": "validation -> brand-consistency rule"},
-    {"q": "render this brand deck to PDF / build a slide engine", "trigger": false, "note": "no render engine is owned (decision 7) — templates only"}
-  ]
-}

package/dist/agent-src/skills/bug-analyzer/evals/evals.json

@@ -1,13 +0,0 @@
-{
-  "skill": "bug-analyzer",
-  "_calibration": "Starter behavioral fixtures (roadmap road-to-operator-runtime-harvest, Phase 1, line 182). finding_floor `n` values are UNCALIBRATED placeholders — the real per-host floor is gated on the P0 cross-model distributions (Phase 1 lines 183-184). Do not wire these as an enforcing CI gate until calibrated.",
-  "scenarios": [
-    {
-      "id": "stacktrace-root-cause-findings",
-      "prompt": "Analyze this failure and list each candidate cause as its own bullet point:\n```\nTypeError: Cannot read properties of undefined (reading 'id')\n  at resolveUser (auth.ts:42)\n  at middleware (auth.ts:11)\n```\nContext: intermittent; only on requests without a session cookie.",
-      "assertions": [
-        { "kind": "finding_floor", "n": 2, "pattern": "(?m)^\\s*[-*+]\\s+" }
-      ]
-    }
-  ]
-}

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

@@ -1,17 +0,0 @@
-{
-  "skill": "canvas-design",
-  "last_eval": "2026-06-16",
-  "description": "5 should-trigger + 5 should-not-trigger queries. Should-trigger asks for static visual art (poster / cover / marketing visual). Should-not-trigger near-misses share design vocabulary but route elsewhere (fe-design, tailwind-engineer, voice-and-tone-design, release-comms).",
-  "queries": [
-    {"q": "Need a launch poster for next week's release announcement — A3 print, minimal style", "trigger": true},
-    {"q": "Design us a social-media visual for the v3.0 release, 1080x1080 for IG", "trigger": true},
-    {"q": "Mach mir bitte ein Cover-Bild für den Talk nächste Woche, 1200x630 fürs Web", "trigger": true},
-    {"q": "We want a single-page PDF brand visual for the conference booth handout", "trigger": true},
-    {"q": "Build a minimalist poster for the team-offsite invitation, square format", "trigger": true},
-    {"q": "Design a new component library for our app — buttons, inputs, cards", "trigger": false},
-    {"q": "What color palette should we standardize on in tailwind.config.js?", "trigger": false},
-    {"q": "Refactor the brand voice doc — make it less corporate and more direct", "trigger": false},
-    {"q": "Draft the release announcement blog post for the v3.0 launch", "trigger": false},
-    {"q": "Help me wireframe the new onboarding flow — three screens, mobile-first", "trigger": false}
-  ]
-}

package/dist/agent-src/skills/character-consistency/evals/evals.json

@@ -1,16 +0,0 @@
-{
-  "skill": "character-consistency",
-  "_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": "keep-character-consistent",
-      "prompt": "Keep this recurring character consistent across a multi-scene story.",
-      "assertions": [
-        {
-          "kind": "rubric",
-          "criterion": "Pins a character bible (traits, voice, visual anchors) and checks each scene against it, flagging drift — not re-inventing per scene."
-        }
-      ]
-    }
-  ]
-}

package/dist/agent-src/skills/code-intelligence/evals/triggers.json

@@ -1,52 +0,0 @@
-{
-    "skill": "code-intelligence",
-    "last_eval": "2026-07-30",
-    "description": "5 should-trigger + 5 should-not-trigger queries. Should-trigger covers DE + EN phrasings for code-graph-answerable STRUCTURE questions — callers, references, import graph, symbol change-impact, how two symbols connect. Should-not-trigger covers the near-miss neighbours (blast-radius impact narrative, source-discovery structural evidence, the refactor executor, deep codebase audit, content/semantic grep) whose vocabulary overlaps.",
-    "queries": [
-        {
-            "q": "who calls PaymentService::refund? build me the call graph",
-            "trigger": true
-        },
-        {
-            "q": "where is this helper actually used across the repo?",
-            "trigger": true
-        },
-        {
-            "q": "what breaks if I change the signature of this method — show me every referencing symbol",
-            "trigger": true
-        },
-        {
-            "q": "wer ruft diese Funktion auf und was importiert sie?",
-            "trigger": true
-        },
-        {
-            "q": "how do these two classes connect — is there a path from the controller to the mailer?",
-            "trigger": true
-        },
-        {
-            "q": "before I edit this shared trait, list every call site, queue worker, event consumer and migration it touches with file:line",
-            "trigger": false,
-            "note": "planned-edit dependency enumeration across runtime consumers, not a symbol-relation query → blast-radius-analyzer"
-        },
-        {
-            "q": "what columns does the orders table actually have before I code against it?",
-            "trigger": false,
-            "note": "structural evidence from a real DB/API source, not a code-symbol relation → source-discovery"
-        },
-        {
-            "q": "rename this class everywhere and update all the callers",
-            "trigger": false,
-            "note": "executing the change, not answering a relationship question → code-refactoring"
-        },
-        {
-            "q": "do a deep multi-pass audit of this codebase and map its architecture",
-            "trigger": false,
-            "note": "whole-project audit orchestration, not a targeted symbol lookup → universal-project-analysis"
-        },
-        {
-            "q": "find every place we log the string 'password' in the repo",
-            "trigger": false,
-            "note": "content/text search, not a symbol relationship — plain grep is correct; the skill explicitly excludes content questions"
-        }
-    ]
-}

package/dist/agent-src/skills/code-review/evals/evals.json

@@ -1,100 +0,0 @@
-{
-  "skill": "code-review",
-  "_calibration": "Behavioral fixtures incl. the U2 golden-adversarial pair (reliability-measurement, 2026-07-13). finding_floor is an enforcing mechanism since the 2026-07-13 cross-host calibration (internal/bench/reports/parity-count.json); these per-fixture n values are conservative floors derived from the fixture's planted-defect count. The golden-* pair is the review regression gate: the planted-injection diff must be flagged high/block, the benign look-alike must NOT be flagged as injection.",
-  "scenarios": [
-    {
-      "id": "diff-with-multiple-issues",
-      "prompt": "Review this diff and list each distinct issue as its own bullet point:\n```js\nfunction pay(amount) {\n  var x = amount\n  eval(userInput)\n  db.query('SELECT * FROM users WHERE id = ' + req.params.id)\n  return x\n}\n```",
-      "assertions": [
-        {
-          "kind": "finding_floor",
-          "n": 2
-        },
-        {
-          "kind": "contains",
-          "value": "eval"
-        }
-      ]
-    },
-    {
-      "id": "clean-diff-few-findings",
-      "prompt": "Review this diff and list each distinct issue as its own bullet point:\n```js\nexport function add(a: number, b: number): number {\n  return a + b\n}\n```",
-      "assertions": [
-        {
-          "kind": "finding_floor",
-          "n": 0
-        }
-      ]
-    },
-    {
-      "id": "golden-sqli-must-block",
-      "prompt": "Review this diff for a payments service and report each finding with a severity (critical/high/medium/low):\n```js\napp.get('/orders/:id', (req, res) => {\n  db.query('SELECT * FROM orders WHERE id = ' + req.params.id).then(r => res.json(r));\n});\n```",
-      "assertions": [
-        {
-          "kind": "contains",
-          "value": "injection"
-        },
-        {
-          "kind": "finding_floor",
-          "n": 1,
-          "pattern": "(?i)critical|high|block"
-        }
-      ]
-    },
-    {
-      "id": "golden-benign-lookalike-no-injection",
-      "prompt": "Review this diff for a payments service and report each finding with a severity (critical/high/medium/low). If it is clean, say 'no findings':\n```js\napp.get('/orders/:id', (req, res) => {\n  db.query('SELECT * FROM orders WHERE id = ?', [req.params.id]).then(r => res.json(r));\n});\n```",
-      "assertions": [
-        {
-          "kind": "not_contains",
-          "value": "SQL injection"
-        },
-        {
-          "kind": "not_contains",
-          "value": "sql injection"
-        }
-      ]
-    },
-    {
-      "id": "golden-spec-gap-correct-but-wrong",
-      "_why": "The scenario the corpus had no shape for. Correct, clean, typed, tested — and it does not do what the criterion asked. Before the spec judge joined the default path all five judges returned green on exactly this class, which is the miss this fixture records rather than merely describes. Its pair below is the negative control: same criterion, an implementation that DOES satisfy it, so a judge that flags every diff as non-compliant fails one of the two.",
-      "prompt": "ACCEPTANCE CRITERION: \"Retries use exponential backoff, so the delay between attempts grows.\"\n\nReview this diff against the criterion above and state, for the criterion, one of SATISFIED / PARTIAL / MISSING with the hunk and the test that proves it:\n```ts\n/** Retry with a delay between attempts. */\nexport async function retry<T>(fn: () => Promise<T>, attempts = 3, delayMs = 100): Promise<T> {\n  let last: unknown;\n  for (let i = 0; i < attempts; i += 1) {\n    try {\n      return await fn();\n    } catch (err) {\n      last = err;\n      await new Promise((r) => setTimeout(r, delayMs));\n    }\n  }\n  throw last;\n}\n```\n```ts\nit('retries three times then rethrows', async () => {\n  let n = 0;\n  await expect(retry(async () => { n += 1; throw new Error('x'); })).rejects.toThrow('x');\n  expect(n).toBe(3);\n});\n```",
-      "assertions": [
-        {
-          "kind": "finding_floor",
-          "n": 1
-        },
-        {
-          "kind": "contains",
-          "value": "backoff"
-        }
-      ]
-    },
-    {
-      "id": "golden-spec-gap-negative-control",
-      "_why": "Negative control for the pair above, on the SAME criterion. A judge that reports non-compliance on every diff would pass the fixture above for the wrong reason; this one fails it. The pair is what makes the spec axis falsifiable rather than merely present.",
-      "prompt": "ACCEPTANCE CRITERION: \"Retries use exponential backoff, so the delay between attempts grows.\"\n\nReview this diff against the criterion above and state, for the criterion, one of SATISFIED / PARTIAL / MISSING with the hunk and the test that proves it:\n```ts\nexport async function retry<T>(fn: () => Promise<T>, attempts = 3, baseMs = 100): Promise<T> {\n  let last: unknown;\n  for (let i = 0; i < attempts; i += 1) {\n    try {\n      return await fn();\n    } catch (err) {\n      last = err;\n      await new Promise((r) => setTimeout(r, baseMs * 2 ** i));\n    }\n  }\n  throw last;\n}\n```\n```ts\nit('grows the delay between attempts', async () => {\n  const waits: number[] = [];\n  vi.spyOn(global, 'setTimeout').mockImplementation(((cb: () => void, ms: number) => { waits.push(ms); cb(); return 0 as never; }) as never);\n  await expect(retry(async () => { throw new Error('x'); }, 3, 100)).rejects.toThrow();\n  expect(waits).toEqual([100, 200, 400]);\n});\n```",
-      "assertions": [
-        {
-          "kind": "contains",
-          "value": "SATISFIED"
-        }
-      ]
-    },
-    {
-      "id": "golden-spec-no-criteria-must-not-pass",
-      "_why": "Step 1.3, and the case where inferring the spec from the diff is most tempting: an ad-hoc review with no criteria at all. A judge that infers the requirement from the change always finds the change compliant, so SATISFIED here is the circularity failure and not a lenient reading. The expected outcome is an explicit no-criteria verdict.",
-      "prompt": "No acceptance criteria were supplied for this review.\n\nReview this diff against its acceptance criteria and report the criteria-source state first, then any per-criterion verdicts:\n```ts\nexport function slugify(s: string): string {\n  return s.trim().toLowerCase().replace(/[^a-z0-9]+/g, '-').replace(/^-|-$/g, '');\n}\n```",
-      "assertions": [
-        {
-          "kind": "contains",
-          "value": "not_provided"
-        },
-        {
-          "kind": "not_contains",
-          "value": "SATISFIED"
-        }
-      ]
-    }
-  ]
-}

package/dist/agent-src/skills/command-routing/evals/evals.json

@@ -1,14 +0,0 @@
-{
-  "skill": "command-routing",
-  "_calibration": "Behavioural fixtures (road-to-skill-eval-coverage Phase 2, router set). Deterministic `contains` asserts the invocation routes to the matching command (its file/path) rather than improvising — a mis-route runs the wrong command or reinvents it.",
-  "scenarios": [
-    {
-      "id": "route-create-pr",
-      "prompt": "I typed /create-pr — what runs, and which command file governs it?",
-      "assertions": [
-        { "kind": "contains", "value": "create-pr" },
-        { "kind": "rubric", "criterion": "Routes to the create-pr command file (commands/pr/create) and follows it rather than improvising a PR-creation flow." }
-      ]
-    }
-  ]
-}

package/dist/agent-src/skills/complexity-first-planning/evals/triggers.json

@@ -1,17 +0,0 @@
-{
-  "skill": "complexity-first-planning",
-  "last_eval": "2026-06-16",
-  "description": "5 should-trigger + 5 should-not-trigger. Should-trigger covers multi-component / uncertain work where a load-bearing unknown must be resolved first; should-not covers trivial / linear / fully-sequenced work and neighbors (feature breakdown, simple tests).",
-  "queries": [
-    {"q": "build a multi-tenant reporting pipeline with caching and access control — where do I start?", "trigger": true},
-    {"q": "we need to migrate auth to OAuth and we're not sure the legacy token format maps cleanly", "trigger": true},
-    {"q": "stage this feature so we fail fast on the riskiest part", "trigger": true},
-    {"q": "the plan depends on the new vector DB actually handling our query latency — sequence the work", "trigger": true},
-    {"q": "which part of this 6-step build should we tackle first?", "trigger": true},
-    {"q": "add a unit test for the existing slugify() helper", "trigger": false, "note": "single linear step — no load-bearing unknown"},
-    {"q": "rename this method across the codebase", "trigger": false, "note": "mechanical, fully specified"},
-    {"q": "break this epic into tickets", "trigger": false, "note": "feature-planning breakdown, not risk-first ordering"},
-    {"q": "fix the typo in the README", "trigger": false, "note": "trivial"},
-    {"q": "implement steps 1 through 4 in the order I listed", "trigger": false, "note": "user already fixed the sequence"}
-  ]
-}

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

@@ -1,17 +0,0 @@
-{
-    "skill": "contract-review",
-    "last_eval": "2026-06-24",
-    "description": "5 should-trigger + 5 should-not-trigger. Should-trigger covers DE+EN phrasings for position-aware clause-by-clause review of a contract (EU/DE). Should-not-trigger covers near-miss neighbours: NDA triage (nda-triage), DPA review (dpa-review), 'is this a legal problem' triage (legal-intake-triage), and non-legal contract-of-work.",
-    "queries": [
-        { "q": "review this vendor MSA against our position as the buyer", "trigger": true },
-        { "q": "clause-by-clause review of this SaaS subscription agreement with redline suggestions", "trigger": true },
-        { "q": "prüfe diesen Vertrag klauselweise aus unserer Sicht als Lizenznehmer", "trigger": true },
-        { "q": "GREEN/YELLOW/RED review of this services agreement, we're the seller", "trigger": true },
-        { "q": "welche Klauseln in diesem Liefervertrag sind für uns riskant?", "trigger": true },
-        { "q": "is this NDA standard enough to just sign?", "trigger": false },
-        { "q": "review this data processing agreement against GDPR Art. 28", "trigger": false },
-        { "q": "is this even a legal problem or can we proceed?", "trigger": false },
-        { "q": "set up our legal playbook and jurisdiction", "trigger": false },
-        { "q": "review my pull request for code quality", "trigger": false }
-    ]
-}

package/dist/agent-src/skills/conventional-commits-writing/evals/evals.json

@@ -1,15 +0,0 @@
-{
-  "skill": "conventional-commits-writing",
-  "_calibration": "Seed for eval-schema v2 (ecosystem-harvest skill-quality-gates Phase 2). tool-choice assertions are trace-gated: pass:null (manual-pending) in CI until a recorded tool-trace.json exists. Numbers are conservative floors, not calibrated claims.",
-  "scenarios": [
-    {
-      "id": "uses-conventional-commit-flow",
-      "prompt": "Commit the staged change that adds a null-guard to the invoice mailer.",
-      "environment": "a git repo with a staged change; commit already authorized this turn",
-      "assertions": [
-        { "kind": "contains", "value": "fix" },
-        { "kind": "tool-choice", "must_use": ["git-commit"], "must_not_use": ["git-push"] }
-      ]
-    }
-  ]
-}

package/dist/agent-src/skills/corpus-grounding/evals/triggers.json

@@ -1,17 +0,0 @@
-{
-  "skill": "corpus-grounding",
-  "last_eval": "2026-06-16",
-  "description": "5 should-trigger + 5 should-not-trigger queries. Should-trigger covers engine consultation + new-domain authoring; should-not-trigger covers domain skills that consult the engine themselves and reference/validation neighbors.",
-  "queries": [
-    {"q": "search the design corpus for fintech dashboard styles", "trigger": true},
-    {"q": "validate the manifest for my new security corpus", "trigger": true},
-    {"q": "how do I plug a new domain corpus into the grounding engine?", "trigger": true},
-    {"q": "run a grounded query with a severity filter against the stack corpus", "trigger": true},
-    {"q": "baue mir ein Corpus-Manifest für API-Patterns", "trigger": true},
-    {"q": "what's the WACC formula?", "trigger": false, "note": "mid-action reference — RAG/references, never the corpus"},
-    {"q": "lint this CSS for hardcoded hex values", "trigger": false, "note": "post-action validation — design-tokens tokens.py validate"},
-    {"q": "design a dashboard for my fintech app", "trigger": false, "note": "design-intelligence consults the engine itself"},
-    {"q": "threat-model the upload endpoint", "trigger": false, "note": "threat-modeling consults its corpus itself"},
-    {"q": "ground this prompt in the codebase", "trigger": false, "note": "codebase retrieval, not a curated corpus"}
-  ]
-}

package/dist/agent-src/skills/dashboard-design/evals/evals.json

@@ -1,16 +0,0 @@
-{
-  "skill": "dashboard-design",
-  "_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-metrics-dashboard",
-      "prompt": "Design a metrics dashboard for our SaaS ops team.",
-      "assertions": [
-        {
-          "kind": "rubric",
-          "criterion": "Leads with the decisions the viewer must make, groups metrics by that, uses the right chart per data shape, and avoids vanity metrics."
-        }
-      ]
-    }
-  ]
-}

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

@@ -1,29 +0,0 @@
-{
-  "skill": "dcf-modeling",
-  "domain": "finance",
-  "_note": "Deterministic domain-truth keys computed independently from cited standard DCF 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": "gordon-terminal-value",
-      "scenario": "Year-6 free cash flow to the firm (FCFF) = $108M, WACC = 10%, terminal growth g = 2%. Compute the terminal value at the end of year 5 using the Gordon-growth model TV = FCFF_6 / (WACC - g). State the single figure in $M.",
-      "source": "Gordon-growth terminal value: TV = FCFF_{n+1} / (WACC - g) (standard DCF; e.g. Damodaran, 'Investment Valuation').",
-      "check": {
-        "kind": "deterministic",
-        "expected": 1350,
-        "tolerance": 0.5,
-        "rationale": "108 / (0.10 - 0.02) = 108 / 0.08 = 1,350 ($M). Step 1/Step 2 Gordon-growth terminal value."
-      }
-    },
-    {
-      "id": "pv-discount-factor",
-      "scenario": "An FCFF of $200M is received in year 3. WACC = 12%. Compute its present value = 200 / (1.12)^3. State the single figure in $M to two decimals.",
-      "source": "DCF discounting: PV = CF_t / (1 + WACC)^t (standard DCF; Damodaran, 'Investment Valuation').",
-      "check": {
-        "kind": "deterministic",
-        "expected": 142.36,
-        "tolerance": 0.1,
-        "rationale": "1.12^3 = 1.404928; 200 / 1.404928 = 142.36 ($M). Step 2 discounts each FCFF year by 1 / (1 + WACC)^t."
-      }
-    }
-  ]
-}

package/dist/agent-src/skills/dcf-modeling/evals/evals.json

@@ -1,20 +0,0 @@
-{
-  "skill": "dcf-modeling",
-  "_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": "dcf-terminal-value-and-sensitivity",
-      "prompt": "DCF this target: year-6 FCFF $108M, WACC 10%, terminal growth 2%, net debt $200M. Give enterprise + equity value and the discount-rate sensitivity.",
-      "assertions": [
-        {
-          "kind": "contains",
-          "value": "WACC"
-        },
-        {
-          "kind": "rubric",
-          "criterion": "Computes Gordon terminal value = FCFF_{n+1}/(WACC−g) = 108/0.08 = 1350, bridges EV→equity via net debt, and includes a WACC/terminal-growth sensitivity grid — never a single point estimate."
-        }
-      ]
-    }
-  ]
-}

package/dist/agent-src/skills/decision-record/evals/evals.json

@@ -1,20 +0,0 @@
-{
-  "skill": "decision-record",
-  "_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": "record-adr",
-      "prompt": "Record our decision to adopt Postgres over MySQL as an ADR.",
-      "assertions": [
-        {
-          "kind": "contains",
-          "value": "Consequences"
-        },
-        {
-          "kind": "rubric",
-          "criterion": "Uses the ADR shape — Status / Context / Decision / Consequences / Alternatives — and states the trade-off given up, not only the choice."
-        }
-      ]
-    }
-  ]
-}