@event4u/agent-config 14.11.0 → 14.12.0

package/dist/agent-src/skills/rice-prioritization/evals/evals.json

@@ -1,20 +0,0 @@
-{
-  "skill": "rice-prioritization",
-  "_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": "rice-rank-three",
-      "prompt": "Prioritize these three features with RICE: A (reach 5000, impact 2, conf 80%, effort 3), B (reach 1000, impact 3, conf 100%, effort 1), C (reach 8000, impact 1, conf 50%, effort 5).",
-      "assertions": [
-        {
-          "kind": "contains",
-          "value": "RICE"
-        },
-        {
-          "kind": "rubric",
-          "criterion": "Computes RICE = Reach×Impact×Confidence/Effort per item (A≈2667, B=3000, C=800) and ranks by the score, not by gut feel."
-        }
-      ]
-    }
-  ]
-}

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

@@ -1,29 +0,0 @@
-{
-  "skill": "runway-cognition",
-  "domain": "finance",
-  "_note": "Deterministic domain-truth keys computed independently from cited standard startup-finance definitions (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": "runway-constant-burn",
-      "scenario": "A startup holds $4,200,000 in cash with a constant net monthly burn of $560,000. Compute the months of runway. State the single number of months.",
-      "source": "Standard startup-finance runway definition: months of runway = cash balance / net monthly burn (constant-burn case). Common startup-finance primers (e.g. YC / Fenwick startup finance).",
-      "check": {
-        "kind": "deterministic",
-        "expected": 7.5,
-        "tolerance": 0.05,
-        "rationale": "4,200,000 / 560,000 = 7.5 months. runway-cognition Step 2 computes months-of-runway = cash / current-burn; this checks the arithmetic is correct off the forged stacks."
-      }
-    },
-    {
-      "id": "runway-variable-burn",
-      "scenario": "A startup holds $1,000,000 in cash. Net monthly burn is $200,000 for the first 3 months, then $300,000 per month thereafter. Compute the runway in months (the point at which cumulative cash reaches zero). State the single number of months to two decimals.",
-      "source": "Cumulative-cash-depletion definition of runway under a non-constant burn schedule (standard startup-finance).",
-      "check": {
-        "kind": "deterministic",
-        "expected": 4.33,
-        "tolerance": 0.1,
-        "rationale": "First 3 months burn 3 x 200,000 = 600,000, leaving 400,000. At 300,000/month that lasts 400,000/300,000 = 1.333 months. Total = 3 + 1.333 = 4.33 months."
-      }
-    }
-  ]
-}

package/dist/agent-src/skills/runway-cognition/evals/evals.json

@@ -1,20 +0,0 @@
-{
-  "skill": "runway-cognition",
-  "_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": "runway-shape-and-decision",
-      "prompt": "We have $4.2M cash and burn $560k/month. How long do we have and what should we do?",
-      "assertions": [
-        {
-          "kind": "contains",
-          "value": "runway"
-        },
-        {
-          "kind": "rubric",
-          "criterion": "Computes months-of-runway = cash/burn (≈7.5) AND frames raise/hold/cut-vs-grow as a shape against the org-stage band, not a single number."
-        }
-      ]
-    }
-  ]
-}

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

@@ -1,29 +0,0 @@
-{
-  "skill": "scenario-modeling",
-  "domain": "finance",
-  "_note": "Deterministic domain-truth keys computed independently from cited standard scenario-construction formulas (NOT the skill's own output). The skill's fuller soundness (named headwind, optionality) is qualitative; these cases check only the deterministic band/sensitivity arithmetic it performs. 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": "downside-band-lower-bound",
-      "scenario": "Base commit = $6.3M with a symmetric forecast confidence band of +/-14%. Compute the downside scenario revenue as the band lower bound = commit x (1 - band). State the single figure in $M to three decimals.",
-      "source": "Three-scenario construction: downside = forecast commit-band lower bound = commit x (1 - band_pct) (standard base/upside/downside modeling; NOT an arbitrary base x 0.8).",
-      "check": {
-        "kind": "deterministic",
-        "expected": 5.418,
-        "tolerance": 0.01,
-        "rationale": "6.3 x (1 - 0.14) = 6.3 x 0.86 = 5.418 ($M). Step 1: downside = O2 commit-band lower bound."
-      }
-    },
-    {
-      "id": "sensitivity-minus-20pct",
-      "scenario": "The load-bearing input of a scenario is an enterprise close rate of 40%. Run a -20% sensitivity on that input. Compute the low sensitivity value = 40% x (1 - 0.20). State the single value as a percentage.",
-      "source": "Sensitivity analysis: vary the single load-bearing input by +/-20% (standard scenario robustness test).",
-      "check": {
-        "kind": "deterministic",
-        "expected": 32,
-        "tolerance": 0.1,
-        "rationale": "40 x 0.80 = 32 (%). Step 4: vary the load-bearing input by +/-20%."
-      }
-    }
-  ]
-}

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

@@ -1,20 +0,0 @@
-{
-  "skill": "scenario-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": "base-upside-downside",
-      "prompt": "Model base / upside / downside for our annual plan off a $6.3M commit.",
-      "assertions": [
-        {
-          "kind": "contains",
-          "value": "downside"
-        },
-        {
-          "kind": "rubric",
-          "criterion": "Downside names a concrete HEADWIND (not base×0.8), upside names a tailwind, and reads optionality — not just ±20% on base."
-        }
-      ]
-    }
-  ]
-}

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

@@ -1,17 +0,0 @@
-{
-    "skill": "schema-review",
-    "last_eval": "2026-07-27",
-    "description": "5 should-trigger + 5 should-not-trigger. Should-trigger covers DE+EN phrasings for reviewing a migration/schema diff for scale hazards. Should-not-trigger covers near-miss neighbours: authoring a migration (laravel-migration), live-traffic performance (performance-analysis), audit-tier selection (history-design), generic code review.",
-    "queries": [
-        { "q": "review this migration for missing indexes before I merge", "trigger": true },
-        { "q": "will this schema change scale to 100k rows?", "trigger": true },
-        { "q": "prüfe meine Migration auf Skalierungsprobleme", "trigger": true },
-        { "q": "check the new schema.prisma diff for unsafe changes", "trigger": true },
-        { "q": "does this ALTER TABLE need CONCURRENTLY and a default?", "trigger": true },
-        { "q": "create a migration that adds a status column to orders", "trigger": false },
-        { "q": "the dashboard endpoint is slow in production, profile it", "trigger": false },
-        { "q": "which audit log mechanism should we use for tenants?", "trigger": false },
-        { "q": "review my pull request for code quality", "trigger": false },
-        { "q": "wie lege ich einen Index in MySQL an?", "trigger": false }
-    ]
-}

package/dist/agent-src/skills/screenshot-hygiene/evals/triggers.json

@@ -1,52 +0,0 @@
-{
-    "skill": "screenshot-hygiene",
-    "last_eval": "2026-07-30",
-    "description": "5 should-trigger + 5 should-not-trigger queries. Should-trigger covers DE + EN phrasings for capturing and anonymising a screenshot that is about to ship into documentation — risk tier, OCR detection, deterministic redaction, the pre-embed human gate. Should-not-trigger covers the near-miss neighbours (image analysis, image editing/inpaint, image generation, the provided-design spec path, PII scrubbing on text surfaces) whose vocabulary overlaps.",
-    "queries": [
-        {
-            "q": "capture a screenshot of the admin dashboard for the feature docs",
-            "trigger": true
-        },
-        {
-            "q": "I want to embed a screenshot of this settings page in the README — is it safe to ship?",
-            "trigger": true
-        },
-        {
-            "q": "redact the customer names and the local path in this screenshot before it lands in docs/media/",
-            "trigger": true
-        },
-        {
-            "q": "mach einen Screenshot für das Doku-Kapitel und anonymisiere vorher alles Sensible",
-            "trigger": true
-        },
-        {
-            "q": "can this dashboard screenshot go on the docs site, or does it leak PII?",
-            "trigger": true
-        },
-        {
-            "q": "analyse this character image feature by feature and diff it against the canon",
-            "trigger": false,
-            "note": "per-feature image analysis / canon drift, not doc-shipping anonymisation → image-analyser (this skill only borrows its OCR read)"
-        },
-        {
-            "q": "inpaint the background out of this photo and give me a couple of variations",
-            "trigger": false,
-            "note": "image editing / lossy inpaint — explicitly forbidden as a redaction method here → image-editing"
-        },
-        {
-            "q": "generate a banner image for the launch post",
-            "trigger": false,
-            "note": "image generation from a brief, not a captured screenshot → image-generation (brand assets → brand-asset-generation)"
-        },
-        {
-            "q": "here's a screenshot of the mockup — build the UI to match it 1:1",
-            "trigger": false,
-            "note": "a user-supplied screenshot used as a design spec to build against → design-fidelity (rule) / cross-source-consistency"
-        },
-        {
-            "q": "scrub the email addresses and tokens out of these log lines before we ship them",
-            "trigger": false,
-            "note": "PII redaction on a text surface (drafts / logs / exports), not inside an image → domain-safety-pii (rule)"
-        }
-    ]
-}

package/dist/agent-src/skills/security-maturity-assessment/evals/triggers.json

@@ -1,52 +0,0 @@
-{
-    "skill": "security-maturity-assessment",
-    "last_eval": "2026-07-12",
-    "description": "5 should-trigger + 5 should-not-trigger queries. Should-trigger covers DE + EN posture/scorecard/baseline phrasings. Should-not-trigger covers the neighbouring security skills (vuln hunt, authz chain, threat model, secure coding, agent config) whose vocabulary overlaps.",
-    "queries": [
-        {
-            "q": "how mature is the security posture of our billing module?",
-            "trigger": true
-        },
-        {
-            "q": "give me a security scorecard for this codebase with evidence per category",
-            "trigger": true
-        },
-        {
-            "q": "wie sicher ist dieses Modul aufgestellt? Bitte pro Kategorie bewerten",
-            "trigger": true
-        },
-        {
-            "q": "baseline our security maturity before the hardening sprint",
-            "trigger": true
-        },
-        {
-            "q": "rate input validation, secrets and tenant isolation for the API package",
-            "trigger": true
-        },
-        {
-            "q": "audit this module for SQL injection and XSS vulnerabilities",
-            "trigger": false,
-            "note": "vulnerability hunt → security-audit"
-        },
-        {
-            "q": "review the authorization chain for the invoice download route",
-            "trigger": false,
-            "note": "single-route authz → authz-review"
-        },
-        {
-            "q": "threat-model the new file-upload feature before we build it",
-            "trigger": false,
-            "note": "pre-implementation → threat-modeling"
-        },
-        {
-            "q": "write a policy and gate for this new admin action",
-            "trigger": false,
-            "note": "writing secure code → security"
-        },
-        {
-            "q": "red-team my Claude agent's MCP and hook config",
-            "trigger": false,
-            "note": "agent config/behaviour → agent-security-review"
-        }
-    ]
-}

package/dist/agent-src/skills/server-hardening/evals/triggers.json

@@ -1,17 +0,0 @@
-{
-  "skill": "server-hardening",
-  "last_eval": "2026-08-23",
-  "description": "5 should-trigger + 5 should-not-trigger. Should-trigger covers the three host surfaces — SSH posture, firewall baseline, unattended upgrades. Should-not-trigger covers the neighbours: application-code vulnerability work (security-audit), application authorization (authz-review), cloud provisioning (terraform, aws-infrastructure), container images (docker) and adjudicating the resulting posture (operational-readiness).",
-  "queries": [
-    {"q": "harden ssh on this server — disable password login", "trigger": true},
-    {"q": "set up a default-deny firewall baseline on the VPS", "trigger": true},
-    {"q": "how do I get automatic security patches on this box?", "trigger": true},
-    {"q": "should I install fail2ban on the host?", "trigger": true},
-    {"q": "host hardening checklist for a new bare-metal server", "trigger": true},
-    {"q": "audit this codebase for injection vulnerabilities", "trigger": false, "note": "application-code vulnerability sweep → security-audit"},
-    {"q": "can user A read user B's records through this endpoint?", "trigger": false, "note": "application authorization → authz-review"},
-    {"q": "write the Terraform for a new ECS service", "trigger": false, "note": "cloud provisioning → terraform / aws-infrastructure"},
-    {"q": "reduce the attack surface of this Dockerfile", "trigger": false, "note": "container image hardening → docker"},
-    {"q": "is the overall system ready to operate given the host posture?", "trigger": false, "note": "adjudicating the verdict → operational-readiness"}
-  ]
-}

package/dist/agent-src/skills/skill-writing/evals/triggers.json

@@ -1,17 +0,0 @@
-{
-  "skill": "skill-writing",
-  "last_eval": "2026-06-16",
-  "description": "5 should-trigger + 5 should-not-trigger queries. No query mentions 'skill-writing' directly. Near-misses share 'skill' vocabulary but route to skill-management, lint-skills, or unrelated skills.",
-  "queries": [
-    {"q": "let's create a skill for database migrations", "trigger": true},
-    {"q": "this SKILL.md feels weak, can you tighten it?", "trigger": true},
-    {"q": "should this be a skill or a rule?", "trigger": true},
-    {"q": "the description says 'covers various things' — fix it", "trigger": true},
-    {"q": "add a proper procedure section to the graphql skill", "trigger": true},
-    {"q": "refactor my PHP controller", "trigger": false},
-    {"q": "run the skill linter on my branch", "trigger": false},
-    {"q": "condense this SKILL.md to half its length", "trigger": false},
-    {"q": "which skill handles git workflow?", "trigger": false},
-    {"q": "write a CONTRIBUTING.md for this repo", "trigger": false}
-  ]
-}

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

@@ -1,47 +0,0 @@
-{
-    "skill": "spreadsheet-authoring",
-    "last_eval": "2026-07-10",
-    "description": "5 should-trigger + 5 should-not-trigger queries for the spreadsheet surface floor (road-to-surface-specific-agent-contracts Phase 2). Should-trigger covers building/editing a spreadsheet or model, entering formulas or sourced/financial figures, and charting raw data. Should-not-trigger covers near-miss neighbours whose vocabulary overlaps but belong to a different surface/skill: unit-economics reasoning, runway shape, a prose document, a slide deck, and backend work.",
-    "queries": [
-        {
-            "q": "build a 3-statement financial model in a spreadsheet",
-            "trigger": true
-        },
-        {
-            "q": "add a formula to sum the revenue column and total it",
-            "trigger": true
-        },
-        {
-            "q": "chart this raw sales transaction data",
-            "trigger": true
-        },
-        {
-            "q": "enter the revenue figures from the company's 10-K into the sheet",
-            "trigger": true
-        },
-        {
-            "q": "create a budget spreadsheet with monthly categories",
-            "trigger": true
-        },
-        {
-            "q": "what is our LTV to CAC ratio and is it healthy?",
-            "trigger": false
-        },
-        {
-            "q": "how long is our cash runway?",
-            "trigger": false
-        },
-        {
-            "q": "write a PRD for the new onboarding feature",
-            "trigger": false
-        },
-        {
-            "q": "turn these results into a slide deck",
-            "trigger": false
-        },
-        {
-            "q": "add a database index on the orders table",
-            "trigger": false
-        }
-    ]
-}

package/dist/agent-src/skills/storybook-workshop/evals/triggers.json

@@ -1,17 +0,0 @@
-{
-    "skill": "storybook-workshop",
-    "last_eval": "2026-08-23",
-    "description": "5 should-trigger + 5 should-not-trigger. Should-trigger covers the named authoring ask, the inventory ask, the story-as-test ask, the MCP-channel question, and a DE phrasing. Should-not-trigger covers the near-misses this skill sits between: authoring the component itself (ui-component-architect), a full WCAG audit of a shipped page (accessibility-auditor), an E2E flow test, the package surface (js-library-packaging), and a visual-design question.",
-    "queries": [
-        { "q": "add stories for the card", "trigger": true },
-        { "q": "what components does our library already have?", "trigger": true },
-        { "q": "can the stories run as tests in CI?", "trigger": true },
-        { "q": "should we wire up the storybook mcp addon?", "trigger": true },
-        { "q": "schreib Stories für die neuen Primitives", "trigger": true },
-        { "q": "build me a Card component with a footer slot", "trigger": false },
-        { "q": "run a full WCAG audit on the checkout page", "trigger": false },
-        { "q": "write a playwright test for the signup flow", "trigger": false },
-        { "q": "why does my hook say invalid hook call", "trigger": false },
-        { "q": "pick a colour palette for the dashboard", "trigger": false }
-    ]
-}

package/dist/agent-src/skills/subagent-orchestration/evals/evals.json

@@ -1,60 +0,0 @@
-{
-    "skill": "subagent-orchestration",
-    "_calibration": "Golden E2E task 2 (road-to-fable-feedback-5 Phase 4c; council 2026-07-10 ranked bad-lite-output delegation second-highest signal/cost). Exercises the never-adopt-unverified Iron Law (delegation-policy) + the escalation path + the telemetry pairing (first_pass_success/escalated per orchestration-telemetry.md § Operationalization). Deterministic `contains` assertions pin the telemetry vocabulary; rubric pins the verification behavior. Baseline: authored 2026-07-10, pending first host-scored run.",
-    "scenarios": [
-        {
-            "id": "sao-bad-lite-output-escalation",
-            "prompt": "You are orchestrating: a lite-tier subagent was dispatched to implement `slugify(title: string): string` (lowercase, spaces to hyphens, strip non-alphanumerics, collapse repeated hyphens). Its return is: `export function slugify(title: string) { return title.toLowerCase().replace(' ', '-'); }` with no tests. Process this return per the orchestration contract and record the dispatch telemetry.",
-            "assertions": [
-                {
-                    "kind": "contains",
-                    "value": "first_pass_success"
-                },
-                {
-                    "kind": "contains",
-                    "value": "escalated"
-                },
-                {
-                    "kind": "rubric",
-                    "criterion": "The return is NOT adopted unverified: verification runs against the stated spec and catches at least two planted defects (String.replace with a string only replaces the FIRST space; non-alphanumerics are not stripped; repeated hyphens are not collapsed; no tests). The orchestrator never merges the defective return as-is."
-                },
-                {
-                    "kind": "rubric",
-                    "criterion": "After the verification failure the slice is re-dispatched on a higher tier (or corrected with the failure fed back), and the telemetry records escalated=true and first_pass_success=false per the operationalization table (business-logic rework counts as rework; formatting would not). The final adopted output satisfies the full spec."
-                }
-            ]
-        },
-        {
-            "id": "sao-good-return-no-spurious-escalation",
-            "prompt": "You are orchestrating: a lite-tier subagent was dispatched to rename the constant `MAX_RETRIES` to `MAX_ATTEMPTS` across a 3-file module. Its return is a diff renaming all 7 occurrences, all references updated, tests still green. Process this return per the orchestration contract and record the dispatch telemetry.",
-            "assertions": [
-                {
-                    "kind": "contains",
-                    "value": "first_pass_success"
-                },
-                {
-                    "kind": "rubric",
-                    "criterion": "Negative control: the clean return is verified and adopted WITHOUT rework or escalation — telemetry records first_pass_success=true and escalated=false. No spurious findings are invented to justify a re-dispatch."
-                }
-            ]
-        },
-        {
-            "id": "sao-adversarial-council-advisory-no-gate",
-            "prompt": "`subagents.adversarial_council: on`. You are orchestrating an adversarial-verification-council (Mode 9) over a high-risk, already-verified change to an auth endpoint. Two distinct-model skeptics return findings: skeptic A raises a critical missing tenant-scope check at `src/http/orders.ts:42` (category security) and a low naming nit; skeptic B independently raises the same tenant-scope issue and refutes the naming nit. Reconcile and report the council result.",
-            "assertions": [
-                {
-                    "kind": "contains",
-                    "value": "advisory"
-                },
-                {
-                    "kind": "rubric",
-                    "criterion": "The reconciled output is a findings-by-severity envelope (findings-union), NOT a single go/no-go verdict: the tenant-scope finding is corroborated (raised_by both skeptics → high confidence), and the naming nit raised by only A and refuted by B is demoted to false_positives_suppressed (not silently dropped)."
-                },
-                {
-                    "kind": "rubric",
-                    "criterion": "The council is treated as ADVISORY and NEVER auto-gates the change (Hard Floor): the orchestrator surfaces the findings for a human decision and does not itself accept/reject/merge or block the change based on the panel verdict."
-                }
-            ]
-        }
-    ]
-}

package/dist/agent-src/skills/supply-chain-intake/evals/triggers.json

@@ -1,52 +0,0 @@
-{
-    "skill": "supply-chain-intake",
-    "last_eval": "2026-07-09",
-    "description": "5 should-trigger + 5 should-not-trigger queries. Should-trigger covers DE + EN phrasings for verifying a new third-party dependency before install (existence/slopsquatting, pin+lock, CVE, no curl|bash). Should-not-trigger covers near-miss neighbours (upgrading existing deps, secrets, generic checklist, server auth) whose vocabulary overlaps.",
-    "queries": [
-        {
-            "q": "add the package the model suggested to package.json and install it",
-            "trigger": true
-        },
-        {
-            "q": "is this pip package real or a hallucination before I install?",
-            "trigger": true
-        },
-        {
-            "q": "the install command is a curl piped to bash — is that safe?",
-            "trigger": true
-        },
-        {
-            "q": "prüf diese neue Abhängigkeit bevor ich sie installiere (existiert sie überhaupt?)",
-            "trigger": true
-        },
-        {
-            "q": "should I pin this dependency and commit a lockfile?",
-            "trigger": true
-        },
-        {
-            "q": "upgrade our existing lodash to the latest major and fix breakages",
-            "trigger": false,
-            "note": "upgrading an already-trusted dep → dependency-upgrade"
-        },
-        {
-            "q": "rotate the API keys stored in our secret manager",
-            "trigger": false,
-            "note": "secrets lifecycle → secrets-management"
-        },
-        {
-            "q": "what cross-cutting controls did I miss across this diff?",
-            "trigger": false,
-            "note": "cross-surface checklist → ai-code-blindspots"
-        },
-        {
-            "q": "review the authorization on this endpoint",
-            "trigger": false,
-            "note": "server-side authz → authz-review"
-        },
-        {
-            "q": "why is my build failing on a type error?",
-            "trigger": false,
-            "note": "build/type debugging — not dependency intake"
-        }
-    ]
-}

package/dist/agent-src/skills/systematic-debugging/evals/evals.json

@@ -1,20 +0,0 @@
-{
-  "skill": "systematic-debugging",
-  "_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": "debug-flaky-test",
-      "prompt": "A test passes locally but fails in CI intermittently. Walk me through debugging it.",
-      "assertions": [
-        {
-          "kind": "contains",
-          "value": "hypothesis"
-        },
-        {
-          "kind": "rubric",
-          "criterion": "Forms a hypothesis, isolates one variable, and runs one-test-one-fix-one-rerun rather than shotgun edits."
-        }
-      ]
-    }
-  ]
-}

package/dist/agent-src/skills/test-case-discovery/evals/triggers.json

@@ -1,52 +0,0 @@
-{
-    "skill": "test-case-discovery",
-    "last_eval": "2026-07-10",
-    "description": "5 should-trigger + 5 should-not-trigger queries. Should-trigger covers DE + EN phrasings for pre-write test-case enumeration (what to test, edge cases, coverage breadth). Should-not-trigger covers near-miss neighbours: assertion quality (testing-anti-patterns), after-the-fact coverage review (judge-test-coverage), failing-test diagnosis (systematic-debugging), stack-specific execution.",
-    "queries": [
-        {
-            "q": "what should we test here — I don't want happy-path-only coverage",
-            "trigger": true
-        },
-        {
-            "q": "enumerate the edge cases for this endpoint before we write the tests",
-            "trigger": true
-        },
-        {
-            "q": "welche Testfälle brauchen wir für dieses Feature — auch Grenzfälle und Fehlerpfade?",
-            "trigger": true
-        },
-        {
-            "q": "build a case matrix for this behavior — happy, boundary, error, abuse",
-            "trigger": true
-        },
-        {
-            "q": "ask a subagent what else we could test so coverage is broad",
-            "trigger": true
-        },
-        {
-            "q": "this assertion looks tautological — is the test overfit?",
-            "trigger": false,
-            "note": "assertion quality → testing-anti-patterns"
-        },
-        {
-            "q": "are the tests on this finished diff enough?",
-            "trigger": false,
-            "note": "after-the-fact coverage review → judge-test-coverage"
-        },
-        {
-            "q": "this Pest test keeps failing and I don't understand why",
-            "trigger": false,
-            "note": "failing-test diagnosis → systematic-debugging"
-        },
-        {
-            "q": "how do I mock Http in a Laravel feature test?",
-            "trigger": false,
-            "note": "stack-specific execution → pest-testing"
-        },
-        {
-            "q": "schreib die Playwright-Specs für den Login-Flow, die Fälle stehen schon im Ticket",
-            "trigger": false,
-            "note": "case list already exists → playwright-testing executes it"
-        }
-    ]
-}

package/dist/agent-src/skills/test-driven-development/evals/evals.json

@@ -1,16 +0,0 @@
-{
-  "skill": "test-driven-development",
-  "_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": "tdd-new-validator",
-      "prompt": "TDD a password-strength validator (min length, mixed case, a digit).",
-      "assertions": [
-        {
-          "kind": "rubric",
-          "criterion": "Writes a failing test FIRST (red), then the minimal code (green), then refactors — and covers boundary + negative cases, not only the happy path."
-        }
-      ]
-    }
-  ]
-}

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

@@ -1,21 +0,0 @@
-{
-  "skill": "threat-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": "threat-model-upload",
-      "prompt": "Threat-model a new file-upload endpoint that accepts user files.",
-      "assertions": [
-        {
-          "kind": "finding_floor",
-          "n": 3,
-          "pattern": "(?m)^\\s*[-*+]\\s+"
-        },
-        {
-          "kind": "rubric",
-          "criterion": "Enumerates concrete abuse cases (path traversal, SSRF via URL fetch, malicious file, authz bypass) and the missing control per case — not generic 'validate input'."
-        }
-      ]
-    }
-  ]
-}

package/dist/agent-src/skills/typography-system/evals/evals.json

@@ -1,14 +0,0 @@
-{
-  "skill": "typography-system",
-  "_calibration": "Behavioural fixtures (road-to-skill-eval-coverage Phase 2, rich set). Deterministic `contains` asserts the line-height output the skill produces; the rubric checks the scale is a computed modular scale (from the given ratio), not arbitrary px — the whole point of the skill.",
-  "scenarios": [
-    {
-      "id": "modular-scale-from-ratio",
-      "prompt": "Build a type scale from a 16px base and a 1.25 modular ratio: give the step sizes, line-heights, and weights for body, h3, h2, h1.",
-      "assertions": [
-        { "kind": "contains", "value": "line-height" },
-        { "kind": "rubric", "criterion": "The step sizes are the 1.25 modular scale off 16px (≈16/20/25/31px), i.e. computed from the ratio, not arbitrary round numbers; each step carries a line-height and weight." }
-      ]
-    }
-  ]
-}

package/dist/agent-src/skills/typography-system/evals/triggers.json

@@ -1,17 +0,0 @@
-{
-  "skill": "typography-system",
-  "last_eval": "2026-06-16",
-  "description": "5 should-trigger + 5 should-not-trigger. Should-trigger covers font selection, scale derivation, and DTCG type token authoring. Should-not-trigger covers near-miss neighbors: icon set selection (iconography), raw design-token authoring without a typography constraint (design-tokens), brand archetype requests that require Stage 2 / Phase B, and general color token work.",
-  "queries": [
-    {"q": "pick fonts for our new SaaS product — something modern and professional", "trigger": true},
-    {"q": "build a typographic scale for our design system with DTCG tokens", "trigger": true},
-    {"q": "we need a type system for a luxury fashion brand — choose pairings and emit tokens", "trigger": true},
-    {"q": "what heading and body fonts match an elegant, editorial mood?", "trigger": true},
-    {"q": "set up font-size tokens and line-height for our Tailwind project", "trigger": true},
-    {"q": "which icon set should we use for our dashboard?", "trigger": false, "note": "icon selection → iconography skill"},
-    {"q": "author a 3-layer DTCG token system for colors with dark mode", "trigger": false, "note": "color token authoring without typography constraint → design-tokens skill"},
-    {"q": "define our brand archetype so the font pairing fits our personality", "trigger": false, "note": "brand archetype → pairing-filter is Stage 2 / Phase B, not authored yet"},
-    {"q": "generate CSS variables for our button component tokens", "trigger": false, "note": "component token generation → design-tokens skill"},
-    {"q": "run validate to find hardcoded hex values in our codebase", "trigger": false, "note": "token-discipline lint step → design-tokens skill (tokens.py validate)"}
-  ]
-}