@event4u/agent-config 2.7.0 → 2.9.0

package/.agent-src/skills/voice-and-tone-design/SKILL.md

@@ -0,0 +1,163 @@
+---
+name: voice-and-tone-design
+description: "Use when shaping brand voice — voice attributes, tone-by-context matrix, consistency review. Triggers on 'define our voice', 'why does our copy sound different on every surface'."
+status: active
+tier: senior
+source: package
+domain: product
+context_spine: [product, customer-segment]
+---
+
+# voice-and-tone-design
+
+## When to use
+
+- A team is producing copy across multiple surfaces and the same segment hears three different brands per quarter — name the voice so the surfaces converge.
+- An audience-by-message matrix exists but each audience cell currently reads in a different tone, breaking the recognition signal across the segment.
+- A new senior persona (CMO, founder, head-of-content) is asking for a voice-and-tone artefact that downstream writers can defend against.
+
+Do NOT use to copy-edit individual assets (out of scope — that is a
+writer's job), draft the message stack (route to
+`messaging-architecture`), or pick channel-specific tactics like
+subject lines or ad creative formats (channel-agnostic skill).
+
+## Cognition cluster
+
+- **Mental model 13 — Occam's Razor.** The simplest voice the
+  segment can recognise across surfaces is the voice that survives
+  contact with three writers under deadline. A five-attribute voice
+  that no one remembers is brand-theatre. See
+  [`docs/contracts/mental-models.md`](../../../docs/contracts/mental-models.md) § 13.
+- **Mental model 15 — Signal vs. noise.** Voice is the
+  identification signal embedded in copy — without distinctiveness
+  it is noise that competes with every peer's noise. Cut to the
+  three attributes that *only* the segment hears as us. See
+  `mental-models.md` § 15.
+- **Context-spine — product + customer-segment.** Read **product**
+  for the proofs the voice must carry (a voice that promises what
+  the product cannot back is fiction); read **customer-segment**
+  for the listening-register the audience already lives in. See
+  [`context-spine`](../../../docs/contracts/context-spine.md).
+
+## Procedure
+
+### Step 0: Inherit the positioning frame and audience matrix
+
+Identify the locked positioning anchors from
+[`positioning-strategy`](../positioning-strategy/SKILL.md) and the audience matrix
+from [`messaging-architecture`](../messaging-architecture/SKILL.md).
+Voice without positioning is style; voice without an audience matrix
+is broadcast.
+
+### Step 1: Analyze the inherited voice
+
+Read 6–10 recent assets across the largest surface set the team
+ships on. For each, note the *register* (formal · conversational ·
+technical · playful) and one *line that sounds like us* (or *like
+anyone*). The output is an honest audit: what voice is currently
+shipping, not what the team intends to ship.
+
+### Step 2: Pick three voice attributes — and three only
+
+Three attributes, each phrased as *"\<we are\> X, not Y."* The
+*not Y* is non-trivial: it names the credible adjacent voice the
+team is choosing against, not a strawman. Examples of the shape
+(not vocabulary):
+
+- *"Precise, not pedantic."*
+- *"Confident, not boastful."*
+- *"Concrete, not buzzword."*
+
+A four-attribute voice will collapse to three under deadline; pick
+the three now.
+
+### Step 3: Build the tone-by-context matrix
+
+Tone modulates voice; voice is constant. For each context — error
+copy, marketing surface, sales follow-up, onboarding, executive
+summary, support reply — fill: *what the audience is feeling · what
+the surface must do · which voice attribute leads · what tone
+amplifier or muter applies.* The matrix is the tool writers
+actually reach for; the three attributes are the spine they hang
+the tone on.
+
+### Step 4: Validate against the recognition signal
+
+Validate the voice on three checks:
+
+1. **Distinctiveness.** Write the same sentence in three credible
+   peer voices. Verify the team's voice is recognisable as distinct
+   on first read — not on the second read after explaining the
+   attributes.
+2. **Proof-coverage.** Confirm the voice does not promise what the
+   product (from the spine) cannot back. *"Calm"* without an
+   uptime story is fiction. Verify each attribute against a proof.
+3. **Survives-deadline.** Hand the artefacts to a writer who was
+   not in the room. If the writer cannot reproduce the voice on a
+   30-minute draft, the voice is documented for the room, not the
+   surface.
+
+### Step 5: Run the consistency review
+
+Re-audit the assets from Step 1 against the locked attributes and
+tone matrix. Mark each line *consistent · slipping · contradiction.*
+Slipping is a writer-coaching problem; contradiction is a re-write.
+The review surfaces the load-bearing surfaces that need a re-pass,
+not a punitive list.
+
+### Step 6: Hand back
+
+Hand the artefacts to writers across the surfaces, to
+[`editorial-calendar`](../editorial-calendar/SKILL.md) for cadence
+mapping, and to [`release-comms`](../release-comms/SKILL.md) for
+launch-surface voice review.
+
+## Related Skills
+
+**WHEN to use this**
+
+- The unit of work is the *voice* (three attributes + tone-by-context matrix), not a single line of copy.
+- Surfaces are diverging in tone and the segment cannot recognise the brand across them.
+- A team needs an artefact that a writer on deadline can actually use.
+
+**WHEN NOT to use this**
+
+- Drafting the message stack (primary message + proofs) — route to [`messaging-architecture`](../messaging-architecture/SKILL.md).
+- Cadence and content-debt management — route to [`editorial-calendar`](../editorial-calendar/SKILL.md).
+- Copy-editing individual assets — out of scope; that is a writer's craft.
+- Launch-wave announcement copy — route to [`release-comms`](../release-comms/SKILL.md).
+
+## When the agent should load this
+
+- "Define our voice — three attributes, no more."
+- "Mach uns einen Tone-by-Context matrix, der Schreibern auf Deadline hilft."
+- "Why does our copy sound different on every surface?"
+- "Run a voice consistency audit on last quarter's assets."
+- "Pick the *not-Y* for each voice attribute."
+
+## Output
+
+1. **`voice-attributes.md`** — three attributes in the *"X, not Y"* shape, with the proof-from-spine that backs each.
+2. **`tone-by-context.md`** — one row per surface context, with audience feeling, surface job, lead attribute, and tone amplifier / muter.
+3. **`consistency-review.md`** — audit of 6–10 recent assets, each line marked consistent · slipping · contradiction, with re-pass list ranked by surface load.
+
+## Gotcha
+
+- A voice that pleases the room is usually below the noise floor — agreement is consensus, not distinctiveness.
+- The *not-Y* is the work. *"Confident, not boastful"* is meaningful; *"confident, not weak"* is filler.
+- Tone-by-context matrices over-amplify when the surface is high-stakes — a calm voice in error copy is the discipline, not the failure.
+
+## Do NOT
+
+- Do NOT exceed three attributes — the fourth collapses on the first deadline.
+- Do NOT prescribe channel-specific tactics or copywriting rules; tactics live with the channel owner.
+- Do NOT promise voice attributes the product cannot back — *"effortless"* without an integration story is fiction the support queue will pay for.
+
+## Runnable example
+
+Mid-market HR analytics tool, positioning locked (retention beats acquisition), audience matrix has HR director · CFO · IT-security:
+
+- Voice attributes — *"Precise, not pedantic."* · *"Confident, not boastful."* · *"Concrete, not buzzword."*
+- Tone-by-context — *Error copy:* audience scared, lead with *precise*, mute *confident*. *Marketing surface:* audience curious, lead with *concrete*, amplify *confident*. *Onboarding:* audience uncertain, lead with *precise*, amplify warmth modifier.
+- Consistency review — 8 of 10 surveyed assets *consistent*; 1 *slipping* (CEO blog leans pedantic); 1 *contradiction* (homepage hero contradicts *not buzzword* with "synergistic"). Re-pass list: homepage hero (load-bearing surface, prioritised).
+- Hand-off → writers across surfaces; `release-comms` voice-reviews the GA-wave announcement.

package/.agent-src/templates/agents/agent-project-settings.example.yml

@@ -39,7 +39,7 @@ schema_version: 1
 # CI guard: a release bump of `package.json` must update this value
 # in lockstep — see scripts/check_template_pin_drift.py (road-to-
 # portable-runtime-and-update-check P3.3).
-agent_config_version: "2.3.0"
+agent_config_version: "2.8.0"
 
 # --- Project identity ---
 project:

package/.agent-src/templates/scripts/telemetry/settings.py

@@ -18,6 +18,12 @@ DEFAULT_LOG_PATH = Path(".agent-engagement.jsonl")
 DEFAULT_GRANULARITY = "task"
 ALLOWED_GRANULARITIES = ("task", "phase-step", "tool-call")
 
+#: Defaults for the tier-usage signal (Phase 5 of road-to-surface-discipline).
+#: Separate file, separate opt-in, same default-off posture. Contract:
+#: ``docs/contracts/command-clusters.md#tier-usage-signal-contract``.
+DEFAULT_TIER_USAGE_LOG_PATH = Path(".agent-tier-usage.jsonl")
+DEFAULT_TIER_USAGE_RETIER = {"window_days": 30, "min_invocations": 20, "min_distinct_users": 3}
+
 
 @dataclass(frozen=True)
 class TelemetrySettings:
@@ -104,9 +110,68 @@ def read_settings(path: Path) -> TelemetrySettings:
     return settings
 
 
+@dataclass(frozen=True)
+class TierUsageSettings:
+    enabled: bool
+    log_path: Path
+    window_days: int
+    min_invocations: int
+    min_distinct_users: int
+
+
+def read_tier_usage_settings(path: Path) -> TierUsageSettings:
+    """Return parsed tier-usage settings — never raises on missing data.
+
+    Sibling of :func:`read_settings`; reads the
+    ``telemetry.tier_usage`` namespace from ``.agent-settings.yml``.
+    Default-off, same parse-tolerant shape — a missing file, a missing
+    section, or PyYAML being absent all collapse to ``enabled=False``.
+    """
+    section: dict[str, Any] = {}
+    if path.is_file():
+        try:
+            import yaml  # type: ignore[import-not-found]
+        except ImportError:
+            yaml = None  # type: ignore[assignment]
+        if yaml is not None:
+            try:
+                raw = yaml.safe_load(path.read_text(encoding="utf-8")) or {}
+            except Exception:
+                raw = {}
+            if isinstance(raw, dict):
+                tele = raw.get("telemetry")
+                if isinstance(tele, dict):
+                    tu = tele.get("tier_usage")
+                    if isinstance(tu, dict):
+                        section = tu
+
+    output = section.get("output") if isinstance(section.get("output"), dict) else {}
+    retier = section.get("retier") if isinstance(section.get("retier"), dict) else {}
+    defaults = DEFAULT_TIER_USAGE_RETIER
+
+    def _coerce_int(value: Any, default: int) -> int:
+        if isinstance(value, bool):
+            return default
+        if isinstance(value, int) and value >= 0:
+            return value
+        return default
+
+    return TierUsageSettings(
+        enabled=_coerce_bool(section.get("enabled"), default=False),
+        log_path=_coerce_path(output.get("path"), DEFAULT_TIER_USAGE_LOG_PATH),
+        window_days=_coerce_int(retier.get("window_days"), defaults["window_days"]),
+        min_invocations=_coerce_int(retier.get("min_invocations"), defaults["min_invocations"]),
+        min_distinct_users=_coerce_int(retier.get("min_distinct_users"), defaults["min_distinct_users"]),
+    )
+
+
 __all__ = [
     "DEFAULT_GRANULARITY",
     "DEFAULT_LOG_PATH",
+    "DEFAULT_TIER_USAGE_LOG_PATH",
+    "DEFAULT_TIER_USAGE_RETIER",
     "TelemetrySettings",
+    "TierUsageSettings",
     "read_settings",
+    "read_tier_usage_settings",
 ]

package/.agent-src/templates/scripts/tier_usage_report.py

@@ -0,0 +1,183 @@
+#!/usr/bin/env python3
+"""Tier-usage report — aggregate the local tier-usage log into a frequency table.
+
+Phase 5 Step 3 of road-to-surface-discipline. Reads the JSONL log
+written by the dispatcher (default ``.agent-tier-usage.jsonl``; override
+via ``telemetry.tier_usage.output.path``) and emits a per-command
+frequency table grouped by tier, plus distinct ``user_hash`` counts.
+Run-local-only; no upload, no remote aggregation.
+
+Privacy floor mirrors the contract in
+``docs/contracts/command-clusters.md#tier-usage-signal-contract`` and
+the four-layer enforcement model used by artefact-engagement telemetry.
+Records that carry any field outside the contract whitelist are dropped
+at the read gate — the report refuses to render leaked shapes rather
+than re-emit them.
+
+Usage:
+    python3 tier_usage_report.py                       # last 30d, table
+    python3 tier_usage_report.py --window-days 7       # last 7d
+    python3 tier_usage_report.py --window-days 0       # full log
+    python3 tier_usage_report.py --json                # JSON for tooling
+    python3 tier_usage_report.py --log-path X.jsonl    # archived snapshot
+
+Exit codes:
+    0   success or telemetry disabled (single header line)
+    1   no records survived the privacy floor on a non-empty file
+    2   IO error (permission denied; passed path missing)
+"""
+from __future__ import annotations
+
+import argparse
+import json
+import sys
+from collections import defaultdict
+from datetime import datetime, timedelta, timezone
+from pathlib import Path
+from typing import Any
+
+from telemetry.settings import DEFAULT_TIER_USAGE_LOG_PATH, read_tier_usage_settings
+
+#: Contract whitelist (see ``docs/contracts/command-clusters.md``).
+ALLOWED_FIELDS = frozenset({"ts_bucket", "command", "tier", "outcome", "user_hash"})
+ALLOWED_OUTCOMES = frozenset({"success", "error", "blocked"})
+
+
+def _parse_record(raw: str) -> dict[str, Any] | None:
+    """Return a sanitized record or ``None`` when the line violates the floor."""
+    try:
+        obj = json.loads(raw)
+    except json.JSONDecodeError:
+        return None
+    if not isinstance(obj, dict):
+        return None
+    if not set(obj.keys()).issubset(ALLOWED_FIELDS):
+        return None
+    cmd = obj.get("command")
+    if not isinstance(cmd, str) or not cmd or "/" in cmd or "\\" in cmd:
+        return None
+    if not isinstance(obj.get("tier"), int) or obj["tier"] not in (0, 1, 2, 3):
+        return None
+    if obj.get("outcome") not in ALLOWED_OUTCOMES:
+        return None
+    uh = obj.get("user_hash")
+    if not isinstance(uh, str) or len(uh) != 16:
+        return None
+    if not isinstance(obj.get("ts_bucket"), str):
+        return None
+    return obj
+
+
+def _within_window(ts_bucket: str, window_days: int | None) -> bool:
+    if window_days is None or window_days == 0:
+        return True
+    try:
+        ts = datetime.fromisoformat(ts_bucket.replace("Z", "+00:00"))
+    except ValueError:
+        return False
+    if ts.tzinfo is None:
+        ts = ts.replace(tzinfo=timezone.utc)
+    return ts >= datetime.now(timezone.utc) - timedelta(days=window_days)
+
+
+def aggregate(
+    log_path: Path, window_days: int,
+) -> tuple[dict[tuple[int, str], dict[str, Any]], int, int]:
+    """Return ``((tier, command) -> stats, total_lines, kept)`` over the window."""
+    buckets: dict[tuple[int, str], dict[str, Any]] = defaultdict(
+        lambda: {"count": 0, "users": set()},
+    )
+    total = 0
+    kept = 0
+    if not log_path.exists():
+        return {}, 0, 0
+    with log_path.open("r", encoding="utf-8") as fh:
+        for line in fh:
+            line = line.strip()
+            if not line:
+                continue
+            total += 1
+            rec = _parse_record(line)
+            if rec is None:
+                continue
+            if not _within_window(rec["ts_bucket"], window_days):
+                continue
+            kept += 1
+            key = (int(rec["tier"]), rec["command"])
+            buckets[key]["count"] += 1
+            buckets[key]["users"].add(rec["user_hash"])
+    out = {k: {"count": v["count"], "distinct_users": len(v["users"])}
+           for k, v in buckets.items()}
+    return out, total, kept
+
+
+def render(
+    table: dict[tuple[int, str], dict[str, Any]],
+    window_days: int,
+) -> str:
+    suffix = f" (last {window_days}d)" if window_days else " (full log)"
+    if not table:
+        return f"(no tier-usage records{suffix})\n"
+    rows = sorted(table.items(), key=lambda kv: (kv[0][0], -kv[1]["count"], kv[0][1]))
+    header = f"{'Tier':<6}{'Command':<32}{'Calls':>8}{'Users':>8}"
+    lines = [header, "-" * len(header)]
+    for (tier, command), stats in rows:
+        lines.append(
+            f"{tier:<6}{command:<32}{stats['count']:>8}{stats['distinct_users']:>8}",
+        )
+    lines.append(f"\n(window:{suffix.strip()})")
+    return "\n".join(lines) + "\n"
+
+
+def main(argv: list[str] | None = None) -> int:
+    parser = argparse.ArgumentParser(description="Tier-usage frequency report.")
+    parser.add_argument("--window-days", type=int, default=30,
+                        help="trailing window in days (0 = full log)")
+    parser.add_argument("--json", action="store_true",
+                        help="emit JSON instead of the table")
+    parser.add_argument("--log-path", type=Path, default=None,
+                        help="override settings; read an archived log")
+    parser.add_argument("--settings-file", type=Path, default=Path(".agent-settings.yml"))
+    args = parser.parse_args(argv)
+
+    settings = read_tier_usage_settings(args.settings_file)
+    log_path = args.log_path or settings.log_path or DEFAULT_TIER_USAGE_LOG_PATH
+
+    if args.log_path is None and not settings.enabled:
+        sys.stdout.write(
+            "(tier-usage telemetry disabled; set "
+            "`telemetry.tier_usage.enabled: true` in .agent-settings.yml)\n",
+        )
+        return 0
+
+    try:
+        table, total, kept = aggregate(log_path, args.window_days)
+    except OSError as exc:
+        print(f"❌  {exc}", file=sys.stderr)
+        return 2
+
+    if total > 0 and kept == 0:
+        print(f"❌  {total} record(s) read; 0 survived the privacy floor — "
+              "report refused", file=sys.stderr)
+        return 1
+
+    if args.json:
+        payload = {
+            "window_days": args.window_days,
+            "log_path": str(log_path),
+            "records_total": total,
+            "records_kept": kept,
+            "rows": [
+                {"tier": t, "command": c, "count": v["count"],
+                 "distinct_users": v["distinct_users"]}
+                for (t, c), v in sorted(table.items(), key=lambda kv: (kv[0][0], kv[0][1]))
+            ],
+        }
+        sys.stdout.write(json.dumps(payload, indent=2) + "\n")
+    else:
+        sys.stdout.write(render(table, args.window_days))
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())

package/.claude-plugin/marketplace.json

@@ -6,7 +6,7 @@
   },
   "metadata": {
     "description": "Shared agent configuration \u2014 skills for AI coding tools (Claude Code, Augment, Cursor, Cline, Windsurf, Gemini CLI).",
-    "version": "2.7.0",
+    "version": "2.9.0",
     "keywords": [
       "agent-config",
       "skills",
@@ -42,6 +42,7 @@
       "strict": false,
       "skills": [
         "./.claude/skills/accessibility-auditor",
+        "./.claude/skills/activation-design",
         "./.claude/skills/adr-create",
         "./.claude/skills/adversarial-review",
         "./.claude/skills/agent-docs-writing",
@@ -69,6 +70,7 @@
         "./.claude/skills/bug-analyzer",
         "./.claude/skills/bug-fix",
         "./.claude/skills/bug-investigate",
+        "./.claude/skills/build-buy-partner",
         "./.claude/skills/challenge-me",
         "./.claude/skills/challenge-me-vision",
         "./.claude/skills/challenge-me-with-docs",
@@ -78,20 +80,25 @@
         "./.claude/skills/chat-history-show",
         "./.claude/skills/check-current-md",
         "./.claude/skills/check-refs",
+        "./.claude/skills/churn-prevention",
         "./.claude/skills/code-refactoring",
         "./.claude/skills/code-review",
         "./.claude/skills/command-routing",
         "./.claude/skills/command-writing",
         "./.claude/skills/commit",
         "./.claude/skills/commit-in-chunks",
-        "./.claude/skills/composer-packages",
+        "./.claude/skills/comp-banding",
+        "./.claude/skills/competitive-moat-analysis",
         "./.claude/skills/competitive-positioning",
+        "./.claude/skills/composer-packages",
         "./.claude/skills/compress",
+        "./.claude/skills/content-funnel-design",
         "./.claude/skills/context",
         "./.claude/skills/context-authoring",
         "./.claude/skills/context-create",
         "./.claude/skills/context-document",
         "./.claude/skills/context-refactor",
+        "./.claude/skills/contracts-cognition",
         "./.claude/skills/conventional-commits-writing",
         "./.claude/skills/copilot-agents-optimization",
         "./.claude/skills/copilot-config",
@@ -106,8 +113,10 @@
         "./.claude/skills/customer-research",
         "./.claude/skills/dashboard-design",
         "./.claude/skills/data-flow-mapper",
+        "./.claude/skills/data-handling-judgment",
         "./.claude/skills/database",
         "./.claude/skills/dcf-modeling",
+        "./.claude/skills/deal-qualification-meddic",
         "./.claude/skills/decision-record",
         "./.claude/skills/deep-reading-analyst",
         "./.claude/skills/defense-in-depth",
@@ -121,10 +130,12 @@
         "./.claude/skills/dto-creator",
         "./.claude/skills/e2e-heal",
         "./.claude/skills/e2e-plan",
+        "./.claude/skills/editorial-calendar",
         "./.claude/skills/eloquent",
         "./.claude/skills/error-handling-patterns",
         "./.claude/skills/estimate-ticket",
         "./.claude/skills/existing-ui-audit",
+        "./.claude/skills/expansion-playbook",
         "./.claude/skills/fe-design",
         "./.claude/skills/feature",
         "./.claude/skills/feature-dev",
@@ -144,13 +155,18 @@
         "./.claude/skills/fix-refs",
         "./.claude/skills/fix-seeder",
         "./.claude/skills/flux",
+        "./.claude/skills/forecast-accuracy",
+        "./.claude/skills/forecasting",
         "./.claude/skills/form-handler",
+        "./.claude/skills/fundraising-narrative",
         "./.claude/skills/funnel-analysis",
         "./.claude/skills/git-workflow",
         "./.claude/skills/github-ci",
         "./.claude/skills/grafana",
         "./.claude/skills/grill-me",
+        "./.claude/skills/gtm-launch",
         "./.claude/skills/guideline-writing",
+        "./.claude/skills/hiring-loop-design",
         "./.claude/skills/implement-ticket",
         "./.claude/skills/incident-commander",
         "./.claude/skills/jira-integration",
@@ -180,6 +196,7 @@
         "./.claude/skills/livewire",
         "./.claude/skills/livewire-architect",
         "./.claude/skills/logging-monitoring",
+        "./.claude/skills/market-entry-analysis",
         "./.claude/skills/markitdown",
         "./.claude/skills/mcp",
         "./.claude/skills/mcp-builder",
@@ -192,6 +209,7 @@
         "./.claude/skills/memory-promote",
         "./.claude/skills/memory-propose",
         "./.claude/skills/merge-conflicts",
+        "./.claude/skills/messaging-architecture",
         "./.claude/skills/migration-architect",
         "./.claude/skills/migration-creator",
         "./.claude/skills/mobile-e2e-strategy",
@@ -203,6 +221,9 @@
         "./.claude/skills/multi-tenancy",
         "./.claude/skills/okr-tree-modeling",
         "./.claude/skills/onboard",
+        "./.claude/skills/onboarding-design",
+        "./.claude/skills/onboarding-program",
+        "./.claude/skills/one-on-one-cadence",
         "./.claude/skills/openapi",
         "./.claude/skills/optimize",
         "./.claude/skills/optimize-agents-dir",
@@ -211,12 +232,14 @@
         "./.claude/skills/optimize-rtk",
         "./.claude/skills/optimize-skills",
         "./.claude/skills/orchestrate",
+        "./.claude/skills/org-design",
         "./.claude/skills/override",
         "./.claude/skills/override-create",
         "./.claude/skills/override-manage",
         "./.claude/skills/override-management",
         "./.claude/skills/package-reset",
         "./.claude/skills/package-test",
+        "./.claude/skills/perf-feedback-craft",
         "./.claude/skills/performance",
         "./.claude/skills/performance-analysis",
         "./.claude/skills/persona-writing",
@@ -224,10 +247,13 @@
         "./.claude/skills/php-coder",
         "./.claude/skills/php-debugging",
         "./.claude/skills/php-service",
+        "./.claude/skills/pipeline-strategy",
         "./.claude/skills/playwright-architect",
         "./.claude/skills/playwright-testing",
         "./.claude/skills/po-discovery",
+        "./.claude/skills/positioning-strategy",
         "./.claude/skills/prepare-for-review",
+        "./.claude/skills/privacy-review",
         "./.claude/skills/project-analysis-core",
         "./.claude/skills/project-analysis-hypothesis-driven",
         "./.claude/skills/project-analysis-laravel",
@@ -258,6 +284,7 @@
         "./.claude/skills/research",
         "./.claude/skills/research-deep",
         "./.claude/skills/research-report",
+        "./.claude/skills/retention-loops",
         "./.claude/skills/review-changes",
         "./.claude/skills/review-routing",
         "./.claude/skills/rice-prioritization",
@@ -273,6 +300,8 @@
         "./.claude/skills/rtk-output-filtering",
         "./.claude/skills/rule-compliance-audit",
         "./.claude/skills/rule-writing",
+        "./.claude/skills/runway-cognition",
+        "./.claude/skills/scenario-modeling",
         "./.claude/skills/script-writing",
         "./.claude/skills/secrets-management",
         "./.claude/skills/security",
@@ -304,6 +333,7 @@
         "./.claude/skills/tests-execute",
         "./.claude/skills/threat-model",
         "./.claude/skills/threat-modeling",
+        "./.claude/skills/throughput-vs-morale-tradeoff",
         "./.claude/skills/token-optimizer",
         "./.claude/skills/traefik",
         "./.claude/skills/ui-component-architect",
@@ -314,7 +344,9 @@
         "./.claude/skills/using-git-worktrees",
         "./.claude/skills/validate-feature-fit",
         "./.claude/skills/verify-completion-evidence",
+        "./.claude/skills/vision-articulation",
         "./.claude/skills/voc-extract",
+        "./.claude/skills/voice-and-tone-design",
         "./.claude/skills/websocket",
         "./.claude/skills/work"
       ]

package/AGENTS.md

@@ -20,7 +20,7 @@ task ci                # full pipeline — green before PR
 - **Kernel + Router** (beta) — 9 always-loaded Iron-Law rules, tier-1 / tier-2 routing, cost profiles, per-rule char caps enforced by `task lint-rule-budget`: [`kernel-membership`](docs/contracts/kernel-membership.md) + [`rule-router`](docs/contracts/rule-router.md).
 - **Content pipelines** — A [compression](docs/architecture/compression.md), B [Augment projection](docs/architecture/augment-projection.md), C [multi-tool projection](docs/architecture/multi-tool-projection.md), D [Claude.ai bundle](docs/architecture/claude-bundle.md). Index: [`docs/architecture.md`](docs/architecture.md).
 - **Editing this repo** — Iron-Law rules (portability, source-of-truth, skill-quality) + Thin-Root contract: [`augment-portability`](.agent-src/rules/augment-portability.md), [`augment-source-of-truth`](.agent-src/rules/augment-source-of-truth.md), [`skill-quality`](.agent-src/rules/skill-quality.md), [`agents-md-thin-root`](.agent-src/skills/agents-md-thin-root/SKILL.md).
-- **Consumer story** — `npm install` + `scripts/install.sh` + `.agent-settings.yml` opt-in flags, sandbox/offline install paths, verified-offline manifest: [`README.md`](README.md).
+- **Consumer story** — `npx` + `scripts/install.sh` + `.agent-settings.yml` opt-in flags, sandbox/offline install paths, verified-offline manifest: [`README.md`](README.md).
 - **Personas** — 11 review-lens cast (6 core · 5 specialist), `personas:` vs `/mode` axes, citation map, override pattern: [`docs/personas.md`](docs/personas.md), schema [`docs/contracts/persona-schema.md`](docs/contracts/persona-schema.md) (beta).
 
 ## Emergency triage — read this when nothing else is reachable