@event4u/agent-config 2.7.0 → 2.8.0

package/.agent-src/skills/positioning-strategy/SKILL.md

@@ -0,0 +1,177 @@
+---
+name: positioning-strategy
+description: "Use when locking the market frame — category, segment, alternative, point-of-view — before messaging, launch, or pricing rides on it. Triggers on 'who are we for', 'opposable audit'."
+status: active
+tier: senior
+source: package
+domain: product
+context_spine: [product, customer-segment]
+---
+
+# positioning-strategy
+
+## When to use
+
+- A category sentence is missing or contested and the next artefact (messaging, launch, pricing page) is about to inherit the ambiguity.
+- The team can name what the product **does** but cannot name **who it is for**, **against what alternative**, or **what it refuses to be**.
+- An opposable-positioning audit is needed: every claim has to survive *"a reasonable competitor would argue the opposite"*.
+
+Do NOT use for peer-versus-peer feature comparison (route to
+`competitive-positioning`), copy generation (route to
+`messaging-architecture`), or pricing-tier construction.
+
+## Cognition cluster
+
+- **Mental model 1 — First-principles thinking.** Strip the category to
+  the underlying job: who fires what, to make what progress, under
+  what pressure. Inherited category labels are the trap; the unit of
+  positioning is the job, not the label. See
+  [`docs/contracts/mental-models.md`](../../../docs/contracts/mental-models.md) § 1.
+- **Mental model 30 — Inversion.** For every positioning claim, ask
+  *"what would a competitor with a credible alternative argue against
+  this?"* A claim that has no opposable counter is either trivially
+  true or invented — drop it. See `mental-models.md` § 30.
+- **Context-spine — product + customer-segment.** Read the **product**
+  slot for non-goals and the **customer-segment** slot for the ICP
+  shape before locking the frame. Positioning that contradicts either
+  slot fails its own audit. See
+  [`context-spine`](../../../docs/contracts/context-spine.md).
+
+## Procedure
+
+### Step 0: Frame the job
+
+Write one sentence: *"\<Segment\> hires \<category\> to make progress
+in \<situation\>, when motivated by \<pressure\>, expecting
+\<outcome\>."* If you cannot finish the sentence, route to
+[`customer-research`](../customer-research/SKILL.md); positioning
+without job-evidence is invention, not earning.
+
+### Step 1: Lock the four anchors
+
+Each anchor is one sentence; ambiguity here propagates.
+
+1. **Category.** *"We are a \<category\>."* The category must be a
+   noun that the segment already uses to describe the budget line
+   the purchase comes out of — not a coined term.
+2. **Segment.** *"For \<segment\>."* Specific enough that a single
+   buyer recognises themselves; broad enough that the segment has
+   shared switch-events.
+3. **Alternative.** *"Instead of \<alternative\>."* Name the
+   single most-likely incumbent — usually a manual workflow, a
+   spreadsheet, or a competing product. *"Doing nothing"* counts.
+4. **Point of view.** *"Because \<load-bearing belief\>."* The
+   belief must be opposable — a credible peer holds the opposite.
+
+### Step 2: Validate via the opposable audit
+
+For every anchor, write the **strongest counter** a credible peer
+would make. Validate each anchor against the rule *"a credible peer
+holds the opposite"* — if no counter exists, the anchor is
+unfalsifiable (either trivially true or invented) and must be
+replaced before continuing.
+
+The four counters become the **assumption ledger**: explicit beliefs
+the positioning rides on. Each gets a re-evaluation trigger (event +
+metric + threshold) the team will watch for.
+
+### Step 3: Identify non-goals
+
+Write three sentences in the form *"We are not for \<adjacent
+segment\>, even though \<surface similarity\>, because \<reason
+grounded in the product slot\>."* Non-goals are how positioning
+earns its category — without them every prospect looks like a fit
+and the segment dissolves.
+
+### Step 4: Stress-test the frame
+
+For each anchor, walk the chain *"if this is true, then…"* through
+two consequences. If a consequence contradicts the product slot,
+the segment slot, or a shipped commitment, the anchor is wrong —
+fix the anchor, not the consequence.
+
+### Step 5: Hand back
+
+Hand the four anchors + assumption ledger + non-goals to
+[`messaging-architecture`](../messaging-architecture/SKILL.md) for
+primary-message construction. Do **not** write copy inside this
+skill — that is `messaging-architecture`'s job.
+
+## Related Skills
+
+**WHEN to use this**
+
+- The unit of work is the four-anchor frame, not a copy block.
+- A category sentence is contested and the next artefact rides on it.
+- An opposable audit is overdue and the team is shipping claims on faith.
+
+**WHEN NOT to use this**
+
+- Peer-vs-peer ours-vs-theirs verdict table — route to
+  [`competitive-positioning`](../competitive-positioning/SKILL.md).
+- Primary message + supporting proofs construction — route to
+  [`messaging-architecture`](../messaging-architecture/SKILL.md).
+- Fundraising "why now / why us" framing under capital constraint —
+  route to [`fundraising-narrative`](../fundraising-narrative/SKILL.md).
+- Pricing-tier construction or unit-economics modelling — route to
+  [`unit-economics-modeling`](../unit-economics-modeling/SKILL.md).
+
+## When the agent should load this
+
+- "Wer sind wir eigentlich für?"
+- "Lock the positioning before we write the launch deck."
+- "Brauche eine Category-Sentence für die Pricing-Page."
+- "Run an opposable-positioning audit on the homepage frame."
+- "Welche Alternative ranken wir uns gegen — Doing Nothing oder ein konkreter Wettbewerber?"
+
+## Output
+
+1. **`positioning.md`** — the four anchors (category · segment ·
+   alternative · point-of-view), one sentence each, opposable.
+2. **`assumption-ledger.md`** — one row per anchor: the strongest
+   peer-counter, the load-bearing belief, the re-evaluation trigger
+   (event + metric + threshold).
+3. **`non-goals.md`** — three sentences naming adjacent segments the
+   product refuses to serve, each grounded in the product slot.
+
+## Gotcha
+
+- A category sentence the segment does not already use is a coined
+  term, not a category — the segment will route around it.
+- *"Doing nothing"* is the most common alternative and the most
+  often skipped. If the buyer's status quo is free, the alternative
+  is free, and the positioning has to clear that bar.
+- A positioning frame without non-goals expands until everyone is a
+  prospect; that is the failure mode, not the success state.
+
+## Do NOT
+
+- Do NOT invent a category to differentiate — earned categories
+  beat coined categories; category theatre is the council Q1
+  out-of-scope.
+- Do NOT collapse positioning into a tagline; the four anchors are
+  the artefact, the tagline is a downstream compression.
+- Do NOT decide pricing tiers from positioning — hand off to
+  pricing / unit-economics work.
+
+## Runnable example
+
+Mid-market HR analytics tool, contested category:
+
+- Frame: *"\<HR leaders at 200–2000-person companies\> hire
+  \<workforce-analytics\> to make progress in \<board-quarter
+  retention reporting\>, when motivated by \<exec ask for cohort
+  attrition\>, expecting \<one-click roll-up by tenure band\>."*
+- Anchors — **category:** workforce analytics. **Segment:** HR
+  leaders at 200–2000-person, growing-headcount companies.
+  **Alternative:** a manually maintained spreadsheet plus the
+  HRIS-vendor's basic report. **Point of view:** *retention beats
+  acquisition as the lever in this segment*.
+- Assumption ledger — peer counter to point of view: *"acquisition
+  velocity dominates at \< 500 headcount."* Re-evaluation trigger:
+  new-hire-rate > 30 % year-on-year AND retention-flat → revisit.
+- Non-goals — *"We are not for enterprise (5000+); not for
+  workforce-planning (capacity modelling); not for engagement-survey
+  tooling."* Each grounded in the product slot's non-goals list.
+- Hand-off: four anchors → `messaging-architecture` for primary
+  message + audience-by-message matrix.

package/.agent-src/skills/retention-loops/SKILL.md

@@ -0,0 +1,161 @@
+---
+name: retention-loops
+description: "Use when designing product-led retention — habit formation, trigger-action-reward, network vs single-user loops. Triggers on 'why don't users come back', 'design a habit loop'."
+status: active
+tier: senior
+source: package
+domain: product
+context_spine: [product, customer-segment, funnel-stage]
+---
+
+# retention-loops
+
+## When to use
+
+- D30 retention is flat or declining and the team cannot name a single product loop that pulls the user back — retention is treated as marketing's problem, not the product's.
+- A new feature shipped but did not move retention — there is no closed loop between trigger, action, and reward, so the feature is a destination, not a habit.
+- The product depends on a network effect that has not been instrumented as a loop — invites, content, or data are produced but the loop that pulls the next user back is unwritten.
+
+Do NOT use to fix days 0–30 onboarding friction (route to
+`onboarding-design`), classify churn causes (route to
+`churn-prevention`), or design human-led account-expansion plays
+(route to `expansion-playbook`).
+
+## Cognition cluster
+
+- **Mental model 14 — Meadows leverage points.** A retention loop
+  is a feedback structure: the leverage sits in the loop's
+  *gain* (how strong the reward is) and *delay* (how long until
+  the reward lands), not in the surface UI. Pick the leverage
+  point — gain or delay — over surface polish. See
+  [`docs/contracts/mental-models.md`](../../../docs/contracts/mental-models.md) § 14.
+- **Mental model 8 — Compounding.** A loop with even small gain
+  per cycle compounds across cohorts; a one-time activation
+  bump does not. Verify which loops compound before investing
+  cycles into them. See `mental-models.md` § 8.
+- **Mental model 18 — Pull vs. push.** A trigger the user pulls
+  (intrinsic need surfaced by the product) compounds; a trigger
+  the vendor pushes (marketing notification firing) decays the
+  channel and trains the user to mute. See `mental-models.md` § 18.
+- **Context-spine — product + customer-segment + funnel-stage.**
+  Read the **product** slot for which capability can carry a loop
+  (a loop is only as strong as the action it routes through), the
+  **customer-segment** slot for which segments have the latent
+  need the loop addresses, and the **funnel-stage** slot for where
+  the loop sits relative to activation and paid. See
+  [`context-spine`](../../../docs/contracts/context-spine.md).
+
+## Procedure
+
+### Step 0: Inspect — name the current loops, if any
+
+Inspect the product. For each suspected loop, write the closed
+form: *"\<trigger\> → \<action\> → \<reward\> → \<trigger again\>."*
+If the loop cannot be written closed, it is not a loop; it is a
+funnel ending. Inspect whether the reward arrives quickly enough
+to reinforce the action — verify the delay against the segment's
+attention cycle.
+
+### Step 1: Classify each loop as single-user vs network
+
+1. **Single-user loop** — trigger and reward both originate from
+   the same user (a daily-summary email triggered by yesterday's
+   activity).
+2. **Network loop** — trigger or reward involves another user
+   (a teammate's comment, a partner's reply, a customer's reaction).
+
+Network loops compound harder but require minimum-viable-network
+density; below density they look broken. Classify before investing.
+
+### Step 2: Audit the gain and the delay per loop
+
+For each loop:
+
+1. **Gain per cycle** — what observable utility does the user
+   receive (information, social affirmation, time saved, reduced
+   error)? Gain measured as the user's revealed willingness to
+   repeat the action.
+2. **Delay** — time from trigger to reward. A delay longer than the
+   segment's attention window kills the loop regardless of gain.
+3. **Decay** — does the loop weaken when the user already has the
+   reward? Most product loops decay; design the next loop before
+   the first decays.
+
+### Step 3: Pick the binding loop and isolate it
+
+Of the loops named, pick the one whose gain × frequency × eligible
+segment-size is largest. **Verify** the loop is intrinsic-pull, not
+vendor-push: confirm the trigger originates from a user action or
+state, not from a marketing schedule. A push-trigger labelled as a
+loop will burn the channel.
+
+### Step 4: Design the missing step, not the missing UI
+
+If the binding loop is broken, the broken step is almost always:
+*trigger missing*, *action too far from trigger*, *reward delayed*,
+or *no path back to next trigger*. Design the missing **step**, not
+a UI tweak. UI tweaks polish a loop that already closes; they do
+not close an open one.
+
+### Step 5: Hand back
+
+Hand the loop inventory, the binding-loop selection with gain /
+delay / decay, and the step-level redesign to the implementing
+team and to
+[`activation-design`](../activation-design/SKILL.md) — activation
+is the loop's first cycle, and the activation event must complete
+the first cycle of the binding loop. Retention work without a named
+loop is rearranging notifications.
+
+## Related Skills
+
+**WHEN to use this**
+
+- Designing or auditing product-led retention loops.
+- Selecting the binding loop and redesigning its missing step.
+
+**WHEN NOT to use this**
+
+- Days 0–30 onboarding milestones — route to
+  [`onboarding-design`](../onboarding-design/SKILL.md).
+- Cause-classification of churn events — route to
+  [`churn-prevention`](../churn-prevention/SKILL.md).
+- Human-led expansion plays — route to
+  [`expansion-playbook`](../expansion-playbook/SKILL.md).
+- Activation-event selection (first cycle of the binding loop) —
+  route to [`activation-design`](../activation-design/SKILL.md).
+
+## When the agent should load this
+
+- "Why don't users come back?"
+- "Design a habit loop for feature X."
+- "Is this loop single-user or network?"
+- "Welcher Loop tr\u00e4gt eigentlich unsere Retention?"
+
+## Output
+
+1. **`loop-inventory.md`** — every named loop in closed form: trigger → action → reward → next trigger, with single-user vs network tag.
+2. **`gain-delay-audit.md`** — per-loop gain · delay · decay · eligible-segment size · revealed repeat-rate.
+3. **`binding-loop-redesign.md`** — selected loop, the broken step, and the redesign in step terms (not UI terms).
+
+## Gotcha
+
+- A loop whose reward arrives outside the segment's attention window will look broken even when gain is high; delay kills loops more often than gain does.
+- A network loop below minimum-viable density behaves like an open funnel; instrumenting it and designing it before density is theatre.
+- *"Notifications fire daily"* is not a loop; it is a push schedule. A loop needs a closed return path from reward to next trigger that the user — not the vendor — closes.
+
+## Do NOT
+
+- Do NOT invest in surface UI on a loop that does not close; the loop closes by adding a step, not polishing one.
+- Do NOT instrument network loops as single-user loops; the metric will look broken until the network reaches density.
+- Do NOT design more than one binding loop at a time; concurrent loop changes destroy the signal.
+
+## Runnable example
+
+Mid-market collaboration tool, D30 retention 41 %, two suspected loops named.
+
+- Loop inventory — *(L1)* user receives daily summary → opens product → reviews changes → leaves a comment → teammate notified (network). *(L2)* user creates a doc → bookmark surfaces in nav → user reopens (single-user).
+- Gain–delay audit — L1 gain medium, delay 24 h (within attention window), decay low (network refreshes); L2 gain low, delay 0, decay high (bookmark stale within a week).
+- Binding loop — L1 selected (gain × frequency × segment-size dominates). Broken step: *"teammate notified"* fires but does not route teammate back to the originating doc — the loop opens.
+- Redesign — add teammate-return path: notification deep-links into the doc at the commented passage; **verify** with cohort A/B at 4-week horizon. Predicted: D30 +6 pp ± 3 pp.
+- Hand-off — loop inventory + redesign → eng team; activation event redefinition (one comment + one teammate notified) handed to `activation-design`.

package/.agent-src/skills/subagent-orchestration/SKILL.md

@@ -149,7 +149,7 @@ worktree → delegated-skill consumes the input shape declared in its
 `## Input` (or `## When the agent should load this`) block. The
 handoff is auditable; `lint_handoffs.py` validates the chain.
 
-**Example chain (W3 launch):** `positioning` (worktree A) →
+**Example chain (W3 launch):** `positioning-strategy` (worktree A) →
 `messaging-architecture` (worktree B, consumes positioning's
 `positioning-statement.md`) → `gtm-launch` (worktree C, consumes
 both prior artifacts). Each worktree carries one branch; the chain

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: "2.7.0"
 
 # --- Project identity ---
 project:

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": "2.8.0",
     "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",
@@ -78,15 +79,17 @@
         "./.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/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",
@@ -108,6 +111,7 @@
         "./.claude/skills/data-flow-mapper",
         "./.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 +125,12 @@
         "./.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",
@@ -144,12 +150,15 @@
         "./.claude/skills/fix-refs",
         "./.claude/skills/fix-seeder",
         "./.claude/skills/flux",
+        "./.claude/skills/forecast-accuracy",
         "./.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/implement-ticket",
         "./.claude/skills/incident-commander",
@@ -192,6 +201,7 @@
         "./.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 +213,7 @@
         "./.claude/skills/multi-tenancy",
         "./.claude/skills/okr-tree-modeling",
         "./.claude/skills/onboard",
+        "./.claude/skills/onboarding-design",
         "./.claude/skills/openapi",
         "./.claude/skills/optimize",
         "./.claude/skills/optimize-agents-dir",
@@ -224,9 +235,11 @@
         "./.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/project-analysis-core",
         "./.claude/skills/project-analysis-hypothesis-driven",
@@ -258,6 +271,7 @@
         "./.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",
@@ -315,6 +329,7 @@
         "./.claude/skills/validate-feature-fit",
         "./.claude/skills/verify-completion-evidence",
         "./.claude/skills/voc-extract",
+        "./.claude/skills/voice-and-tone-design",
         "./.claude/skills/websocket",
         "./.claude/skills/work"
       ]