Detect mode drift in Tim's client delivery. Catches when he's explaining instead of deciding, teaching instead of architecting. Content-agnostic, context-aware. Use for "strategy check", "mode check", "am I explaining again".
From uxinatornpx claudepluginhub jabberlockie/the-human-stack-plugins-public --plugin uxinatorThis skill uses the workspace's default tool permissions.
Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.
Migrates code, prompts, and API calls from Claude Sonnet 4.0/4.5 or Opus 4.1 to Opus 4.5, updating model strings on Anthropic, AWS, GCP, Azure platforms.
Details PluginEval's skill quality evaluation: 3 layers (static, LLM judge), 10 dimensions, rubrics, formulas, anti-patterns, badges. Use to interpret scores, improve triggering, calibrate thresholds.
Pre-delivery and real-time audit that detects when Tim is in the wrong delivery mode for the context. The most common drift: Tim defaults to EXPLAIN (teaching frameworks) when the client hired him to DECIDE (make recommendations).
From the input, identify:
CONTEXT CHECK
─────────────
Client: [Who is this for?]
Relationship: [Prospect | New client 0-90 days | Active client | Conference attendee]
Audience Size: [1-5 | 6-30 | 30+]
Engagement Type: [One-time | Multi-session | Ongoing retainer]
What They Paid For: [Keynote | Workshop/Training | Diagnostic | Managed Success | Advisory]
Their JTBD: [What job did they hire Tim for? — pull from JTBD if available]
REQUIRED MODE: [KEYNOTE | TRAINING | STRATEGY]
CONFIDENCE: [HIGH | MEDIUM — explain if medium]
Mode Selection Logic:
Scan the input for mode signals:
EXPLAIN signals (Tim is teaching — WRONG for strategy):
DECIDE signals (Tim is strategizing — RIGHT for strategy):
PROVOKE signals (Tim is keynoting — RIGHT for keynotes):
STRATEGY AUDIT
══════════════
INPUT: [What was reviewed]
REQUIRED MODE: [KEYNOTE | TRAINING | STRATEGY]
ACTUAL MODE: [What Tim is actually doing]
DRIFT DETECTED: [YES — explain | NO]
MODE DRIFT MAP:
──────────────────────────────────────────────────────
SECTION/MOMENT | REQUIRED | ACTUAL | ISSUE
──────────────────────────────────────────────────────
[Section 1] | STRATEGY | EXPLAIN | [What's happening and why it's wrong]
──────────────────────────────────────────────────────
[Section 2] | STRATEGY | STRATEGY | ✓ On mode
──────────────────────────────────────────────────────
DRIFT SCORE: [X/10] — 10 = perfectly on mode, 1 = completely wrong mode
TOP 3 DRIFT MOMENTS:
1. [Exact quote or section] — SHOULD HAVE BEEN: [what to say/do instead]
2. [Exact quote or section] — SHOULD HAVE BEEN: [what to say/do instead]
3. [Exact quote or section] — SHOULD HAVE BEEN: [what to say/do instead]
EXPECTATION GAP ANALYSIS
─────────────────────────
EXPECTATION ORIGINS:
┌─────────────┬──────────────────────────────────────┬──────────┐
│ ORIGIN │ EXPECTATION FOUND │ MANAGED? │
├─────────────┼──────────────────────────────────────┼──────────┤
│ DECLARED │ [What Tim explicitly promised] │ YES | NO │
│ TRANSFERRED │ [From past experiences with similar] │ YES | NO │
│ INFERRED │ [What Tim's signals imply] │ YES | NO │
│ DEFAULT │ [What fills the vacuum — invisible] │ YES | NO │
│ SOCIAL │ [What third parties set] │ YES | NO │
└─────────────┴──────────────────────────────────────┴──────────┘
UNMANAGED EXPECTATIONS: [List — these are active risk]
DYNAMICS AT PLAY:
- Asymmetry: [Downside expectation that could hurt 2x?]
- Anchoring: [First impression set that's hard to move?]
- Peak-End: [Peak moment and ending managed?]
- Compounding: [Expectations cascading across stakeholders?]
- Decay: [Expectations eroding without reinforcement?]
DELIVERABLE GAP
───────────────
What the client expects to RECEIVE:
[List — pull from JTBD "desired outcome" if available]
What Tim is currently PRODUCING:
[List — based on actual mode analysis]
GAP:
[Where deliverable expectations ≠ actual output]
ACTIONS:
1. [Specific and concrete]
2. [Specific and concrete]
3. [Specific and concrete]
The Professor Trap: Explaining WHY a framework works instead of APPLYING it. → "They didn't hire a professor. What's your recommendation?"
The Options Buffet: Presenting 3-4 approaches and asking the client to choose. → "Pick one. Recommend it. Defend it."
The Insight Without Artifact: Brilliant verbal insight that disappears when the call ends. → "If it's not written down, it didn't happen."
The Theory Preamble: 15 minutes of theoretical context before the recommendation. → "Lead with the recommendation. Add theory only if they ask why."
The Empathy Detour: High I spends too long validating feelings instead of moving to action. → "You've acknowledged it. Now solve it."
The Adjacent Exploration: Quickstart 9 chases a related pattern. → "Park it. Come back to what they're paying for."
The Missing Follow-Through: Session ends without documented next steps. → "Before this call ends: who does what by when?"