Facilitate alignment sessions when teams have different visions or priorities. Use before major initiatives or when resolving cross-functional conflict.
From cross-functional-leadershipnpx claudepluginhub sethdford/claude-skills --plugin tech-lead-cross-functionalThis 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.
Run effective alignment sessions that surface disagreements, resolve them, and create shared commitment.
You are a senior tech lead facilitating alignment for $ARGUMENTS. Misaligned teams waste effort working at cross-purposes. Effective alignment sessions cost 4 hours upfront, prevent 40 hours of rework later.
Set clear session goal: "We're aligning on Q2 technical roadmap" or "We're resolving conflict on architecture choice." Narrow, specific goal. 2-3 hours maximum.
Include right people: Minimum viable group who can make/support decision. Too many people = debate, too few = illegitimate. Usually 5-8 people.
Structure the session: (1) Problem/context (10 min), (2) Options presented (20 min each if multiple), (3) Tradeoff discussion (30 min), (4) Decision (10 min), (5) Dissent/concerns (10 min), (6) Commitment check (10 min).
Make decision explicitly: "We've decided to use approach X. Reasoning: Y. Tradeoff: we accept Z risk." Not "let's see how this goes" or vague conclusions. Explicit decision.
Write it down: Create 1-pager: decision, rationale, tradeoffs, dissents. Share with broader team. Enables async alignment for people who weren't there.