Agent skill · Workflow & Productivity

ai-strategist

Use when evaluating AI tools and agentic workflows against workflow gaps, when conducting quarterly landscape scans, or when assessing integration feasibility of new tools for startup workflows.

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill ai-strategist --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 20 KB
Bundled scripts: none
Path: skills/analysis/ai-strategist/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

Review
written from the skill's own SKILL.md · Aug 5, 2026

What it does

ai-strategist is an orchestrator that coordinates parallel research agents to scan the AI tool landscape, evaluate tools against identified workflow gaps using a weighted scoring framework with sensitivity analysis, and produce a prioritized integration roadmap. It does not perform specialist work itself, but delegates to researchers, strategists, editors, devils-advocates, and other roles to gather data, score tools, and synthesize outputs into a roadmap.

How it works

  • Acts as the coordinator across Phase 0 through Phase 6, delegating specialist tasks via the Task tool and asserting orchestrator-owned responsibilities (session setup, state management, quality gates, user communication, handoffs).
  • Phase 0 creates a session with a workspace and state tracking; Phase 1 refines scope via requirements-analyst; Phase 2 fans out 3-4 researchers to collect landscape data; Phase 3 has a strategist score tools using a weighted matrix; Phase 4 synthesizes phase 2 and phase 3 outputs into an integration roadmap; Phase 5 invites adversarial review; Phase 6 delegates editorial polish.
  • Uses a 7-phase pipeline with defined handoffs, state anchoring, and quality gates (QG0–QG6).
  • Invocation modes include Quarterly scan, Deep Dive, Event-triggered, and Resume; each mode specifies agent counts, minimal tools, user checkpoints, and durations.
  • State and directory management steps are explicitly performed at each phase (e.g., creating session directories, writing handoffs, anchoring state).

When to use it

  • Use for evaluating AI tools and agentic workflows against workflow gaps, conducting quarterly landscape scans, or assessing integration feasibility for startup workflows.

What it can touch

  • Tools: It coordinates via the Task tool to engage specialist skills (requirements-analyst, researcher, strategist, devils-advocate, editor) and references a scoring-matrix and deliverable templates in its workflow. It relies on the outputs produced by those specialists and writes handoffs and final artifacts into designated directories (research, assessment, roadmap, review, final).

Caveats

  • The skill is strictly orchestration: it delegates specialist work and does not perform scoring, gap assessments, or prose polishing itself.
  • It requires that required skills (requirements-analyst, researcher, strategist, devils-advocate, editor) have SKILL instructions available; optional brainstorming-pm is allowed.
  • The workflow enforces a quality gate sequence with specific success criteria (QG0–QG6) and escalation rules for failures.
From the SKILL.md

# ai-strategist: AI Tool Landscape Orchestrator ## Overview ai-strategist is a Tier 1 orchestrator that coordinates parallel research agents to scan the AI tool landscape, evaluate tools against identified workflow gaps using a weighted scoring framework with sensitivity analysis, and produce a prioritized integration roadmap. **Goal**: Produce a scored, prioritized integration roadmap that maps AI tools to specific workflow gaps with actionable next steps across multiple time horizons. **Scope**: 7-phase pipeline (Phase 0-6) coordinating 5 required specialists plus 1 optional specialist. ## Delegation Mandate You are an **orchestrator**. You coordinate specialists -- you do not perform specialist work yourself. You delegate all specialist work using the appropriate tool (see Tool Selection below). This means you do not research tools, do not write strategic assessments, do not challenge recommendations, and do not polish deliverables. Those are specialist tasks. You are NOT a researcher. You do not search for tools or evaluate their features. You are NOT a strategist. You do not write gap assessments or score tools. You are NOT a devil's advocate. You do not challenge recommendati

What's inside
Steps it walks through
  1. Overview
  2. Delegation Mandate
  3. When You Might Be Resisting Delegation
  4. Tool Selection
  5. Invocation Modes
  6. Pre-Flight Validation
  7. State Anchoring
  8. Workflow: 7-Phase Pipeline
  9. Phase 0: Archival Guidelines Review
  10. Phase 1: Scope Refinement
  11. Phase 2: Parallel AI Landscape Research
  12. Phase 3: Strategic Gap Assessment
  13. Phase 4: Integration Roadmap Synthesis (Orchestrator-Owned)
  14. Phase 5: Adversarial Review
Ships with 1 file
  • metadata.json
Commands it runs
for skill in "${REQUIRED_SKILLS[@]}"; do
if [ ! -f "$HOME/.claude/skills/$skill/SKILL.md" ]; then
echo "ABORT: Required skill missing: $skill"
exit 1
fi
done
for skill in "${OPTIONAL_SKILLS[@]}"; do
echo "WARNING: Optional skill missing: $skill (proceeding without)"
More from claude-skill-registry
All skills →
About this skill
What does the ai-strategist skill do?

Use when evaluating AI tools and agentic workflows against workflow gaps, when conducting quarterly landscape scans, or when assessing integration feasibility of new tools for startup workflows.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill ai-strategist --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going