Skip to content

Commit 02dc056

Browse files
geledekclaude
andcommitted
people-tool-selection: new skill — AI tool selection for a specific user group
Six roles: Audience Profiler, Constraint Mapper (hard eliminators before capability comparison), Intervention-Mode Selector (Deepen / Extend / Introduce), Capability-Delta Assessor, First-Win & Day-2 Realist, Synthesis. Verdict: Adopt-now / Adopt-with-scaffolding / Pilot-with-subgroup / Skip. Ships with the Mongolian-teachers reference case (NotebookLM over advanced prompting, agent skills, Manus). Wired into both manifests, README decision tree + executive flow, INSTALL trigger table, usage-guide table, references/_index.md consumer columns, and tests/golden-prompts.md. Skill count 15 -> 16. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
1 parent 3ab9b86 commit 02dc056

12 files changed

Lines changed: 215 additions & 15 deletions

File tree

.claude-plugin/marketplace.json

Lines changed: 3 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -5,7 +5,7 @@
55
"email": "ray@rayhan.ai"
66
},
77
"metadata": {
8-
"description": "Fifteen installable skills for diagnosing, designing, governing, and scaling enterprise AI transformation — distilled from 21 flagship research sources (Stanford, MIT, McKinsey, BCG, Deloitte, PwC, Accenture, NIST, EU AI Act, IMDA, WEF).",
8+
"description": "Sixteen installable skills for diagnosing, designing, governing, and scaling enterprise AI transformation — distilled from 21 flagship research sources (Stanford, MIT, McKinsey, BCG, Deloitte, PwC, Accenture, NIST, EU AI Act, IMDA, WEF).",
99
"version": "0.4.0"
1010
},
1111
"plugins": [
@@ -29,7 +29,8 @@
2929
"./skills/tech-agent-guardrail",
3030
"./skills/people-readiness-conversation",
3131
"./skills/people-literacy-curriculum",
32-
"./skills/people-frontline-engagement"
32+
"./skills/people-frontline-engagement",
33+
"./skills/people-tool-selection"
3334
]
3435
}
3536
]

.claude-plugin/plugin.json

Lines changed: 3 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -2,7 +2,7 @@
22
"name": "enterprise-ai-transformation-skills",
33
"displayName": "Enterprise AI Transformation Skills",
44
"version": "0.4.0",
5-
"description": "Fifteen installable skills for diagnosing, designing, governing, and scaling enterprise AI transformation. Distilled from 21 flagship sources (Stanford, MIT, McKinsey, BCG, Deloitte, PwC, Accenture, NIST, EU AI Act, IMDA, WEF).",
5+
"description": "Sixteen installable skills for diagnosing, designing, governing, and scaling enterprise AI transformation. Distilled from 21 flagship sources (Stanford, MIT, McKinsey, BCG, Deloitte, PwC, Accenture, NIST, EU AI Act, IMDA, WEF).",
66
"author": "Ray Han",
77
"license": "MIT",
88
"homepage": "https://github.com/geledek/enterprise-ai-transformation-skills",
@@ -33,6 +33,7 @@
3333
"skills/tech-agent-guardrail",
3434
"skills/people-readiness-conversation",
3535
"skills/people-literacy-curriculum",
36-
"skills/people-frontline-engagement"
36+
"skills/people-frontline-engagement",
37+
"skills/people-tool-selection"
3738
]
3839
}

CHANGELOG.md

Lines changed: 5 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -2,6 +2,11 @@
22

33
All notable changes to this plugin are documented here.
44

5+
## [Unreleased]
6+
7+
### Added
8+
- **New skill: `people-tool-selection`** — six-role selector for choosing which AI tool to put in front of a specific user group (training cohort, team, department). Constraint-first method: hard eliminators (cost, ecosystem, setup friction, data, language, IT policy) filter candidates before capability comparison; then picks an intervention mode (Deepen / Extend / Introduce) and ranks survivors by new-artifact delta per unit of friction. Outputs Adopt-now / Adopt-with-scaffolding / Pilot-with-subgroup / Skip plus a first-win exercise and growth path. Ships with the Mongolian-teachers reference case (NotebookLM chosen over advanced prompting, agent skills, and Manus). Skill count is now 16.
9+
510
## [0.4.0] — 2026-07-02
611

712
### Added

CLAUDE.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
# CLAUDE.md
22

3-
This repo is a Claude Code plugin: 15 prompt-only skills for enterprise AI
3+
This repo is a Claude Code plugin: 16 prompt-only skills for enterprise AI
44
transformation. No build step, no runtime dependencies — everything is
55
markdown plus two JSON manifests.
66

INSTALL.md

Lines changed: 3 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -8,7 +8,7 @@
88
claude plugin install https://github.com/geledek/enterprise-ai-transformation-skills
99
```
1010

11-
Restart Claude Code. All 15 skills activate automatically.
11+
Restart Claude Code. All 16 skills activate automatically.
1212

1313
### Option B — Manual Clone
1414

@@ -53,6 +53,7 @@ After restart, test each skill with its trigger phrase. Skills are grouped by bu
5353
| `people-readiness-conversation` | "Surface AI readiness gaps in our leadership team" |
5454
| `people-literacy-curriculum` | "Build a role-based AI literacy curriculum" |
5555
| `people-frontline-engagement` | "How do we engage skeptical frontline experts?" |
56+
| `people-tool-selection` | "Which AI tool should I teach this group?" |
5657

5758
---
5859

@@ -62,7 +63,7 @@ After restart, test each skill with its trigger phrase. Skills are grouped by bu
6263
2. Click **Add plugin** (`+`) → **Create Plugin****Add Marketplace****Add from a repository**
6364
3. Paste this URL when prompted:
6465
`https://github.com/geledek/enterprise-ai-transformation-skills`
65-
4. Restart Claude Desktop. All 15 skills activate automatically from their trigger phrases.
66+
4. Restart Claude Desktop. All 16 skills activate automatically from their trigger phrases.
6667

6768
Requires a paid plan (Pro, Max, Team, or Enterprise). See [Claude plugin docs](https://support.claude.com/en/articles/13837440-use-plugins-in-claude).
6869

README.md

Lines changed: 4 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
# Enterprise AI Transformation Skills
22

3-
Fifteen installable skills that help executives, operators, and consultants run enterprise AI transformation — from "where do we start?" to "is our agent governed correctly?" — distilled from 21 flagship research sources (Stanford, MIT, McKinsey, BCG, Deloitte, PwC, Accenture, NIST, EU AI Act, IMDA, WEF) published 2024–2026.
3+
Sixteen installable skills that help executives, operators, and consultants run enterprise AI transformation — from "where do we start?" to "is our agent governed correctly?" — distilled from 21 flagship research sources (Stanford, MIT, McKinsey, BCG, Deloitte, PwC, Accenture, NIST, EU AI Act, IMDA, WEF) published 2024–2026.
44

55
> **TL;DR.** 95% of enterprise GenAI pilots return zero P&L impact. The 5% that win don't have better models — they operate differently across **people, process, technology**, and a layer of **general** strategy/diagnostics. This skill library encodes those operating patterns. Each skill is a structured prompt the AI runs for you; you ask the question, the skill produces a board-ready output.
66
@@ -42,6 +42,7 @@ Skills are grouped by what they fix. Pick the bucket that matches your problem;
4242
| "Why isn't our AI investment moving the needle? (people gaps)" | `people-readiness-conversation` | people |
4343
| "We need an AI literacy / EU AI Act Art. 4 training program." | `people-literacy-curriculum` | people |
4444
| "Frontline experts (clinicians, lawyers, agents) are blocking the pilot." | `people-frontline-engagement` | people |
45+
| "Which AI tool should I teach / roll out to this specific group?" | `people-tool-selection` | people |
4546

4647
If your question hits multiple rows, run the **higher one first** — it sets context for the rest.
4748

@@ -55,7 +56,7 @@ If your question hits multiple rows, run the **higher one first** — it sets co
5556
```
5657
https://github.com/geledek/enterprise-ai-transformation-skills
5758
```
58-
Restart. All 15 skills activate from their trigger phrases.
59+
Restart. All 16 skills activate from their trigger phrases.
5960

6061
**Claude Code**`claude plugin install https://github.com/geledek/enterprise-ai-transformation-skills`
6162

@@ -105,6 +106,7 @@ For a leader running an end-to-end AI transformation, this is the canonical sequ
105106
├─ people-readiness-conversation ── (run quarterly — surfaces gaps the tech can't fix)
106107
├─ people-literacy-curriculum ───── (close the literacy gap, satisfy EU AI Act Art. 4)
107108
├─ people-frontline-engagement ──── (when fearful experts are blocking rollout)
109+
├─ people-tool-selection ────────── (choosing which AI tool to put in front of a group)
108110
109111
├─ general-peer-cases ──────────── (pull at any decision point: "what have others done?")
110112
└─ tech-stack-diagnostic ───────── (run before any major scaling decision)

docs/usage-guide.md

Lines changed: 3 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
# Usage Guide — Enterprise AI Transformation Skills
22

3-
A comprehensive, worked-example reference for the 15 skills in this repo. Every section is the actual transcript an agent produces when the skill is invoked against a real situation — not summaries, not abstractions.
3+
A comprehensive, worked-example reference for the skills in this repo. Every section is the actual transcript an agent produces when the skill is invoked against a real situation — not summaries, not abstractions.
44

55
This guide answers four questions:
66

@@ -25,7 +25,7 @@ References are bundled per-skill (in `references/`) and resolved by filename, no
2525

2626
---
2727

28-
## 2. The 15 skills at a glance
28+
## 2. The skills at a glance
2929

3030
| # | Skill | When to use it | Closes which gap |
3131
|---|---|---|---|
@@ -44,6 +44,7 @@ References are bundled per-skill (in `references/`) and resolved by filename, no
4444
| 13 | `people-literacy-curriculum` | Stand up role-based literacy + EU AI Act Art. 4 evidence | People |
4545
| 14 | `people-frontline-engagement` | Engage skeptical frontline experts as co-designers, protect tradecraft | People |
4646
| 15 | `general-peer-cases` | "What have others actually done?" — pull closest-match analogs | Reference |
47+
| 16 | `people-tool-selection` | Choose which AI tool to put in front of a specific user group | Tool choice |
4748

4849
For a typical executive flow, see the README. For chained-flow examples, see Section 4 below.
4950

references/_index.md

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -16,21 +16,21 @@ Skills reference files by name only — no relative paths. Example pointer in a
1616

1717
| File | Contents | Primary for skill | Also consulted by |
1818
|---|---|---|---|
19-
| `70-20-10-value-split.md` | BCG 70/20/10 People/Process/Tech value split || people-literacy-curriculum, people-readiness-conversation, process-portfolio-observability |
19+
| `70-20-10-value-split.md` | BCG 70/20/10 People/Process/Tech value split || people-literacy-curriculum, people-readiness-conversation, people-tool-selection, process-portfolio-observability |
2020
| `95-5-genai-divide.md` | MIT NANDA 95% zero P&L + Scope × Execution Grid | process-pilot-design | general-idea-diagnostic, general-peer-cases, tech-buy-vs-build |
2121
| `nanda-tech-buy-vs-build.md` | 2:1 buy advantage; orchestration-as-moat | tech-buy-vs-build | general-peer-cases, tech-stack-diagnostic |
2222
| `pwc-roi-2026-governance.md` | 1.7× RAI advantage; 1.6× vs. 2.6× productivity gap || general-maturity-assessment, general-roi-gate, process-portfolio-observability, tech-agent-guardrail |
2323
| `pwc-20-item-checklist.md` | PwC 10 Do's + 10 Don'ts (full checklist) | general-roi-gate | process-portfolio-observability, process-productionization, tech-data-deployment |
2424
| `andrew-ng-three-moats.md` | Three AI moat types (portfolio/industry/virtuous cycle) || general-idea-diagnostic, general-use-case-discovery, tech-buy-vs-build |
2525
| `wef-strategic-positions.md` | WEF/BCG positional choice; strategic dilution risk || — (not currently cited by any skill) |
2626
| `pwc-six-step-roadmap.md` | PwC six-step AI ROI pathway || — (not currently cited by any skill) |
27-
| `stanford-51-deployments.md` | 51 deployments; invisible costs (77%); workflow-redesign-first || general-idea-diagnostic, general-peer-cases, general-roi-gate, general-use-case-discovery, people-frontline-engagement, process-pilot-design, process-productionization |
28-
| `bcg-manager-modeling.md` | 88/25 manager role-modeling gap || people-frontline-engagement, people-literacy-curriculum, people-readiness-conversation |
27+
| `stanford-51-deployments.md` | 51 deployments; invisible costs (77%); workflow-redesign-first || general-idea-diagnostic, general-peer-cases, general-roi-gate, general-use-case-discovery, people-frontline-engagement, people-tool-selection, process-pilot-design, process-productionization |
28+
| `bcg-manager-modeling.md` | 88/25 manager role-modeling gap || people-frontline-engagement, people-literacy-curriculum, people-readiness-conversation, people-tool-selection |
2929
| `deloitte-cheerleader-to-champion.md` | CEO champion vs. cheerleader; HR's 5 jobs; 74/21 governance gap || general-maturity-assessment, people-frontline-engagement, people-literacy-curriculum, people-readiness-conversation |
3030
| `mckinsey-3x-senior-ownership.md` | 3× CEO ownership differential; AI high-performer archetype || people-readiness-conversation |
3131
| `mckinsey-3-objective-mix.md` | Efficiency / Growth / Innovation objective mix; 80% efficiency-only || general-idea-diagnostic, general-maturity-assessment, general-peer-cases, general-roi-gate, general-use-case-discovery, people-readiness-conversation |
3232
| `imda-4-dimensions-agentic.md` | IMDA four dimensions of agentic AI governance | tech-agent-guardrail | people-frontline-engagement, people-literacy-curriculum, process-portfolio-observability, process-productionization, tech-data-deployment |
33-
| `eu-ai-act-essentials.md` | Art. 4 literacy obligation; risk tiers; deployer obligations || people-literacy-curriculum, people-readiness-conversation, tech-agent-guardrail, tech-data-deployment |
33+
| `eu-ai-act-essentials.md` | Art. 4 literacy obligation; risk tiers; deployer obligations || people-literacy-curriculum, people-readiness-conversation, people-tool-selection, tech-agent-guardrail, tech-data-deployment |
3434
| `nist-rmf-functions.md` | NIST AI RMF: GOVERN / MAP / MEASURE / MANAGE || people-literacy-curriculum, process-portfolio-observability, process-productionization, tech-agent-guardrail, tech-data-deployment, tech-stack-diagnostic |
3535
| `accenture-maturity-archetypes.md` | Accenture AI Achievers/Innovators/Builders/Experimenters | general-maturity-assessment | people-readiness-conversation |
3636
| `mit-cisr-4-stages.md` | MIT CISR four maturity stages; Stage 3 inflection; DBS/Ping An examples | general-maturity-assessment | general-peer-cases, process-portfolio-observability, process-productionization, tech-stack-diagnostic |
Lines changed: 30 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,30 @@
1+
# People — AI Tool Selection
2+
3+
A six-role selector for choosing which AI tool to put in front of a specific user group — or whether to introduce a new tool at all.
4+
5+
## What it does
6+
7+
Decides between three intervention modes and, within them, ranks candidate tools:
8+
- **Role 1 (Audience Profiler):** baseline fluency, weekly artifact inventory, language/device/subscription reality, time budget
9+
- **Role 2 (Constraint Mapper):** hard eliminators — cost, ecosystem, setup friction, data sensitivity, language support, IT policy. Constraints eliminate *before* capability ranks.
10+
- **Role 3 (Intervention-Mode Selector):** Deepen (better use of current tools) / Extend (agent skills, templates) / Introduce (a new tool)
11+
- **Role 4 (Capability-Delta Assessor):** new artifact classes vs. improved-same, ranked by delta-per-unit-of-friction
12+
- **Role 5 (First-Win & Day-2 Realist):** the in-session win, who role-models next week, blast radius review
13+
- **Synthesis:** Adopt-now / Adopt-with-scaffolding / Pilot-with-subgroup / Skip, plus a growth path
14+
15+
## When to use it
16+
17+
Planning a training, a team rollout, or a "which tool should we standardize on for this group?" decision. The unit of analysis is a human group's adoption, not architecture.
18+
19+
Boundaries: for build/buy/partner sourcing of a *capability*, use `tech-buy-vs-build`. For an org-wide literacy *curriculum*, use `people-literacy-curriculum` (this skill picks the tool; that one designs the program). If sensitive data is central, `tech-data-deployment` gates first.
20+
21+
## What it outputs
22+
23+
- Verdict: Adopt-now / Adopt-with-scaffolding / Pilot-with-subgroup / Skip
24+
- Primary tool + mode (Deepen / Extend / Introduce)
25+
- A concrete first-win exercise and a growth path
26+
- Weakest link and closest reference case
27+
28+
## Cases
29+
30+
See `cases/` — starting with the Mongolian-teachers decision (NotebookLM chosen over advanced prompting, agent skills, and Manus).

0 commit comments

Comments
 (0)