Add setup-my-iq skill 🤖🤖🤖

[LakshmiStoltz]

What this adds

A new skill, setup-my-iq, that creates and maintains a personal context portfolio: a set of structured markdown files (identity, role and responsibilities, team, tools/config, communication style, preferences and constraints) that any agent, skill, or plugin can read to immediately understand who it is working with.

Why

People re-introduce themselves to AI tools every session and across every harness. This skill runs a guided interview once, writes the files anywhere the user chooses, and wires them into the user's custom instructions (AGENTS.md / copilot-instructions.md / CLAUDE.md) so every agent can find them. It also supports targeted updates and gap-filling for files that already exist.

Details

• skills/setup-my-iq/SKILL.md plus bundled templates under assets/templates/.
• Pre-fills factual fields from authorized data sources before asking the user.
• Cross-platform guidance (Windows and POSIX).
• Safety rules: never stores secrets, never deletes files, treats context as data.

Validation

• npm run skill:validate passes (skill is valid).
• npm run build regenerated docs/README.skills.md.

🤖 This PR was prepared with AI assistance.

[github-actions]

🔍 Skill Validator Results

⚠️ Warnings or advisories found

Scope	Checked
Skills	1
Agents	0
Total	1

Severity	Count
❌ Errors	0
⚠️ Warnings	1
ℹ️ Advisories	0

Summary

Level	Finding
ℹ️	Found 1 skill(s)
ℹ️	[setup-my-iq] 📊 setup-my-iq: 7,844 BPE tokens [chars/4: 8,521] (comprehensive ✗), 37 sections, 5 code blocks
ℹ️	[setup-my-iq] ⚠ Skill is 7,844 BPE tokens (chars/4 estimate: 8,521) — "comprehensive" skills hurt performance by 2.9pp on average. Consider splitting into 2–3 focused skills.
ℹ️	✅ All checks passed (1 skill(s))

Full validator output

Found 1 skill(s)
[setup-my-iq] 📊 setup-my-iq: 7,844 BPE tokens [chars/4: 8,521] (comprehensive ✗), 37 sections, 5 code blocks
[setup-my-iq]    ⚠  Skill is 7,844 BPE tokens (chars/4 estimate: 8,521) — "comprehensive" skills hurt performance by 2.9pp on average. Consider splitting into 2–3 focused skills.
✅ All checks passed (1 skill(s))

[Copilot]

Pull request overview

Note

Copilot was unable to run its full agentic suite in this review.

Adds a new setup-my-iq skill and supporting templates to help users create and maintain a structured “personal context portfolio” (identity, role, team, tools/config, communication style, and constraints), and registers the skill in the skills index.

Changes:

• Introduces the setup-my-iq skill with a guided first-time setup + update workflow.
• Adds bundled markdown templates for the six context files plus a canonical AGENTS.md wiring template.
• Updates the skills documentation index to include the new skill.

Reviewed changes

Copilot reviewed 9 out of 9 changed files in this pull request and generated 4 comments.

Show a summary per file

File	Description
skills/setup-my-iq/SKILL.md	Defines the new skill’s behavior: discovery, interview flow, wiring into instructions, safety, and error handling.
skills/setup-my-iq/assets/templates/AGENTS.md	Provides the canonical “Personal Context” instruction block used to point agents to the context files.
skills/setup-my-iq/assets/templates/identity.md	Template for user identity context file.
skills/setup-my-iq/assets/templates/role-and-responsibilities.md	Template for responsibilities/cadences/deliverables context file.
skills/setup-my-iq/assets/templates/team.md	Template for team/partners roster context file.
skills/setup-my-iq/assets/templates/tools-systems-and-config.md	Template for tools, notes system, ADO config, reporting outputs, and pillars.
skills/setup-my-iq/assets/templates/communication-style.md	Template capturing writing voice, avoid-list, and audience adjustments.
skills/setup-my-iq/assets/templates/preferences-and-constraints.md	Template for working preferences, hard boundaries, and memory rules.
docs/README.skills.md	Registers the new skill in the documentation index.

[LakshmiStoltz]

this is a template table in a template file. I dont see any leading double pipes. there are comments left in the column to specify what goes there. I think no change is necessary.

[aaronpowell]

This reads really like it's two skills in one - an interviewer that will produce the identity and then a skill to instruct the agent to leverage the identity.

The resulting on this is that, particularly in the "use identity" stages of the workflow there will be a large number of wasted tokens added into each request.

Also, I do wonder how much value is gained with much of this information. How does the behaviour of the agent change if it knows the users role, their IDE choice, etc., or does that just become tokens in the request that are ignored?