Skip to content
Back to skills

Embed

ASecurity

Challenge a rough idea and create a ready PM ticket

  • 67 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added September 23, 2026
ai-agentsgit

Security analysis

A100/100

Pro scans all 21 files and shows the line behind each finding

Scanned October 2, 2026

npx -y skills add gethuman-sh/human --skill embed --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Embed?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Embed
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/gethuman-sh-embed-0840e30c/badge)](https://www.skillsdirectory.com/skills/gethuman-sh-embed-0840e30c)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: human-ideate
description: Challenge a rough idea and create a ready PM ticket
argument-hint: <idea or topic>
---

Follow these steps in order:

1. **Parse** `$ARGUMENTS`:
   - Set `<topic>` to a slugified version (lowercase, spaces to hyphens, strip special chars).
   - If `$ARGUMENTS` is an existing ticket key whose ticket carries the `human/idea` label (bare `idea` also classifies), this run **evolves** that idea ticket in place instead of creating a new one: fetch it, note the key as `<IDEA_KEY>`, and use its title/description as the rough idea. Quick-captured ideas (e.g. from the board's Ideas column) are exactly such tickets. Otherwise the run creates a ticket from scratch as below.

2. **Create** the output directory: `mkdir -p .human/ideations`

3. **Phase 1 -- Context & challenge**: Delegate to the **human-ideator** agent:

   ```
   Task(subagent_type="human-ideator", model="opus", prompt="Phase 1: Gather context and generate challenge questions for: $ARGUMENTS. Read the codebase, recent git history, and existing tickets for context. Return a context summary and 5 forcing questions.")
   ```

4. **Present** the agent's context summary to the user.

5. **Ask forcing questions** one at a time using `AskUserQuestion`. Ask each of the agent's 5 forcing questions individually. Collect all answers.

6. **Phase 2 -- Scope decision**: Delegate to the **human-ideator** agent with the collected answers:

   ```
   Task(subagent_type="human-ideator", model="opus", prompt="Phase 2: Based on the challenge answers, propose scope. Answers: <paste all Q&A pairs>. Original idea: $ARGUMENTS. Return a problem statement, user story, acceptance criteria, and a scope recommendation (Expand / Hold / Reduce) with rationale.")
   ```

7. **Present** the scope recommendation to the user.

8. **Ask** the user to confirm or adjust the scope using `AskUserQuestion`: "The recommendation is to [Expand/Hold/Reduce] scope. Do you agree, or would you prefer a different scope direction?"

9. **Resolve PM tracker**: Run `human tracker topology` and use its `pm` entry: the entry's `type` as the tracker and its first configured project.

10. **Phase 3 -- Create ticket**: Delegate to the **human-ideator** agent with the scope decision, tracker, and project:

    ```
    Task(subagent_type="human-ideator", model="sonnet", prompt="Phase 3: Create the PM ticket. Tracker: <tracker>. Project: <project>. Scope decision: <user's scope choice>. Problem statement, user story, and acceptance criteria from Phase 2: <paste Phase 2 output>. Create the ticket and add the challenge record as a comment.")
    ```

    When evolving an idea ticket, instruct the agent instead: "Phase 3: Evolve idea ticket <IDEA_KEY> in place — rewrite its title and description, remove the idea label, and add the challenge record as a comment." The key stays the same; no new ticket is created.

11. **Present** the created (or evolved) ticket key to the user.

12. **Write** the complete ideation record to `.human/ideations/<topic>.md`.

13. **Tell** the user: `Ideation written to .human/ideations/<topic>.md -- ticket created (or evolved) as <KEY>.`

Files in this skill

  • brainstorm-codebase-agent.md3.3 KB
  • brainstorm-opportunities-agent.md3.7 KB
  • brainstorm-recon-agent.md3.3 KB
  • brainstorm-trajectory-agent.md3.4 KB
  • brainstorm-triage-agent.md4.5 KB
  • codenav-skill.md2.6 KB
  • features-recon-agent.md4.8 KB
  • features-synthesis-agent.md10.2 KB
  • findbugs-api-agent.md5.8 KB
  • findbugs-concurrency-agent.md5.6 KB
  • findbugs-errors-agent.md5 KB
  • findbugs-logic-agent.md4.8 KB
  • findbugs-recon-agent.md4.6 KB
  • findbugs-triage-agent.md4.7 KB
  • gardening-complexity-agent.md5.8 KB
  • gardening-duplication-agent.md5.2 KB
  • gardening-hygiene-agent.md6.6 KB
  • gardening-structure-agent.md5.3 KB
  • gardening-survey-agent.md7.1 KB
  • gardening-triage-agent.md8.6 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.