Install
$ agentstack add skill-hiteshbandhu-skills-i-use-ship-ai-as-pm ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
Ship AI as PM
Action playbook from nine AI Engineer / World's Fair talks. Do not summarize talks — pick a workflow and execute it.
Supporting files (read when needed):
- [workflows.md](workflows.md) — workflows A–I (steps, deliverables, stop conditions)
- [source-index.md](source-index.md) — src-NNN → talk learnings in ingest-into-skills
Optional: {SKILL_OUTPUT_DIR}/ship-ai-as-pm/
Step 0 — Pick workflow
Use the decision tree below. Open the matching section in [workflows.md](workflows.md).
What is the user trying to do?
├─ Define AI PM role / ownership → A
├─ Competitive strategy (knife fight, moats) → B
├─ Ship to real users fast → C
├─ Roadmap under capability uncertainty → D
├─ Expert-in-the-loop vertical product → E
├─ Domain expert + eval ownership → F
├─ Agent coordination in work tools → G
├─ Post-engineer engineering org → H
└─ Taste-led UX (anti-slop) → I
Stop summarizing once a workflow is identified — run its checklist.
Install
cp -r skills/ship-ai-as-pm ~/.claude/skills/
cp -r skills/ship-ai-as-pm ~/.cursor/skills/
cp -r skills/ship-ai-as-pm ~/.codex/skills/
From skills-i-use or ingest-into-skills (playlists/product-management-ai-engineer-world-s-fair/).
Cross-cutting rules
| Rule | Source | |------|--------| | Ship to someone weekly beats platform build | [src-005 @ 0:19] | | Evals as discovery under uncertainty | [src-004 @ 9:03] | | Experts own rubrics in verticals | [src-006 @ 7:26] |
Disputed steps: see [source-index.md](source-index.md). Name workflow A–I; save artifacts to ./skill-outputs/ship-ai-as-pm/ when requested; do not auto-commit.
Invocation examples
@ship-ai-as-pm AI product strategy for crowded market
roadmap when we dont know model limits
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: hiteshbandhu
- Source: hiteshbandhu/skills-i-use
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.