SkeletIQ
AI tool that designs, critiques, and hands system specs to coding agents.
At a glance
Price not confirmed · Source review 2026-11-02- Price & billing
No paid tier amount was verified on the official homepage or pricing page reviewed on 2026-11-02; plan card amounts did not render in the text fetch. The homepage and pricing page confirm a free plan with no card needed and monthly-refreshing credits. Recheck official pricing before purchase.
- Free allowance
The homepage and pricing page confirm a free plan with no card needed and monthly-refreshing credits.
- Best suited to
Engineers who want spec-driven development with AI coding agents
Fit is editorial guidance, not a measured result.- Platforms
Access: not separately verified. Operating systems not separately verified.
Published-source facts and editorial guidance. No product test is implied. Confirm current conditions before purchase.
No product screenshot is claimed for this listing. Use the official website ↗ to inspect the current interface.
What to know before choosing
Good fit
Engineers who want spec-driven development with AI coding agents
Limits and trade-offs
Still in beta; paid plan amounts did not render on the pricing page in this text review, so no paid price is asserted. On the Free plan, using your own key carries a small per-generation platform fee.
Plans and free allowances
No paid tier amount was verified on the official homepage or pricing page reviewed on 2026-11-02; plan card amounts did not render in the text fetch. The homepage and pricing page confirm a free plan with no card needed and monthly-refreshing credits. Recheck official pricing before purchase.
Evidence
Official homepage ↗ (reviewed 2026-11-02)
Official published page review; no authenticated product test
Dates: Last reviewed 2026-11-02. Last reviewed is the latest source or editorial review date; it is not a content-change date.
A closer look at SkeletIQ
SkeletIQ is the architecture layer for AI coding agents: describe a system and it designs it, critiques it, and hands the result to a coding agent over MCP as a spec it can be held to — a brief written into the repo's AGENTS.md, a build order, and a drift check against what was actually built. Designs are kept as a graph rather than a document, so checks can be recomputed and traced to components, and it works with Claude Code and any MCP host, with hosted models or your own key.
Editorial guidance based on published documentation. The workflow below is a suggested starting point, not a measured product result.
When to choose SkeletIQ
- Engineers who use Claude Code or other MCP-host coding agents
- Teams that want a defensible system design before building
- Developers who want build order and drift checks, not just diagrams
When to choose something else
- Users who only want a diagram image rather than a spec workflow
- Teams that do not use an MCP and AGENTS.md-based agent workflow, since SkeletIQ hands the spec to a coding agent over MCP as a brief in AGENTS.md
A practical starting workflow
- Describe the system in a prompt
- Review SkeletIQ's design and its critique
- Release the design so the agent pulls a brief into AGENTS.md
- Let the agent build in the given build order
- Run the drift check to see what is missing, half done or not in the design
Check before committing
- Vendor claims on the official page are not guarantees; actual results, quality and availability must be tested in the product.
- Prices and features may change after this review; recheck the official site before purchase or signup.
Common questions
What is SkeletIQ?
The architecture layer for AI coding agents: it designs a system from a prompt, critiques it, and hands a spec to the coding agent over MCP.
How does SkeletIQ hand work to Claude Code?
The agent pulls a brief into the repository's AGENTS.md, builds in SkeletIQ's order, and reports back what it built so drift can be checked.
Is SkeletIQ free?
It is in beta with a free plan and no card needed; credits refresh monthly and top-up packs are available on every plan, but paid plan amounts did not render in this text review.
Compare approaches for this task
Sources and checks
Last source review is not a date of product testing. No rating or test result is implied by inclusion. Check the current plan and terms before buying.