methodology
How we build Skilskis.
The methodology behind the Top-Verified ✓✓ stamp. Six steps, no invented citations, operator sign-off required before anything reaches the catalog.
207Top-Verified ✓✓ flagships
284sectors covered
0federated tools available
01 — the process
Six steps from idea to ✓✓ stamp.
Every step has a gate. No step is skipped. Skills that fail any gate do not receive the ✓✓ stamp.
6 steps · 0 shortcuts
Domain selection
Where AI saves the most billable hours per week.
Operator-led selection: we look at where AI saves the most billable hours per week. Industries with clear, repeatable workflows and measurable time cost are prioritized. We track practitioner forums, job cost data, and regulatory burden density before choosing a domain.
artifacts produced
practitioner forum scrapeBLS occupational time costregulatory burden index
Real-world research
Federal regs, peer-reviewed studies, authoritative bodies — no invented citations.
Federal regulations, peer-reviewed studies, industry standards bodies, and authoritative government sources. No invented citations. No hallucinated authority. If a claim requires a source and no credible source exists, the claim is cut. Every power quote in a Skilski is traceable to a real document.
artifacts produced
CFR / USC citationspeer-reviewed studiesagency guidance documentsstandards body publications
First-draft authoring
SKILL.md format with structured frontmatter and inline citations.
Skills are written in our SKILL.md format: structured frontmatter, body content covering the workflow, inline citations, and a buyer-facing power quote grounded in the cited material. The format enforces scope discipline — one skill, one job.
artifacts produced
YAML frontmatterworkflow bodyinline citation listbuyer-facing power quote
Multi-phase quality review
Schema, security, sandbox, field — four automated phases before operator review.
Four automated phases before operator review: schema validation and markdown integrity, static security grep (injection patterns, unsafe dependencies, misuse vectors), isolated sandbox execution against normal and adversarial inputs, and field-readiness testing covering idempotency, humanized errors, latency, and resource bounds.
artifacts produced
schema + markdown lintsecurity grep suitesandbox execution logfield-readiness benchmark
Operator sign-off
Founder reviews every Skilski for scope drift and citation gaps.
The founder reviews every Skilski before the ✓✓ stamp is granted. This is not a rubber stamp — it is a final read for scope drift, overclaiming, missing human-review markers, and research-citation gaps. Skills that surface problems here go back to step 2 or 3.
artifacts produced
scope-drift checkoverclaiming reviewhuman-pass marker auditcitation completeness pass
Daily-drop publication
Pushed to Git, deployed to Vercel, indexed in MCP — logged with timestamp.
Passed skills are pushed to Git, deployed to Vercel, indexed in the MCP registry, and surfaced in /changelog. The release is logged with a timestamp and verification record. The catalog is live. The moat compounds daily.
artifacts produced
git commit + tagVercel deploymentMCP registry indexchangelog row
02 — rejection criteria
What gets rejected.
The ✓✓ stamp is not granted by default. Skills fail the gate for specific, documented reasons. The most common disqualifiers are listed here. Failed skills are not listed in the catalog.
0 marketing exceptions
✕
Invented citations or hallucinated authority
If a claim cannot be traced to a real document — a CFR section, a peer-reviewed paper, an agency guidance memo, a vendor specification — it does not ship. Power quotes without a source are cut, not embellished.
✕
Auto-execute outputs in regulated domains
Skills that would produce final filings or autonomous decisions in legal, medical, or financial domains are tagged human_pass_required. They are designed for informed-and-reviewed use only.
✕
Duplicate scope without meaningful differentiation
A skill that overlaps an existing Top-Verified flagship without adding meaningfully different scope or depth is rejected. We pick depth over breadth every time.
03 — honest scope
What we do not claim.
Honest scope is part of the methodology. We build things we can actually deliver. We do not market ourselves into roles we do not fill or obligations we cannot fulfill.
01We are not your lawyer, doctor, or CPA.
Skills in legal, medical, and financial domains are drafting aids. A qualified human reviews before the output acts on the world.
02We are not a SaaS app.
Skilskis are a registry your AI agent loads from — discrete, composable capabilities delivered over MCP. No portals, no dashboards, no workflow builder lock-in.
03We do not train models on your invocations.
Your prompts and agent outputs are not used for model training. We do not license or sell invocation data to third parties.
04 — source authorities
Where Skilski citations come from.
Every Top-Verified Skilski cites real authorities. These are the source classes we draw from. Each citation is link-traceable.
Federal regulationprimary
CFR · USC · Federal Register
Agency guidanceprimary
EEOC · DOL · IRS · DOJ · CMS
Peer-reviewed studiesprimary
PubMed · IEEE · arXiv · SSRN
Standards bodiesprimary
NIST · ISO · ASTM · ANSI
Court precedent
SCOTUS · circuit · state appellate
Vendor specifications
manufacturer manuals · API specs