PRODUCT · SKILLS

Your agent doesn't need every skill loaded.

Stuffing 40 skills into the system prompt taxes every token. Skills inverts this — agents discover the right one at runtime, fetch the folder, run it, rate it. The catalog gets sharper without you curating.

Get started — free
SKILL · query: summarize PDF · top-4
summarize-pdfsP04.6★
extract-tablesP14.3★
ocr-scanP24.1★
redact-piiP33.8★
✓ runtime fetch · 1 MCP call · review fed back
/skills

Skills

Stop curating skill libraries. Agents find the right one at runtime, fetch it, run it, and rate it.

  • Search
  • Fetch
  • Review
  • Public
  • Private
  • Dedupe
1MCP call to fetch a skill folder
4 dimsagent reviews drive ranking
30 sGitHub commit → searchable
0skills you curate by hand
What it does

The three things skills actually does.

STOP CURATING

Agents pick at runtime, not you in advance.

Your skill list is whatever your platform has indexed. The agent calls find_skill the moment it needs a capability. Hybrid search returns the top matches with review aggregates. The agent picks. You don't.

stop curating · ok
public catalog discovery
200 · 30 s
REVIEWS COMPOUND

Quality from real usage, not LLM judges.

After every run, the agent leaves a 4-dimension review. Accuracy, value, efficiency, clarity. The composite boosts what works on the next search. New skills get a fair shot — the boost is multiplicative, never punitive.

reviews compound · ok
private platform skills
200 · 30 s
ZERO PROMPT TAX

Skills aren't pre-loaded.

Stuffing 40 skill descriptions into a system prompt costs ~12k tokens per call and distracts the model. Skills (the product) ships one MCP tool — find_skill — and lets the agent pull only what it needs.

zero prompt tax · ok
end-user-owned skills
200 · 30 s

Stuffing 40 skills into the system prompt taxes every token, distracts the model, and rots into a museum nobody uses. Runtime discovery is the fix — but it needs a registry, content-hash dedup, agent reviews that compound, and a fetch path fast enough to call inline. We did all of it.

Why we built this

Urgent backstory

We watched five AI startups in a row hand-roll the same skills stack — and burn three weeks doing it. We packaged ours so you don't have to. Drop the SDK in once; this product, plus the rest of the suite, comes with it.

Use it for

Four common
ways teams ship with Skills.

01P

Public catalog discovery

Admin-vetted GitHub repos sync every 30 seconds. Plugin-bundle dedup collapses byte-identical copies. Your agents see one match per unique skill, not seven.

02P

Private platform skills

Upload via API. Owned by the platform key (sk-plat_), encrypted at rest in GCS. Visible only to your agents, never the public catalog.

03E

End-user-owned skills

Created with sk-eu_, owned by the end-user — not the key. Survives API rotation. Each end-user gets their own evolving capability set.

04C

Capability ranking

Best-rated skill wins on the next search. New skills get a fair shot via multiplicative boost — never punished for having no reviews yet. Failures stay visible, not invisible.

How it works

Four steps, ten minutes.

1

Find at runtime

find_skill({ query: "summarize PDF" })
2

Fetch the folder

fetch_skill(skill_id, target_path)
3

Agent runs the bundle

// runtime materializes + executes
4

Review feeds ranking

submit_skill_review({ accuracy, ... })
It works with

The stack you already have.

Anthropic
OpenAI
Cursor
Claude Code
S&P Global
LSEG
GitHub
MCP

We stopped maintaining a curated skills list. The agent finds what it needs, runs it, and our system-prompt size dropped 70%.

Adam · CTO, Quill
Q
Pricing

Free to ship. Pay when you scale.

FREE$0

Up to 1k requests/mo. Every product included.

Start free →
SCALE$0.0008

per request, after free tier. No markup on tokens. Cancel anytime.

What's next

Shipping this quarter.

Read full changelog →
WK 12Skill versioning + pinning
WK 13Cross-platform skill licensing
WK 14Per-call cost predictions
WK 15Auto-prune by review threshold
ONE AFTERNOON AWAY

Stop curating skills. Ship runtime discovery this afternoon.

We onboard 1–2 indie startups a week. If you'd rather ship features than maintain a skills stack, talk to us.

Get started — free