An eval of the Quarkdown agent skill | Quarkdown
May 24, 2026 • 3 min read<br>An eval of the Quarkdown agent skill<br>The agent skill shipped in Quarkdown 2.1, aiming at making it easier for agents to write correct and idiomatic Quarkdown<br>for a frictionless authoring experience.
If you already have the CLI installed, wiring it up to Claude Code is one line:
ln -s "$(quarkdown doctor get agent-skill)" ~/.claude/skills/quarkdown<br>The skill
The skill is a SKILL.md file bundled with the Quarkdown distribution. When the agent loads it, it picks up on a few key points:
Quarkdown ships with an offline copy of its own wiki and API reference, which the agent is pointed to for on-demand lookups.
Given a problem, the agent scans the wiki’s table of contents to orient, then pulls the wiki pages for what’s relevant.
Types and enum values are looked up from the API reference, to cut down on compilation errors from hallucinated values.
The eval
Five tasks, each handed to two clean agents on Opus 4.7. Both arms got the spec, the path to the quarkdown CLI, and permission to compile, read the error, and retry up to three times.
Legend:
✅ correct and idiomatic on the first try
⚠️ works but non-idiomatic, or needed a retry
❌ wrong or missed
Article
A web article with metadata, titles, a table and a blockquote.
withwithoutDoctype choice✅⚠️Document metadata✅⚠️Plain Markdown syntax✅✅<br>With-skill output:
.docname {Tonk Coffee Grinder Review}<br>.doctype {plain}<br>.doclang {English}<br>.theme {paperwhite} layout:{latex}<br>.docauthor {Giorgio}
# Tonk Coffee Grinder: A Hands-On Review
## Overview
The Tonk is a mid-range burr grinder aimed at home baristas who want espresso-grade<br>consistency without the price tag of commercial machines. It features 40 mm conical<br>steel burrs, a stepless adjustment ring, and a single-dose hopper that holds up<br>to 30 g of beans. After two weeks of daily use, here is what stood out.
## Build Quality
The chassis is solid cast aluminum with a brushed finish, and the grinder weighs in<br>at 3.4 kg, heavy enough to stay put during use. The adjustment ring turns smoothly<br>with detents that are easy to feel but never sloppy. Internal wiring is tidy, and<br>the motor runs cooler than competitors at the same price point.
| Pros | Cons |<br>|-------------------------------|----------------------------------|<br>| Excellent grind consistency | Loud at higher speeds |<br>| Stepless adjustment | Single-dose hopper feels small |<br>| Solid all-metal construction | No timed dosing |<br>| Low retention (<br>| Easy to disassemble for cleaning | Limited warranty (1 year) |
## Verdict
> Note: The Tonk replaced my old grinder on day one, and I have not looked back. It<br>> pulls espresso shots that taste cleaner and brighter than anything I have made<br>> at home before. -- Marco R., home barista
For the price, the Tonk delivers performance that punches well above its class.<br>The minor quibbles around noise and the small hopper are easy to forgive once<br>you taste the results in the cup.
**Rating: 4.5 / 5 stars**<br>Title page
A title page with a two-column body, a title spanning both columns, and callout boxes.
withwithoutTitle spanning columns✅❌Two-column layout✅⚠️Callout boxes✅⚠️Authors metadata✅⚠️<br>With-skill output:
.docname {Resilient Caching at the Edge}<br>.doctype {paged}<br>.doclang {English}<br>.theme {paperwhite} layout:{latex}
.docauthors<br>- Ada Lovelace<br>- affiliation: Edge Systems Lab, Analytical Institute<br>- Grace Hopper<br>- affiliation: Distributed Computing Group, Naval Research
.pageformat columns:{2} margin:{1.8cm}
.fullspan<br>.center<br>.text {Resilient Caching at the Edge} size:{huge} weight:{bold}
.center<br>.text {Ada Lovelace} weight:{bold} .text {(Edge Systems Lab, Analytical Institute)} size:{small} .text { | } .text {Grace Hopper} weight:{bold} .text {(Distributed Computing Group, Naval Research)} size:{small}
.box {Problem} type:{error}<br>Edge caches face frequent node failures, partial network partitions, and bursty<br>request patterns. Traditional LRU and TTL-based policies degrade rapidly under<br>these conditions, producing cold-cache stampedes that overwhelm origin servers<br>and inflate tail latency by an order of magnitude during failover.
.box {Approach} type:{note}<br>We introduce **GossipCache**, a decentralized replication protocol that combines<br>consistent hashing with reactive prefetching driven by peer-to-peer gossip.<br>Each edge node maintains a probabilistic digest of its neighbors' working sets<br>and proactively replicates entries whose loss would breach a configurable<br>availability budget.
Key ingredients:
1. Adaptive replication factor tied to live failure rate<br>2. Bloom-filter digests exchanged every 200 ms<br>3. Origin-side admission control to absorb residual misses
.box {Result} type:{tip}<br>Across a 30-node testbed driven by a production CDN trace, GossipCache reduced<br>p99 latency by **62%** during simulated rack failures and cut origin egress by<br>**41%** compared to a tuned LRU baseline, while adding under 3% steady-state<br>network...