quicksilver
Offload bulk judgment calls to Jev (TypeSafe's fast System One model) so Claude doesn't read, and pay for, content it only needs a verdict on.
Skill by qveys
Chalk Labs
Need help deploying quicksilver?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/qveys-quicksilver
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents, testing, writing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Nov 1, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Node.js package
Network hosts it talks to 3
api.typesafe.ai· found in codecodeload.github.com· found in install commandconsole.typesafe.ai· found in code
Files it touches
~/.claude/skills/quicksilver- Your home directory (~)
What's inside
- Skill name
quicksilver- Description
- Offload bulk judgment calls to Jev (TypeSafe's fast System One model) so Claude doesn't read, and pay for, content it only needs a verdict on. Use this BEFORE reading many files, long logs, or big lists just to decide which parts matter. That covers finding which files relate to a feature or bug, filtering log lines for errors, triaging or labelling many items (tickets, test failures, commits, TODOs, search hits), ranking candidates by relevance, locating the right lines in a huge file, or a yes/no check on a large document. Also use when the user says quicksilver, jev, "save tokens", "delegate", or "cheaper/faster". Skip it for generation, editing, multi-step reasoning, math, counting, or date comparison, and when the input is small enough to just read.
- License
- unknown
- Instructions
- 160 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (2)
- SKILL.md
- qs.mjs · scripts/
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from qveys/agent-skills
- 0.565score
preflight-autonome
qveys
Preflight avant de laisser un agent travailler en autonomie sur n'importe quel projet : lister les items d'une TODO, déterminer l'accès requis par item (dépôt…
SkillAFreshness: AClaude Code +9 - 0.565score
chantier-relais
qveys
Utiliser dès que l'utilisateur veut découper un plan ou un gros projet en étapes exécutables par petites sessions Claude autonomes, mentionne « chantier », «…
SkillAFreshness: AClaude Code +9 - 0.565score
wsh-cockpit
qveys
Run commands for the user in a VISIBLE Wave Terminal block — local or on a Wave-connected host — so they can watch and take the keyboard.
SkillAFreshness: AClaude Code +9 - 0.565score
ou-en-suis-je
qveys
Utilise ce skill quand Quentin veut faire le point sur son travail récent, toutes sessions/projets confondus : terminé, ouvert, interrompu, bloqué ou en…
SkillAFreshness: AClaude Code +9 - 0.559score
vps-dokploy
qveys
Operate the vps-dokploy production server — Dokploy itself (compose apps, file mounts, deploy webhooks, its Postgres state) and the Housekeeper stack it hosts…
SkillAFreshness: AClaude Code +9 - 0.556score
tailscale-vps
qveys
Accéder aux VPS (vps-openclaw, vps-dokploy) depuis un agent — toujours `tailscale ssh <hôte>`, jamais `ssh` direct ; méthode cockpit wsh.
SkillAFreshness: AClaude Code +9 - 0.551score
paperclip-vps
qveys
Debug/administer the Paperclip AI-company server on vps-openclaw — paths, CLI board auth, agent/adapter config, logs, DB, patch infra.
SkillAFreshness: AClaude Code +9 - 0.546score
orchestration-regles-locales
qveys
Règles locales de Quentin pour l'orchestration Orca, à charger AVEC le skill `orchestration` et avant tout `worker-start` / dispatch / run-create…
SkillAFreshness: AClaude Code +9 - 0.541score
template-skill
qveys
A template skill to demonstrate the structure.
SkillAFreshness: AClaude Code +9 - 0.529score
ai-ready
qveys
**ANALYSIS SKILL** — Analyze any repository and generate AI-ready configuration — AGENTS.md, copilot-instructions.md, skills, CI workflows, issue templates.
SkillBFreshness: BClaude Code +9 - 0.524score
conflict-resolve
qveys
Use when Housekeeper or a user asks to resolve Git merge/rebase conflicts on a pull request via rebase + force-with-lease, after GitHub reports mergeable=false.
SkillBFreshness: BClaude Code +9 - 0.519score
omniroute-ops
qveys
Operate OmniRoute (Task Router, combos, IP whitelist, cache/cost, real vs virtual models) from what is actually installed, preferring the admin UI over source…
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 25, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/qveys/agent-skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from qveys
- 0.565score
chantier-relais
qveys
Utiliser dès que l'utilisateur veut découper un plan ou un gros projet en étapes exécutables par petites sessions Claude autonomes, mentionne « chantier », «…
SkillAFreshness: AClaude Code +9 - 0.565score
ou-en-suis-je
qveys
Utilise ce skill quand Quentin veut faire le point sur son travail récent, toutes sessions/projets confondus : terminé, ouvert, interrompu, bloqué ou en…
SkillAFreshness: AClaude Code +9 - 0.565score
preflight-autonome
qveys
Preflight avant de laisser un agent travailler en autonomie sur n'importe quel projet : lister les items d'une TODO, déterminer l'accès requis par item (dépôt…
SkillAFreshness: AClaude Code +9 - 0.565score
wsh-cockpit
qveys
Run commands for the user in a VISIBLE Wave Terminal block — local or on a Wave-connected host — so they can watch and take the keyboard.
SkillAFreshness: AClaude Code +9 - 0.559score
vps-dokploy
qveys
Operate the vps-dokploy production server — Dokploy itself (compose apps, file mounts, deploy webhooks, its Postgres state) and the Housekeeper stack it hosts…
SkillAFreshness: AClaude Code +9 - 0.556score
tailscale-vps
qveys
Accéder aux VPS (vps-openclaw, vps-dokploy) depuis un agent — toujours `tailscale ssh <hôte>`, jamais `ssh` direct ; méthode cockpit wsh.
SkillAFreshness: AClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get quicksilver running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
quicksilver skill. Agent Mart. https://agentmart.dev/skills/qveys-quicksilver (last updated 2026-10-24)