openrouter
Call non-Anthropic models (DeepSeek, Qwen, GLM, Kimi, etc.) from Claude Code via OpenRouter.
Skill by siinghd
Chalk Labs
Need help deploying openrouter?
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/siinghd-openrouter
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: agent-building
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. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/openrouter
What's inside
- Skill name
openrouter- Description
- Call non-Anthropic models (DeepSeek, Qwen, GLM, Kimi, etc.) from Claude Code via OpenRouter. Two dispatch modes - a curl-based one-shot "oracle" (or-chat.sh) for generation/review from supplied context, and fully agentic headless workers (or-proxy.sh + or-worker.sh) that run claude -p on an OpenRouter model through a local LiteLLM gateway. Use when the user asks to use DeepSeek/OpenRouter/another provider's model, wants a cheap second opinion, or /orchestrate needs the cheap execution tier.
- License
- unknown
- Instructions
- 106 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
- Instructions read files in your home folder (~/.ssh, ~/.aws…)
Files (16)
- SKILL.md
- led.py · ledger/
- schema.sql · ledger/
- test_led.py · ledger/tests/
- litellm-config.yaml
- server.py · mcp/
- or-chat.sh · scripts/
- or-common.sh · scripts/
- or-config.sh · scripts/
- or-evidence.sh · scripts/
- or-monitor.sh · scripts/
- or-proxy.sh · scripts/
- or-worker.sh · scripts/
- test-or-evidence.sh · scripts/tests/
- setup.sh
- worker-settings.json
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from siinghd/skills
- 0.524score
research
siinghd
Autonomous ML research loop for a "research lab" repo — survey, hypothesize, pre-register, run matched-compute experiments with seeds and a negative control…
SkillBFreshness: BClaude Code +9 - 0.519score
optimize
siinghd
Comprehensive optimization audit for any codebase (frontend, backend, libraries, scripts) — finds bad logic, missing abstractions, security smells…
SkillBFreshness: BClaude Code +9 - 0.519score
orchestrate
siinghd
Run the current task in orchestrator/worker mode - the session model plans, delegates execution to Opus-pinned workers (worker/scout/verifier agents)…
SkillBFreshness: BClaude Code +9 - 0.516score
startfrom
siinghd
Create a HANDOFF.md document at the end of a long conversation that captures full context (goal, work done, decisions, dead ends, current state, next concrete…
SkillBFreshness: BClaude Code +9 - 0.508score
git-commit
siinghd
Generates a Conventional Commit message based on staged changes.
SkillBFreshness: BClaude Code +9 - 0.508score
save
siinghd
Creates a temporary 'checkpoint' commit with all current changes.
SkillBFreshness: BClaude Code +9 - 0.505score
tdd-scaffold
siinghd
Scaffolds failing tests and a shell implementation for TDD.
SkillBFreshness: BClaude Code +9 - 0.505score
refactor
siinghd
Refactors a file for clarity, performance, and correctness.
SkillBFreshness: BClaude Code +9 - 0.474score
plan
siinghd
Creates a durable, file-based implementation plan with up-to-date dependency research.
SkillCFreshness: CClaude Code +9 - 0.459score
revert
siinghd
Reverts the last CHECKPOINT commit and analyzes the reverted changes.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 23, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/siinghd/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from siinghd
- 0.524score
research
siinghd
Autonomous ML research loop for a "research lab" repo — survey, hypothesize, pre-register, run matched-compute experiments with seeds and a negative control…
SkillBFreshness: BClaude Code +9 - 0.519score
optimize
siinghd
Comprehensive optimization audit for any codebase (frontend, backend, libraries, scripts) — finds bad logic, missing abstractions, security smells…
SkillBFreshness: BClaude Code +9 - 0.519score
orchestrate
siinghd
Run the current task in orchestrator/worker mode - the session model plans, delegates execution to Opus-pinned workers (worker/scout/verifier agents)…
SkillBFreshness: BClaude Code +9 - 0.516score
startfrom
siinghd
Create a HANDOFF.md document at the end of a long conversation that captures full context (goal, work done, decisions, dead ends, current state, next concrete…
SkillBFreshness: BClaude Code +9 - 0.508score
git-commit
siinghd
Generates a Conventional Commit message based on staged changes.
SkillBFreshness: BClaude Code +9 - 0.508score
save
siinghd
Creates a temporary 'checkpoint' commit with all current changes.
SkillBFreshness: BClaude 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 openrouter 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
openrouter skill. Agent Mart. https://agentmart.dev/skills/siinghd-openrouter (last updated 2026-10-24)