SkillAgentSearch skills...

openrouter

Design, build, debug, and optimize OpenRouter API integrations. Use for any OpenRouter API work, including models, reasoning, routing, media, tools, structured output, cost, or performance.

Install / Use

npx skills add davidondrej/skills --skill openrouter

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

82/100

Supported Platforms

Universal

Our assessment of openrouter

openrouter scores 82/100 on our quality scale, 3322nd of 4,698 Development & Engineering skills we index.

Its SKILL.md is 5.1 KB long, split into 5 sections and no code examples: a solid amount of guidance for an agent.

With 4,079 GitHub stars, it is one of the more widely adopted skills in the catalogue.

Substance
26/30
Structure
11/20
Description
15/15
Adoption
15/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated about 2 months ago, so openrouter is actively maintained.
  • Our last check on 2026-11-07 found the source still online.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-11-16. Automated pattern scan on 2026-11-16. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

openrouter compared with similar skills

All 4 of these similar skills score higher than openrouter; compare them before choosing.

SkillScoreStarsUpdatedFormat
openrouter (this skill)by davidondrej824.1k53d agoSKILL.md
taste-skillby Leonxlnx100116.8k8d agoCLAUDE.md
Agent-Reachby Panniantong100112.3k8d agoCLAUDE.md
headroomby headroomlabs-ai10079.8ktodayCLAUDE.md
ai-job-searchby ai-job-search-dev10072.1ktodayCLAUDE.md

Frequently asked questions

How do I install openrouter?
Run npx skills add davidondrej/skills --skill openrouter. The install tabs above show the steps for each supported agent.
Which AI agents does openrouter work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is openrouter safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is openrouter still maintained?
The repository was last updated about 2 months ago, so openrouter is actively maintained.

name: openrouter description: 'Design, build, debug, and optimize OpenRouter API integrations. Use for any OpenRouter API work, including models, reasoning, routing, media, tools, structured output, cost, or performance.'

OpenRouter

Make model behavior explicit. Preserve the user's quality, cost, privacy, and reliability requirements across every route and retry.

Before changing configuration

  1. Inspect the actual outgoing request, SDK version, existing configuration, and user preferences. Redact credentials and content. A setting in a UI or config file does not prove the SDK sends it.
  2. Verify exact model IDs and live capabilities through the models API. Inspect the selected model's provider endpoints too. Check input/output modalities, context and output limits, supported parameters, reasoning options, prices, and provider availability for both primary and fallback models.
  3. Choose and record an explicit reasoning setting for each reasoning model. Use the user's requested effort. If unspecified, choose a supported value for the task and state the choice; do not silently inherit a provider default or impose one effort on every model. Read reasoning and output before setting these fields.
  4. Set an output ceiling, total deadline, bounded retry policy, and cost limits appropriate to the workload. Reasoning uses output tokens too. A model's context window is not its maximum output length.
  5. Read the relevant reference below. Consult current official docs for unfamiliar fields; do not invent model IDs, provider slugs, parameter support, or SDK syntax.

Rules that prevent expensive mistakes

  • Use the unified reasoning object. reasoning.exclude: true hides reasoning; it does not turn reasoning off or make it free. Mandatory reasoning models cannot be disabled.
  • Check every fallback against the same required capabilities and privacy/cost constraints. A single models request shares configuration across candidates. If models need different efforts or budgets, implement bounded application-level attempts with separate configs.
  • Separate provider failover from model fallback. provider.order is a preference; only restricts providers; ignore excludes them. Use provider.require_parameters: true when silently dropping requested parameters would break correctness. Recheck endpoint support; this is not a semantic guarantee.
  • Match routing to the real goal: provider.sort: "price" for price, "latency" for TTFT, "throughput" for tokens/second. :nitro also permits priority tiers; :floor also permits flex tiers. They can change price or availability beyond plain sorting.
  • HTTP 200 is not application success. Check errors, finish reason, expected output type, schema, and task-specific validity. Null text may be a valid tool call. A truncated or unreviewed answer must not become a successful artifact.
  • Do not repeat a deterministic failure unchanged. On a confirmed output-limit failure, consider a supported lower effort, smaller task, or compatible fallback within the quality budget. Increasing the cap is one option, not the automatic answer. Preserve fail-closed validation on every attempt.
  • Keep keys server-side. Log diagnostic metadata, not prompts, attachments, raw reasoning, or provider errors that may contain private content. Never weaken safety/privacy restrictions just to get a successful response.

Read only what the task needs

Verify the integration

Capture the serialized request in a redacted local test. Verify explicit reasoning, output limits, fallbacks, and routing constraints survive SDK serialization. Test the actual failure boundary: limit reached, null/tool output, malformed JSON, missing required capability, or mid-stream error. Run a small real smoke test when inference is authorized; do not describe mock validation as a production test.

For tuning, compare representative tasks using valid-result rate, cost per valid result, time to first visible answer, and total duration. Include retries and failed attempts. Lower effort or a faster route is acceptable only if required quality and safety still pass.

Report the chosen primary/fallback models, explicit effort and caps, routing goal, and what was verified. Distinguish confirmed API evidence from hypotheses.

Related Skills

View on GitHub
GitHub Stars4.1k
CategoryDevelopment
Updated1mo ago
Forks601

Languages

Shell

Trust signals

100/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

No cautions