Hi - I answer from the OpenSmartRoute documentation: routing, the API, plans and quotas, self-hosting. Ask away, or open a support ticket if you need a person.
Grounded in the docs - follow a source before acting on it.
strategy - Skill - OpenSmartRoute
Skillv1.0.0
strategy
Strategic pre-code planning for a single feature or goal: explore the codebase, clarify requirements, weigh approaches, and produce a high-level implementation strategy. Reason, not sequence — see con
Imported from nq-rdl/agent-extensions (plugins/planning/skills/strategy/SKILL.md). Install upstream with npx skills add nq-rdl/agent-extensions --skill strategy. Copyright stays with the author (MIT).
Strategy
Establish the goal, constraints, current architecture, and unresolved decisions. Compare viable approaches and produce a high-level implementation strategy with risks and validation criteria. Keep code unchanged; use the sequence skill when a file-by-file edit order is needed.
Optional delegation
references/subagent.rst contains the subagent outline,
handoff inputs, execution boundaries, and expected result. Read it when delegating
would help or the user asks to “create a subagent to execute this.” Otherwise,
work directly from this skill; the reference does not need to be loaded.
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
# after Install: the listing is in your workspace's routing pool - a plan picks it for its slot
curl -s -X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'
Manifest
An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.
nq-rdl-agent-extensions-strategy.ocm.jsonjson
{
"ocm": "1",
"id": "nq-rdl-agent-extensions-strategy",
"kind": "skill",
"name": "strategy",
"description": "Strategic pre-code planning for a single feature or goal: explore the codebase, clarify requirements, weigh approaches, and produce a high-level implementation strategy. Reason, not sequence — see context-architect when you need file-level ordering.",
"publisher": "nq-rdl",
"version": "1.0.0",
"capabilities": {
"domains": [
"coding"
],
"tags": [
"skill-md",
"github"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Strategic pre-code planning for a single feature or goal: explore the codebase, clarify requirements, weigh approaches, and produce a high-level implementation strategy. Reason, not sequence — see context-architect when you need file-level ordering."
],
"primary": false,
"metadata": {
"source": {
"provider": "github",
"repository": "https://github.com/nq-rdl/agent-extensions",
"path": "plugins/planning/skills/strategy/SKILL.md",
"ref": "660a2cee33830716f60e43a897de149ad1293277",
"url": "https://github.com/nq-rdl/agent-extensions/blob/660a2cee33830716f60e43a897de149ad1293277/plugins/planning/skills/strategy/SKILL.md",
"key": "nq-rdl/agent-extensions/plugins/planning/skills/strategy/SKILL.md"
},
"license": "MIT"
},
"instructions": "# Strategy\n\nEstablish the goal, constraints, current architecture, and unresolved decisions. Compare viable approaches and produce a high-level implementation strategy with risks and validation criteria. Keep code unchanged; use the sequence skill when a file-by-file edit order is needed.\n\n## Optional delegation\n\n[references/subagent.rst](references/subagent.rst) contains the subagent outline,\nhandoff inputs, execution boundaries, and expected result. Read it when delegating\nwould help or the user asks to “create a subagent to execute this.” Otherwise,\nwork directly from this skill; the refere",
"cost": {
"context_tokens": 157
}
}
Fetch it by URL: GET /api/v1/registry/nq-rdl-agent-extensions-strategy/manifest?version=1.0.0
Reviews
Star ratings from people who tried it. One review per account; edit yours any time.
No reviews yet. Install it, try it, and be the first to rate it.
