Answers from the documentation; checking which model is on duty
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.
map - Skill - OpenSmartRoute
Skillv1.0.0
map
The yard's skill map — which skill owns which job, in delivery-loop order. Use when something needs doing but not which of the shipped skills owns it; the map routes, it never executes.
Imported from yeachan-heo/oh-my-claudecode (skills/map/SKILL.md). Install upstream with npx skills add yeachan-heo/oh-my-claudecode --skill map. Copyright stays with the author.
Map
You know something needs doing; you do not know which skill owns it. Find the job below and follow its route. Most routes call the Skill tool; a route marked manual gives you the slash command to invoke yourself because model invocation is disabled. The map routes and explains nothing twice — each routed skill owns its own doctrine.
The delivery loop
You are here
Skill
External work arrived (issues, PRs, reports)
harbor
A non-engineer handed you a chat log as requirements
intent
The destination is foggy — the first three decisions cannot be stated yet
ask-navigator
Vague idea; questions must come before anything else
deep-interview
Requirements are clear; you need a plan
plan (multi-perspective consensus: ralplan)
Approved plan; decompose and ship end to end with human checkpoints
launch
One task; persistence until verified complete
ralph
Hands-off idea-to-code
autopilot
Work needs coordinated parallel workers
team
One approved task carried through verified code
execute
One attempt risks locking in the wrong shape
arena
Code crosses a function boundary; designs should compete first
architect
Finished work needs attack before it ships
interrogate
A design question prose cannot settle
loft
Finished work needs judgment
review
Something claims to be done
verify
Work is landing as a PR
pr
An open PR needs driving to merge-ready
babysit
The run taught the environment something
refit
On-ramps (off the main loop)
Job
Skill
A bug needs its root cause
debug; competing-hypothesis tracing: trace
The question is why the code is this way
why
A subsystem needs explaining
how; as a lesson: teach
A risky change needs its blast radius mapped
blast-radius
The same agent mistake keeps recurring
correct
Long autonomous work needs an audit trail
show-me-your-work
No bundled skill fits the task shape
figure-it-out (designs one, validated against anchors)
ketchup; as a subtitled video: ketchup-video; after a break or crash: recall
A brief is vague
sharpen; playback before starting: in-your-own-words
A reply was too dense
bro
Shipping prose needs the standard
technical-writing; TS type discipline: typescript-best-practices
The period's authored work needs summarizing
what-did-i-get-done
A queue must land as one stacked PR chain
stacked-delivery; watch state: babysit
A measured target needs climbing over multiple rounds
hillclimb
A long session's lessons should be banked as skill edits
reflect; extraction: skillify
A cross-project personal behavior profile is wanted
personal-mode; single facts: remember
Rules
The map routes; it never executes. Each ordinary row resolves to one Skill-tool call — make it, then follow that skill's doctrine. For a manual-only route, show the user its slash command; do not try to call the Skill tool.
When two rows both fit, the delivery loop above is the tiebreak: earlier legs come first.
Phase boundaries (continue / re-enter from disk / hand off / compact) are defined in launch's Context hygiene — the map does not restate them.
A job matching no row is itself information: say so plainly rather than picking the nearest-sounding skill.
Installed into a catalogue, chosen by a router
Install map and it becomes one more candidate the router can pick - when it fits.
A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.
When a provider is down or over quota the request moves on; the trace says it did.
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 slotcurl-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.
yeachan-heo-oh-my-claudecode-map.ocm.jsonjson
{
"ocm": "1",
"id": "yeachan-heo-oh-my-claudecode-map",
"kind": "skill",
"name": "map",
"description": "The yard's skill map — which skill owns which job, in delivery-loop order. Use when something needs doing but not which of the shipped skills owns it; the map routes, it never executes.",
"publisher": "yeachan-heo",
"version": "1.0.0",
"capabilities": {
"domains": [
"coding",
"customer_support"
],
"tags": [
"skill-md",
"skills-sh"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"The yard's skill map — which skill owns which job, in delivery-loop order. Use when something needs doing but not which of the shipped skills owns it; the map routes, it never executes."
],
"primary": false,
"metadata": {
"source": {
"provider": "skills.sh",
"repository": "https://github.com/yeachan-heo/oh-my-claudecode",
"path": "skills/map/SKILL.md",
"ref": "HEAD",
"url": "https://github.com/yeachan-heo/oh-my-claudecode/blob/HEAD/skills/map/SKILL.md",
"key": "yeachan-heo/oh-my-claudecode/skills/map/SKILL.md"
}
},
"instructions": "# Map\n\nYou know something needs doing; you do not know which skill owns it. Find the job below and follow its route. Most routes call the Skill tool; a route marked manual gives you the slash command to invoke yourself because model invocation is disabled. The map routes and explains nothing twice — each routed skill owns its own doctrine.\n\n## The delivery loop\n\n| You are here | Skill |\n|---|---|\n| External work arrived (issues, PRs, reports) | `harbor` |\n| A non-engineer handed you a chat log as requirements | `intent` |\n| The destination is foggy — the first three decisions cannot be stated yet | `ask-navigator` |\n| Vague idea; questions must come before anything else | `deep-interview` |\n| Requirements are clear; you need a plan | `plan` (multi-perspective consensus: `ralplan`) |\n| Approved plan; decompose and ship end to end with human checkpoints | `launch` |\n| One task; persistence until verified complete | `ralph` |\n| Hands-off idea-to-code | `autopilot` |\n| Work needs coordinated parallel workers | `team` |\n| One approved task carried through verified code | `execute` |\n| One attempt risks locking in the wrong shape | `arena` |\n| Code crosses a function boundary; designs should compete first | `architect` |\n| Finished work needs attack before it ships | `interrogate` |\n| A design question prose cannot settle | `loft` |\n| Finished work needs judgment | `review` |\n| Something claims to be done | `verify` |\n| Work is landing as a PR | `pr` |\n| An open PR needs driving to merge-ready | `babysit` |\n| The run taught the environment something | `refit` |\n\n## On-ramps (off the main loop)\n\n| Job | Skill |\n|---|---|\n| A bug needs its root cause | `debug`; competing-hypothesis tracing: `trace` |\n| The question is why the code is this way | `why` |\n| A subsystem needs explaining | `how`; as a lesson: `teach` |\n| A risky change needs its blast radius mapped | `blast-radius` |\n| The same agent mistake keeps recurring | `correct` |\n| Long autonomous work needs an audit trail | `show-me-your-work` |\n| No bundled skill fits the task shape | `figure-it-out` (designs one, validated against anchors) |\n| A property tests cannot reach needs formal proof | `create-formal-verification-skill`; drifted spec: `maintain-formal-verification-skill` |\n| A flow or protocol bug shows up as a path through states | `statechart` |\n| The repo needs its own verification commands recorded | `create-verification-skill`; drifted commands: `maintain-verification-skill` |\n| Roles should run on chosen models | `models` |\n| Tests should drive the implementation | `tdd` |\n| The codebase is getting harder to change | `architecture-survey` |\n| AI-generated slop needs cleanup | `ai-slop-cleaner` |\n| A measured number needs vetting before it is reported or acted on | `benchmark-checklist` |\n| A delegated brief needs cross-cutting judgment guardrails | `principles` |\n| An open question needs grounded answers | `research`; external docs: `external-context` |\n| Knowledge should compound across sessions | `wiki`; durable project memory: `remember` |\n| A recurring autonomous improvement loop | `self-improve`; durable goal ledger: `ultragoal` |\n| A session needs reorientation across its pivots and outcomes | `session-flow` — run `/oh-my-claudecode:session-flow` manually |\n| Visual work needs verdicts or diagrams | `visual-verdict`; `diagram` |\n\n## Utilities\n\n| Job | Skill |\n|---|---|\n| Install, diagnose, configure | `omc-setup`; `omc-doctor`; `configure-notifications` |\n| Manage skills themselves | `skill` (local); `skillify` (extract from session) |\n| Inspect orchestration state | `trace` (also the tracing lane); `graph` (DAG runtime) |\n| Cancel a mode | `cancel` |\n| CI is red on a PR you own | `fix-ci`; review threads: `get-pr-comments`; conflicts: `fix-merge-conflicts` |\n| The user missed the session | `ketchup`; as a subtitled video: `ketchup-video`; after a break or crash: `recall` |\n| A brief is vague | `sharpen`; playback before starting: `in-your-own-words` |\n| A reply was too dense | `bro` |\n| Shipping prose needs the standard | `technical-writing`; TS type discipline: `typescript-best-practices` |\n| The period's authored work needs summarizing | `what-did-i-get-done` |\n| A queue must land as one stacked PR chain | `stacked-delivery`; watch state: `babysit` |\n| A measured target needs climbing over multiple rounds | `hillclimb` |\n| A long session's lessons should be banked as skill edits | `reflect`; extraction: `skillify` |\n| A cross-project personal behavior profile is wanted | `personal-mode`; single facts: `remember` |\n\n## Rules\n\n- The map routes; it never executes. Each ordinary row resolves to one Skill-tool call — make it, then follow that skill's doctrine. For a manual-only route, show the user its slash command; do not try to call the Skill tool.\n- When two rows both fit, the delivery loop above is the tiebreak: earlier legs come first.\n- Phase boundaries (continue / re-enter from disk / hand off / compact) are defined in `launch`'s Context hygiene — the map does not restate them.\n- A job matching no row is itself information: say so plainly rather than picking the nearest-sounding skill.",
"cost": {
"context_tokens": 1288
}
}
Fetch it by URL: GET /api/v1/registry/yeachan-heo-oh-my-claudecode-map/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.
