router
Skill86 starsChanged 9 days agoMITView on GitHub
Intent router that detects user intent from plain messages and dispatches to the appropriate skill.
17 other projects use a version of this.
Adopted by
Most recently taken up by
- lizzyDeng/claude-skillstheir own version, first seen Nov 8, 2026
- apattichis/agentic-research-toolkittheir own version, first seen Nov 8, 2026
- Wellsonr/skillsettheir own version, first seen Nov 8, 2026
- guang-lee-cn/scaffold-skillstheir own version, first seen Nov 8, 2026
- sam-ash-cy/sams-agentic-workflowtheir own version, first seen Nov 8, 2026
- lubusIN/frappe-skillstheir own version, first seen Nov 4, 2026
Other versions17 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 17
- gamedev-skills/awesome-gamedev-agent-skills★ 6.4ksame name
- lubusIN/frappe-skills★ 68same name
- timharris707/skills★ 44same name
- jammyfu/open-game-skills★ 12same name
- Canary-ECAD/eplan-scripting-skill★ 5same name
- Aetherdz/huntpack★ 4same name
- SunCherry/agentic-AI_analog_IC_auto-designer★ 4same name
- Adnova-Group/muster★ 2same name
- guang-lee-cn/scaffold-skills★ 2same name
- letsloose501/sqs-agent-memory★ 2same name
7 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository20 other files it gives its agents.
- AGENTS.mdAGENTS.md
- analyticsSkill
- blind-spotSkill
- briefSkill
- calibrateSkill
- challengeSkill
- feedbackSkill
- fetchSkill
- grainulatorSkill
- healthcheckSkill
- initSkill
- orchestrateSkill
- presentSkill
- pullSkill
- researchSkill
- resolveSkill
- setupSkill
- statusSkill
- syncSkill
- witnessSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 13 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 35
If a clear match exists, announce the routing:
“Common” is measured: kept by at least 6 in 10 of the 13 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
/router -- Intent Router
Routes plain-language user messages to the appropriate grainulator skill.
Intent Map
| User says something like... | Route to | Why |
| "look into X", "what about X", "explore X" | /research X | Information gathering |
| "is p001 really true?", "I doubt X" | /challenge <id> | Adversarial testing |
"check this: <url>", "does <url> support X" | /witness <id> <url> | External corroboration |
| "what are we missing", "any gaps?" | /blind-spot | Structural gap analysis |
| "where are we", "what's the status" | /status | Sprint snapshot |
| "write it up", "summarize for the team" | /brief | Decision document |
| "make slides", "prepare for the meeting" | /present | Stakeholder presentation |
| "publish to confluence", "sync to confluence", "push to wiki" | /sync | Confluence publish |
| "pull from confluence", "import from wiki", "backfill from confluence" | /pull <slug> | Confluence pull |
| "show the plan", "what sprints are next", "dependency graph" | /orchestrate | Multi-sprint orchestration |
| "show analytics", "how healthy is this sprint", "stale claims" | /analytics | Sprint analytics |
| "fetch this url", "what does <url> say", "summarize <url>" | /fetch <url> | Size-efficient URL fetch |
Instructions
- Analyze the user's message for intent signals (verbs, keywords, URLs, claim IDs).
- If a clear match exists, announce the routing:
Running as
/research "topic"-- this will create claims and compile. Say "just answer" if you wanted a quick response instead. - Invoke the matched skill.
- Preserve the active task and use its context to resolve routine ambiguity. Ask only for missing information that materially changes the work. An explicit
/grainulatorengineering request routes toskills/grainulator/SKILL.mdand includes implementation and verification.
When NOT to route
- Questions about the framework itself ("how does the compiler work?")
- Ordinary code edits without an explicit Grainulator workflow request
- General conversation
- Ambiguous intent without research context
Host access
Use available grainulator MCP tools, passing the active sprint dir explicitly for evidence operations. If a tool is unavailable, use the local grainulator CLI (or node <checkout>/bin/grainulator.js). Read sibling skill files directly when slash commands are unavailable. Resolve template paths relative to this skill’s checkout when CLAUDE_PLUGIN_ROOT is unset. Optional external connectors are not required for local work; use local code, supplied documents, or available web tools. Do not write managed ledger files directly to bypass a missing MCP connection.
Next-step output
For standalone fetch, setup, or read-only orchestration without an evidence sprint, derive next steps from that task. Do not initialize or compile an unrelated ledger just to produce this footer.
When working in an evidence sprint, use the current compiler's next_actions to present exactly two bullet lists labeled Auto and Manual. Auto is work the agent can continue under existing authorization. Manual is only work requiring the user's decision, access, or action. Classify using the current request and constraints; compiler suggestions never grant permission. Continue authorized Auto work without asking again.
Keep 2–3 useful actions total when available, use short concrete labels and commands where useful, and show None. for an empty group. Do not invent work to fill a quota. Never omit next steps merely because compilation is ready or the answer should be brief. Refresh stale compilation first and exclude work the user removed from scope. When the user asks only for next steps, output only these two lists: no findings recap, counts, reasons, or offer to continue.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

