mitriyweb/task-routing
agents/fullstack/skills/task-routing/SKILL.md
Classify task scope (frontend, backend, fullstack) and route to the correct developer(s). Used by the team lead for every task before spawning agents.
$ install --global
skillsauthnpx skillsauth add mitriyweb/agent-team task-routingInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 25, 2026, 9:17 AM244.0s1 file scanned
SKILL.md
- name:
- task-routing
- description:
- >-
- compatibility:
- Requires bash, Claude Code
- team:
- fullstack
- role:
- team-lead
- version:
- 1.0
The team lead uses this skill to classify and route every task to the correct developer(s).
Scope Classification Procedure
Step 1: Read Task Spec
Read the task description, any referenced files, and .claude-loop/reports/task-{id}-spec.md (if it exists from a prior architect pass).
Step 2: Identify File Signals
| Files / Directories | Scope |
|---------------------|-------|
| src/components/, src/views/, src/pages/, *.tsx, *.jsx, *.vue, *.svelte, *.css, *.scss | frontend |
| src/api/, src/routes/, src/services/, src/models/, src/middleware/, migrations/, *.controller.*, *.service.* | backend |
| src/lib/, src/utils/, src/types/, src/config/ | shared (check contents) |
| tests/unit/views/, tests/unit/components/, *.test.tsx | frontend tests |
| tests/unit/api/, tests/unit/services/, tests/integration/ | backend tests |
| tests/e2e/ | fullstack tests |
Step 3: Identify Keyword Signals
| Keywords in Task Description | Scope | |------------------------------|-------| | component, view, page, layout, responsive, design token, CSS, WCAG, accessibility, UI | frontend | | endpoint, API, route, controller, service, model, migration, database, query, auth, middleware | backend | | feature (that names both UI and API), user flow, integration | fullstack |
Step 4: Decide
- If ALL signals point to one stack -> route to that stack
- If signals are mixed -> classify as fullstack
- If ambiguous -> default to fullstack (safer to involve both developers than to miss a stack)
Step 5: Log Decision
Always document the routing decision in SUMMARY.md:
## Routing Decision
- **Scope**: frontend | backend | fullstack
- **Routed to**: fe-dev | be-dev | both
- **Signals**: [list of files/keywords that drove the decision]
Common Routing Mistakes
- Routing a "fix API validation" task to fe-dev
- Routing a "add loading spinner" task to be-dev
- Routing a "add user settings" task to only one dev when it needs both a settings API and a settings page
- Assuming test tasks don't need routing (they do -- frontend tests go to fe-dev, backend tests to be-dev)
Related Skills
mitriyweb/lib/templates
development
VerifiedTrustedCommunity
--- name: agent-team description: Use this skill when working on the agent-team repository — adding agents, modifying orchestration logic, updating CLAUDE.md configs, extending memory patterns, or debugging multi-agent flows. Covers: Claude SDK query() loop, YAML frontmatter agent configs, memory.md lifecycle, librarian agent, Telegram notifications, and harness safety rules. --- # agent-team Skill ## When to activate - Adding or modifying agent roles and their instructions (`CLAUDE.m
3SKILL.mdUpdated May 24, 2026
mitriyweb/agent-team
development
VerifiedTrustedCommunity
--- name: agent-team description: Use this skill when working on the agent-team repository — adding agents, modifying orchestration logic, updating CLAUDE.md configs, extending memory patterns, or debugging multi-agent flows. Covers: Claude SDK query() loop, YAML frontmatter agent configs, memory.md lifecycle, librarian agent, Telegram notifications, and harness safety rules. --- # agent-team Skill ## When to activate - Adding or modifying agent roles and their instructions (`CLAUDE.m
3SKILL.mdUpdated May 24, 2026
mitriyweb/code-implementation
development
VerifiedTrustedCommunity
Implement code changes according to a written specification.
3SKILL.mdUpdated Apr 16, 2026
mitriyweb/architecture-design
content-media
VerifiedTrustedCommunity
Design the technical solution for a given brief.
3SKILL.mdUpdated Apr 15, 2026