Chalk Labs
Need help deploying intent-classification?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/dr-pabs-intent-classification
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions: not checked yet.
What's inside
- Skill name
intent-classification- Description
- None
- License
- MIT
- Instructions
- 50 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- missing YAML frontmatter
- name: missing
- description: missing
Files (1)
- SKILL.md
SKILL.md (first lines)
# Intent Classification
The orchestrator invokes this skill to classify a user message into a supported intent before dispatching minions.
## When to invoke
- At the start of every user request.
- When the orchestrator needs to re-classify after clarification.
## Input
- `user_message`: the raw text from the user (string).
- `platform`: the source channel — `slack`, `teams`, `cli`, or `dashboard` (string).
- `session_context`: optional prior-turn summary (string).
## Output
Return JSON matching `schemas/intent.json`:
```json
{
"intent": "ticket_lookup|ticket_summary|code_explore|code_review|pr_create|security_audit|ticket_fix_pr",
"complexity": "simple|complex",
"platform": "slack|teams|cli|dashboard",
"entities": {}
}
```
### Intent definitions
- `ticket_lookup` — "What's the status of INC00421?"
- `ticket_summary` — "Summarize AB#1234"
- `code_explore` — "Find where login timeout is handled"
- `code_review` — "Review PR #342"
- `pr_create` — "Create a PR for this fix"
- `security_audit` — "Audit this repo for secrets"
- `ticket_fix_pr` — "Fix work item #567 and create a PR"
### Complexity rules
- `simple` — single minion can handle it (`ticket_lookup`, `ticket_summary`, `code_explore`, `code_review`, `security_audit`).
- `complex` — requires a DAG of multiple minions (`ticket_fix_pr`, batch reviews, multi-ticket summaries).
## Example
Input: `"@minions review PR #342"`
Output:
```json
{
"intent": "code_review",
"complexity": "simple",
"platform": "slack",
"entities": { "pr_number": 342 }
}
```From dr-pabs/managed-service-minions, MIT.
More from dr-pabs/managed-service-minions
- 0.461score
Frontend / Dashboard Engineer
dr-pabs
Deliver the operator-facing dashboard and observability surfaces for the framework.
SkillCFreshness: CClaude Code +9 - 0.461score
Goose / Agent Engineer
dr-pabs
Build and evolve the core Goose-based orchestration layer for the Minions Agent Framework.
SkillCFreshness: CClaude Code +9 - 0.461score
Product Owner
dr-pabs
Define scope, priorities, and delivery readiness for the Goose framework.
SkillCFreshness: CClaude Code +9 - 0.461score
QA / Test Engineer
dr-pabs
Make the framework reliable through automated and manual verification.
SkillCFreshness: CClaude Code +9 - 0.461score
DevOps / CI-CD Engineer
dr-pabs
Automate build, validation, deployment, and release operations for the project.
SkillCFreshness: CClaude Code +9 - 0.461score
Prompt / LLM Engineer
dr-pabs
Make the minions reliable, accurate, and measurable through prompt design and evaluation.
SkillCFreshness: CClaude Code +9 - 0.461score
Azure / Infrastructure Engineer
dr-pabs
Provision and operate the Azure runtime that hosts the Goose framework.
SkillCFreshness: CClaude Code +9 - 0.461score
Security Engineer
dr-pabs
Protect the framework from unsafe tool use, privilege escalation, and operational risk.
SkillCFreshness: CClaude Code +9 - 0.461score
MCP / Integration Engineer
dr-pabs
Connect the framework to real external systems through MCP and API integrations.
SkillCFreshness: CClaude Code +9 - 0.251score
result-synthesis
dr-pabs
No description from the publisher yet.
SkillCFreshness: CClaude Code +9 - 0.251score
task-decomposition
dr-pabs
No description from the publisher yet.
SkillCFreshness: CClaude Code +9 - 0.251score
approval-gating
dr-pabs
No description from the publisher yet.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 2
- Open issues
- 0
- Last commit (this folder)
- Jun 16, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from dr-pabs
- 0.461score
DevOps / CI-CD Engineer
dr-pabs
Automate build, validation, deployment, and release operations for the project.
SkillCFreshness: CClaude Code +9 - 0.461score
MCP / Integration Engineer
dr-pabs
Connect the framework to real external systems through MCP and API integrations.
SkillCFreshness: CClaude Code +9 - 0.461score
Prompt / LLM Engineer
dr-pabs
Make the minions reliable, accurate, and measurable through prompt design and evaluation.
SkillCFreshness: CClaude Code +9 - 0.461score
Security Engineer
dr-pabs
Protect the framework from unsafe tool use, privilege escalation, and operational risk.
SkillCFreshness: CClaude Code +9 - 0.461score
Azure / Infrastructure Engineer
dr-pabs
Provision and operate the Azure runtime that hosts the Goose framework.
SkillCFreshness: CClaude Code +9 - 0.461score
Frontend / Dashboard Engineer
dr-pabs
Deliver the operator-facing dashboard and observability surfaces for the framework.
SkillCFreshness: CClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get intent-classification running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
intent-classification skill. Agent Mart. https://agentmart.dev/skills/dr-pabs-intent-classification (last updated 2026-10-24)