Orchestrator
Skill karim-bhalwani/agent-skills-collection/skills/orchestrator
AI agents are smart but unreliable without procedure. "Agent Skills" are executable checklists that package expertise.
npx -y skills add karim-bhalwani/agent-skills-collection --skill orchestratorAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Specialized in managing project-wide constraints, context tiers, and coordination between specialized skills. Use when interpreting project rules, coordinating complex workflows, managing context and dependencies, or overseeing multi-skill project execution.
SKILL.md
4.1 KB, 810 tokens by cl100k_base, as published. Nobody here has run it
Orchestrator Skill - Project Governance & Context Management
Overview
The Orchestrator skill acts as the project's "Knowledge Keeper." It ensures that every action taken by other skills aligns with the project's technology stack, architecture styles, and critical rules.
Core Responsibilities
1. Tiered Context Management
- Tier 1 (Constant): Ensure tech stack, OS platform, and critical security rules are always top-of-mind.
- Tier 2 (Task-Specific): Load domain context (e.g., API patterns for web tasks, schemas for data tasks) only when needed to save tokens.
- Tier 3 (Historical): Reference
decisions.mdto understand why certain patterns were established.
2. Constraint Validation
- Authority: Maintain the "Approved Libraries" list.
- Guardrail: Block any implementation that violates project-wide "Non-Negotiables" (e.g., "No raw SQL", "Mandatory Pydantic validation").
- Escalation: Identify when a specialist's request conflicts with existing documentation.
3. Skill Coordination
- Analyze a task and determine the sequence of skills required (e.g.,
navigator->architect->implementer->guardian). - Manage handoffs between skills, ensuring the output of one serves as a clean input for the next.
Output Format: Tiered Context Block
When preparing a task, the Orchestrator should output:
- Project Pillars: Core tech and architecture.
- Hard Constraints: Non-negotiable rules for this specific task.
- Handoff Map: Sequence of skills to be invoked.
When to Use
- When first joining a project.
- To clarify "how we do things here."
- To validate if a new library or pattern is allowed.
- To plan the multi-step execution of a complex feature.
Constraints
- NO implementation. Only governs and validates.
- NO writing source code.
- DO NOT invent context. If rules aren't documented, explicitly state the gap.
Outputs & Deliverables
- Primary Output: Tiered context block (Tier 1/2/3), handoff map, and skill routing recommendations
- Secondary Output: Constraint validation report identifying conflicts or gaps
- Success Criteria: All team members agree on the handoff sequence and context requirements
- Quality Gate: Approved by project owner or lead before skill delegation begins
Common Pitfalls
- Inventing Constraints: "I assume we use TypeScript" when it's undocumented. If rules aren't documented, explicitly state the gap.
- Over-Constraining: Blocking everything with "team standards" that don't exist yet. Only enforce documented rules.
- Poor Handoff Maps: Routing tasks to the wrong skill because you didn't understand the requirement. Always think through skill dependencies.
- Missing Context Tiers: Throwing everything at an agent at once instead of tiering (Tier 1: always, Tier 2: on demand, Tier 3: history).
- Ignoring New Patterns: Not updating constraints when the codebase evolves. Review and refresh quarterly.
- Conflict Blindness: Not catching when a new requirement contradicts existing documented rules. Always cross-reference.
Integration Points
| Phase | Input From | Output To | Context |
|---|---|---|---|
| Project Onboarding | Project README, existing rules | Context setup | Create initial Tiered Context Block |
| Task Routing | Task request + project context | Skill coordination | Map required skill sequence |
| Constraint Validation | New implementation requests | Approval/Feedback | Verify against documented standards |
| Context Refresh | Evolution of codebase | Updated project-context.md | Keep context current as project matures |
| Conflict Resolution | Conflicting requirements | Escalation | Document discrepancies between old/new rules |
What ships with it: 2 files
7.4 KB alongside SKILL.md
references/
- pipeline_example.md147 B
- project-context.md7.3 KB