Sk dynamic routing
Skill gustavo-meilus/superpipelines/plugins/superpipelines/skills/sk-dynamic-routing
Maps pipeline agent roles to intent-based model categories on Tier 1 (Claude Code). Use when a Tier 1 pipeline stage requires model assignment beyond the two-slot fast/deep abstraction — e.g., pure read-only audit agents, deep architectural planners, or visual-analysis roles. Non-CC tiers resolve models via platform_profile.model_tiers only; this skill must not be invoked on tier_1b/1c/1d/2.From its SKILL.md
npx -y skills add gustavo-meilus/superpipelines --skill sk-dynamic-routingAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 5 stars5 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.
SKILL.md
3.3 KB, 726 tokens by cl100k_base, as published. Nobody here has run it
Dynamic Model Routing — Intent-Based Capability Mapping
<overview> This skill is **Claude Code-scoped (tier_1 only)**. Superpipelines on Tier 1 maintains `claude-sonnet-4-6` as the baseline default for implementation workers (the Tier 1 resolution of `platform_profile.model_tiers.fast`). Certain specialized roles — fast audits, deep architectural planning, visual analysis — benefit from dynamic routing beyond the two-slot `fast`/`deep` abstraction. This skill defines the CC-specific categories and fallback chains for those overrides. Non-CC tiers do not consult this skill; they resolve models via `platform_profile.model_tiers` only. </overview> <glossary> <term name="Category">An intent-based tag that dictates the model requirement (e.g., `quick-audit`, `deep-plan`).</term> <term name="Fallback Chain">The sequence of alternative models if the primary is unavailable or rate-limited.</term> </glossary>Category Mappings
<categories_table>
| Category | Primary Model | Fallback Chain | Use Case |
|---|---|---|---|
default | claude-sonnet-4-6 | None | Implementation, general tasks, and task-execution. |
deep-plan | claude-opus-4-8 | gpt-5.4 -> sonnet-4-6 | High-stakes architectural planning (e.g., pipeline-architect). |
quick-audit | claude-haiku-4-5-20251001 | None | Fast, broad pattern matching and codebase grepping. |
visual | gemini-3.5-pro | gpt-5.4 | Tasks requiring image processing, UI screenshots, or diagram analysis. |
| </categories_table> |
Routing Protocol
<protocol> ### 1. EVALUATE INTENT - Determine the nature of the specific task or agent role. - Standard code implementation or functional review maps to category `default`.2. ASSIGN CATEGORY
- Roles exclusively concerned with planning, architecture, or deep conceptual alignment →
deep-plan. - Roles restricted to read-only utility (fast file searching, lint aggregation) →
quick-audit. - Roles that interpret screenshots or diagrams →
visual.
3. CONFIGURATION OVERRIDE
- When generating an agent or scaffold, the
model:field in the frontmatter is set to the primary model of the selected category. - A comment or meta-tag noting the category intent is added for future auditing. </protocol>
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most context ai engineering skills give in 726 tokens
Counted across 1,328 of the 2,349 authors here whose files we hold, read 2026-09-06
- Dispatch a fresh subagent for each taskin 76 of 1328, across 59 files
- Perform spec compliance review before code quality reviewin 44 of 1328, across 34 files
- Dispatch a final code reviewer after all tasksin 38 of 1328, across 26 files
- Answer subagent questions before allowing implementationin 36 of 1328, across 26 files
- Use the least powerful model capable of the taskin 33 of 1328, across 26 files
- Create a TodoWrite list for all tasksin 32 of 1328, across 22 files
- Perform a task review after each implementationin 31 of 1328, across 24 files
- Extract all tasks and context from the planin 29 of 1328, across 20 files
- Provide full task text to subagentsin 28 of 1328, across 20 files
- Use git worktrees for isolated workspacesin 25 of 1328, across 20 files
- Specify the model explicitly when dispatching a subagentin 23 of 1328, across 18 files
- Execute all tasks from the plan without stoppingin 21 of 1328, across 16 files
Said here and by no other author read
- Evaluate task intent before assigning a category
- Assign deep-plan for architectural planning roles
- Assign quick-audit for read-only utility roles
- Assign visual for image or diagram analysis
- Set model field to the category primary model
- Add meta-tag noting the category intent
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.