when-using-sparc-methodology-use-sparc-workflow
About
This skill orchestrates structured SPARC (Scope, Plan, Act, Review, Consolidate) workflows for developers, enforcing gated checkpoints and explicit confidence ceilings throughout the process. Use it for stage-gated problem-solving and evidence-backed reviews, but not for ad-hoc, single-pass tasks. It ensures intent capture and confidence-aware delivery within a defined operational framework.
Quick Install
Claude Code
Recommended/plugin add https://github.com/DNYoussef/context-cascadegit clone https://github.com/DNYoussef/context-cascade.git ~/.claude/skills/when-using-sparc-methodology-use-sparc-workflowCopy and paste this command in Claude Code to install this skill
Documentation
STANDARD OPERATING PROCEDURE
Purpose
Run SPARC methodology end-to-end with clear intent capture, stage gates, evidence-backed reviews, and confidence-aware delivery.
Trigger Conditions
- Positive: structured problem solving using SPARC, stage-gated delivery, retrospectives, consolidation of learnings.
- Negative: ad-hoc single-pass tasks, prompt-only edits (route to prompt-architect), or new skill weaving (route to skill-forge).
Guardrails
- Skill-Forge structure-first: maintain
SKILL.md,examples/,tests/; addresources//references/or log remediation tasks. - Prompt-Architect hygiene: capture HARD/SOFT/INFERRED constraints per SPARC stage, keep English-only outputs, and declare ceilings.
- Stage safety: set entry/exit criteria for Scope/Plan/Act/Review/Consolidate, enforce registry usage, and keep hook latency budgets.
- Adversarial validation: challenge assumptions each stage, run COV, and document evidence and deltas.
- MCP tagging: store SPARC runs with WHO=
sparc-workflow-{session}and WHY=skill-execution.
Execution Playbook
- Scope: define objective, constraints, and success metrics; confirm inferred assumptions.
- Plan: design approach, assign owners, and set timelines plus rollback points.
- Act: execute tasks with monitoring, TodoWrite updates, and guardrails.
- Review: validate outcomes, run adversarial checks, and log evidence.
- Consolidate: capture learnings, decisions, and next actions.
- Delivery: summarize SPARC path, evidence, risks, and confidence ceiling.
Output Format
- SPARC stage summary with constraints and decisions.
- Evidence log, risks, and follow-ups.
- Confidence:
X.XX (ceiling: TYPE Y.YY) - rationale.
Validation Checklist
- Structure-first assets present or ticketed; examples/tests reflect SPARC flow.
- Stage gates and rollback points defined; registry and hooks validated.
- Adversarial/COV runs stored with MCP tags; confidence ceiling declared; English-only output.
Completion Definition
Workflow is done when SPARC stages complete with evidence, risks are owned, learnings captured, and MCP logs tagged for reuse.
Confidence: 0.70 (ceiling: inference 0.70) - SPARC workflow doc rewritten with skill-forge scaffolding and prompt-architect constraint/confidence discipline.
GitHub Repository
Related Skills
sglang
MetaSGLang is a high-performance LLM serving framework that specializes in fast, structured generation for JSON, regex, and agentic workflows using its RadixAttention prefix caching. It delivers significantly faster inference, especially for tasks with repeated prefixes, making it ideal for complex, structured outputs and multi-turn conversations. Choose SGLang over alternatives like vLLM when you need constrained decoding or are building applications with extensive prefix sharing.
Algorithmic Art Generation
MetaThis skill helps developers create algorithmic art using p5.js, focusing on generative art, computational aesthetics, and interactive visualizations. It automatically activates for topics like "generative art" or "p5.js visualization" and guides you through creating unique algorithms with features like seeded randomness, flow fields, and particle systems. Use it when you need to build reproducible, code-driven artistic patterns.
business-rule-documentation
MetaThis skill provides standardized templates for systematically documenting business logic and domain knowledge following Domain-Driven Design principles. It helps developers capture business rules, process flows, decision trees, and terminology glossaries to maintain consistency between requirements and implementation. Use it when documenting domain models, creating business rule repositories, or bridging communication between business and technical teams.
huggingface-accelerate
DevelopmentHuggingFace Accelerate provides the simplest API for adding distributed training to PyTorch scripts with just 4 lines of code. It offers a unified interface for multiple distributed training frameworks like DeepSpeed, FSDP, and DDP while handling automatic device placement and mixed precision. This makes it ideal for developers who want to quickly scale their PyTorch training across multiple GPUs or nodes without complex configuration.