Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →hashgraph-online/prompt-pipeline
How to design the numbered prompt pipeline that drives Hunt phases in Cavekit. Covers greenfield 3-prompt patterns, rewrite 6-9 prompt patterns, shared principles, prompt engineering best practices, task templates, and time guards. Trigger phrases: "prompt pipeline", "design prompts for SDD", "create Hunt prompts", "pipeline prompts", "how many prompts do I need"
Passed 18 of 20 test cases with the skill, and 5 of 20 without it.
and 31 more in the full report
15 fixed5 passed either way2 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.
In the 3-prompt greenfield pipeline, what directory paths must Prompt 002 read from and write to when generating implementation plans?
| Checked | Without skill | With skill |
|---|---|---|
| Reads specification context from context/kits/ | Missed | Passed |
| Reads implementation tracking from context/impl/ | Missed | Passed |
| Writes generated plan files to context/plans/ | Missed | Passed |
The instructions your model reads when the skill loads.
The prompt pipeline is the engine of SDD. Each numbered prompt drives one phase of the Hunt lifecycle (Spec, Plan, Implement, Iterate, Monitor). Prompts are structured markdown files that instruct an AI agent to perform a specific phase, with detailed information delegated to specs, plans, and reference materials.
Core principle: Prompts should be as lightweight and systemic as possible. They define the process, not the content -- specs and plans hold the content.
For new projects starting from reference materials (PRDs, language specs, design docs, research).
Pipeline Flow:
refs/ ──> [001] ──> specs/ ──> [002] ──> plans/ ──> [003] ──> src/ + tests/
^ |
| |
+── impl/ <───────────+
(bidirectional flow)
| Prompt File | Lifecycle Stage | Reads From | Writes To | Description |
|---|---|---|---|---|
001-generate-specs-from-refs.md | Spec | context/refs/ | context/kits/ | Reads reference materials, decomposes into domain-specific specs with cross-references and testable acceptance criteria |
002-generate-plans-from-specs.md | Plan | context/kits/ + context/impl/ | context/plans/ | Reads specs plus implementation progress, creates framework-specific plans with feature dependencies, test strategies, and acceptance criteria |
003-generate-impl-from-plans.md | Implement | context/plans/ + context/kits/ | src/, tests/, context/impl/ | Implements the highest-priority unblocked work from plans, runs tests, updates implementation tracking |
context/refs/ and produces context/kits/.context/impl/). It produces plans that sequence the work.context/impl/ with progress.# 001: Generate Specs from Reference Materials
## Runtime Inputs
test cases passed, vs 5 / 20 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.