Stats
Actions
Available In
Tags
Plugin
prompt-engineering
Prompt & context engineering team — 3 agents (prompt-architect, prompt-implementation-engineer, prompt-reliability-engineer) that own the layer between the model and the app: prompt & context strategy (task decomposition, pattern selection across few-shot / CoT / decomposition / role, system-vs-user structure), the output-format contract (JSON mode, tool/function-calling schemas, few-shot curation, token budgeting), and prompt reliability (eval sets & regression, prompt versioning/CI, prompt-injection & jailbreak defense at the prompt layer). Provider-neutral. 4 skills, a 2-doc knowledge bank with 4 Mermaid decision trees + a dated 2026 reference, 5 best-practices, 2 templates. Seams: which model → ai-coding-model-guidance / claude-api; retrieval → ai-rag-engineering; eval at scale → llm-evaluation-engineering; adversarial testing → ai-red-teaming; the app → claude-app-engineering / backend-engineering. Requires ravenclaude-core@>=0.7.0.
What's Inside
Agents3
prompt-architect
/prompt-architect
Use to design prompt & context strategy: decompose a task into prompts, pick the pattern (few-shot / CoT / decomposition / role), engineer what goes in the context window, and set the output-format contract. NOT model choice (ai-coding-model-guidance) or retrieval design (ai-rag-engineering).
prompt-implementation-engineer
/prompt-implementation-engineer
Use to write and iterate the actual prompts: refine wording, curate few-shot examples, implement structured outputs (JSON mode / tool schemas), build templates, budget tokens. NOT the architecture (prompt-architect) or the eval harness (prompt-reliability-engineer).
prompt-reliability-engineer
/prompt-reliability-engineer
Use to make prompts trustworthy in production: build the eval/regression set, gate prompt changes in CI, version prompts, and defend against prompt injection & jailbreaks at the prompt layer. NOT the full offline eval program (llm-evaluation-engineering) or system red-teaming (ai-red-teaming).
Skills4
prompt-eval-and-regression
/prompt-eval-and-regression
Build the eval/regression set that gates prompt changes — labeled input/expected pairs over the hard cases, a scoring method (exact / schema-valid / rubric / LLM-judge with its caveat), a pass threshold, a CI gate with the model pinned, and injection cases. Reach for this before shipping a prompt, when a tweak silently broke other cases, or to defend against prompt injection. Pairs with structured-output-design.
context-window-engineering
/context-window-engineering
Decide what actually goes in the context window — static instructions vs just-in-time retrieval vs conversation history vs tools — with a per-section token budget and lost-in-the-middle-aware ordering. Reach for this when the window is bloating, quality is dropping as context grows, cost/latency is climbing, or you're unsure what to keep vs compress. Pairs with prompt-pattern-selection.
prompt-pattern-selection
/prompt-pattern-selection
Choose the prompting pattern — zero-shot, few-shot, chain-of-thought, decomposition/chaining, role framing, or self-consistency — by tracing the task against reliability need and token/latency cost. Reach for this when a prompt is inconsistent, when you're about to add examples 'just in case', or when one prompt is quietly doing several jobs. Pairs with structured-output-design.
structured-output-design
/structured-output-design
Make an LLM return reliably machine-parseable output — choose the enforcement mechanism (native JSON/schema mode, tool/function calling, constrained grammar, or prose+parser), define the schema, and build the parse/validate/repair path. Reach for this when output format drifts, when downstream code parses model output, or when 'return JSON' in prose keeps failing. Pairs with prompt-pattern-selection.
Stats
Version0.1.0
LanguageHTML
Stars4
Forks1
MaintenanceGood
LicenseMIT
Last Commit
Added
Available In
Safety Signals
Caution
Uses power tools
Uses Bash, Write, or Edit tools
'%20stop-opacity%3D'0.16'%2F%3E%3Cstop%20offset%3D'1'%20stop-color%3D'rgb(200%2C90%2C60)'%20stop-opacity%3D'0.03'%2F%3E%3C%2FlinearGradient%3E%3C%2Fdefs%3E%3Crect%20width%3D'320'%20height%3D'200'%20fill%3D'url(%23g)'%2F%3E%3Ccircle%20cx%3D'250'%20cy%3D'56'%20r%3D'92'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.06'%2F%3E%3Ccircle%20cx%3D'64'%20cy%3D'172'%20r%3D'58'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.05'%2F%3E%3C%2Fsvg%3E)
