EVA / prompt library
Each prompt is a self-contained artefact: metadata, body, examples, evals, and shell verbs in one place. 11 prompts across harness, rag, domain, and writing patterns.
ready · 1
tested · 2
-
handbook-section-generatorv0.5.0 writingGenerate a Handbook Section from Notes
Synthesises bullet-form notes into a named handbook section in a chosen voice; surfaces contradictions.
-
orchestrate-multistepv0.3.0 harnessMulti-step Orchestration Executor (autopilot-shaped)
Executes one step of a JSON plan; emits strict-JSON handoff with predict/wake/learn fields per autopilot loop semantics.
draft · 8
-
impeccable-handbook-generatorv0.1.0 writingImpeccable Handbook Generator
Inspect a freshly /impeccable-onboarded project and emit a project-specific IMPECCABLE_HANDBOOK.md plus skeleton sidecar.
-
impeccable-harness-executorv0.2.0 harnessImpeccable Harness Executor
Deterministic orchestrator that drives an IMPECCABLE_HANDBOOK.md to completion via Claude Code Task() sub-agents.
-
rag-chunk-rerankerv0.1.0 ragRAG Chunk Reranker (LLM-as-reranker with MMR diversity)
Reranks candidate chunks against a query, balancing relevance and MMR-style diversity; preserves input ids.
-
rag-context-synthesizerv0.1.0 ragRAG Context Synthesizer (cited answer with coverage report)
Composes a grounded answer from id-keyed chunks; cites by id; refuses on insufficient evidence.
-
rag-evidence-validatorv0.1.0 ragRAG Evidence Validator (faithfulness · groundedness · citation audit)
Audits a RAG answer against its source chunks; pairs each claim to supporting ids and flags unsupported spans.
-
rag-query-rewriterv0.1.0 ragRAG Query Rewriter (expand · decompose · HyDE)
Rewrites a user query for retrieval — expansion, decomposition, or HyDE — emitting a strict JSON plan.
-
repo-dag-executorv0.2.0 harnessRepo Audit DAG Executor
Drive a shell-script harness that dispatches Claude Code Task sub-agents against an audit DAG until every node verifies green.
-
repo-dag-generatorv0.1.0 writingRepo Audit DAG Generator
Audit a repository and emit state.md + graph.md + per-node prompts/*.md — the execution plan for a fleet of agents to finish the repo.
no prompts match.