Engineers prompts for LLMs and agents: instruction lines, structure, examples, named techniques, model and sampler choices, context budget, grounding, injection resistance, and proof that a change helped. Use when the user wants to tune a prompt or the standing instructions an agent runs under, get a model to follow a format or stop refusing, add few-shot examples, pick between reasoning and instruction models, set temperature or reasoning effort, shrink a bloated instruction set, ground answers on retrieved documents, harden a prompt against injection, organize a prompt library, rewrite an agent's tool or handoff sections, prompt image or video models, or check whether a prompt edit actually improved anything. Not for one-off chat messages, model training or fine-tuning, choosing an AI product to buy, or building attack payloads.
cp -r cryptoskill/skills/exchanges/anoscranel-ac-prompt-engineer .claude/skills/clawhub install anoscranel-ac-prompt-engineerCapabilities below are detected automatically by an open-source scanner that reads the skill's text and scripts (see how this is computed). Not measured means the scanner couldn't make a confident call — it is NOT a green check, and you should treat it as a possible red flag until a human or a stronger scanner has measured it.
analysis_only Phase 1 single-mode classification — multi-mode breakdown deferred to Phase 2.
External services this skill needs in order to work. The skill's behavior depends on these services being up, honest, and unchanged. Today we only show services we recognize from a curated list of ~50 well-known hosts (exchanges, RPC providers, data APIs); a complete dependency list — including every package, library, and binary the skill installs or imports — is on the roadmap.
anthropic.comopenai.comNo one has audited this skill yet. That is different from “audited and clean” — it just means no professional reviewer (a security firm, the CryptoSkill team, or a verified independent researcher) has signed off on it. There are no audit reports to read. How reviewer levels work →
SKILL.md → SOURCE.md → TRUST.auto.yaml → Browse directory →
Auto-generated by cryptoskill/extract-capabilities/0.3.1 · hosted-service list version 2026-09-06 · how this is computed