can-you-assist/registry/capabilities/capability.agents.cli-assistant.md

id, name, summary, owner, status, domain, tags, maturity, external_evidence, discovery, availability, relations, evidence, consumer_guidance, promotion_history

id	name	summary	owner	status	domain	tags	maturity	external_evidence	discovery	availability	relations	evidence	consumer_guidance	promotion_history
capability.agents.cli-assistant	Console-Native LLM Assistant (cya)	Console-native, backend-agnostic assistant CLI that expresses user intent in natural language and returns safe, explainable, context-aware help.	can-you-assist	draft	agents	cli assistant llm safety	discovery availability current target confidence rationale D2 D4 medium README documents the MVP slice (CYA-WP-0001), the LLMAdapter seam, and the rule-based risk-classification safety layer; no separate INTENT/SCOPE file found. current target confidence rationale A2 A3 medium Installable today via `pip install -e .`; ships a working CLI (`cya "..."`, `--explain-context`) with a FakeLLMAdapter default and optional real llm-connect backend.	completeness reliability level confidence basis satisfied_expectations broken_expectations out_of_scope_expectations C1 low scope_vs_intent_and_consumer_expectations natural-language CLI entry point context-explain mode mandatory confirmation for destructive/privileged/mass-edit/network actions level confidence basis known_reliability_risks R0 low consumer_quality_signals MVP slice only; real llm-connect backend optional/not always configured	intent includes excludes assumptions use_cases research_memos Let users express intent in natural language from the terminal and receive safe, explainable, context-aware help, without owning LLM inference or memory storage itself. CLI orchestration and UX rule-based risk classification and confirmation gating LLMAdapter seam to llm-connect LLM inference (owned by llm-connect) memory storage (owned by phase-memory)	current_level target_level current_artifacts target_artifacts consumption_modes A2 A3 `cya` CLI package, pip-installable cli	depends_on supports related_to	documentation tests consumer_feedback bug_reports incidents README.md tests/	recommended_for not_recommended_for known_limitations shell-based workflows wanting a safety-gated natural-language assistant needs beyond the first MVP slice (CYA-WP-0001) first narrow MVP slice; FakeLLMAdapter is the default, real backend is optional

Console-Native LLM Assistant (cya)

Overview

cya is the CLI surface for the capabilities domain: it owns orchestration, UX, and a safety layer, and talks to llm-connect only through a stable LLMAdapter boundary, keeping memory under phase-memory.

Assessment notes

Discovery

README documents the MVP slice (CYA-WP-0001), the LLMAdapter seam, and the rule-based risk-classification safety layer; no separate INTENT/SCOPE file found.

Availability

Installable today via pip install -e .; ships a working CLI (cya "...", --explain-context) with a FakeLLMAdapter default and optional real llm-connect backend.

Completeness

First-pass honest assessment from the REUSE-WP-0017 coverage campaign (reuse-surface). No external consumer feedback exists yet; levels reflect scope-vs-intent documentation quality, not internal code quality.

Reliability

No production consumer telemetry exists yet; reliability level is intentionally conservative pending REUSE-WP-0019 reuse-telemetry evidence.

Promotion checklist

• ID follows capability.<domain>.<name> pattern
• Maturity enums match specs/CapabilityMaturityStandard.md
• external_evidence is populated separately from maturity
• Relations reference valid capability IDs (none yet)
• Index entry added in registry/indexes/capabilities.yaml