cli-agent-sp ec · Agent Skills
出典を確認した実質的な文書を持つ Skill が 9 件あります。カードを開くと原文、パッケージ内容、導入方法を確認できます。
cli-agent-audit
Autonomous end-to-end CLI audit pipeline. Downloads and installs the CLI non-interactively, onboards it, scores proactive readiness, evaluates all Critical failure modes, and generates the full report bundle (dev, agent-dev, runtime, issues, index, LinkedIn post). Single command, zero human steps required in the happy path.
- 1時間の導入数
- 1
- GitHub Stars
- 9
- 更新日
- 8月7日
cli-agent-diagnose
Classify a failed agent CLI tool call against the CLI Agent Spec §N failure taxonomy. Given a failed command with stdout, stderr, and exit code, identifies the matching failure mode, returns an actionable workaround, and produces a memory string and skill patch to prevent recurrence. Use when a CLI invocation fails and you need to understand why and how to work around it.
- 1時間の導入数
- 1
- GitHub Stars
- 9
- 更新日
- 8月7日
cli-agent-evaluate
Evaluate a CLI tool against a single CLI Agent Spec failure mode. Runs the failure mode's check, scores 0–3, and provides an applicable agent workaround if the score is below 3. Use this for targeted single-failure-mode evaluation. For multi-failure-mode evaluation use cli-agent-evaluate-batch.
- 1時間の導入数
- 1
- GitHub Stars
- 9
- 更新日
- 8月7日
cli-agent-evaluate-batch
Evaluate a CLI tool against multiple CLI Agent Spec failure modes in one run. Accepts a severity filter, part number, or an explicit list of §N identifiers. Skips already-evaluated failure modes (resumable). Emits a scorecard table when done.
- 1時間の導入数
- 1
- GitHub Stars
- 9
- 更新日
- 8月7日
cli-agent-implement
Guide implementing the CLI Agent Spec specification in a CLI framework or tool. Audits command naming against Unix conventions, walks through requirements tier-by-tier (REQ-F → REQ-C → REQ-O), generates language-specific schema types, and verifies acceptance criteria. Use when building or extending a CLI framework to support AI agent orchestration.
- 1時間の導入数
- 1
- GitHub Stars
- 9
- 更新日
- 8月7日
cli-agent-onboard
Onboard a CLI tool for agent evaluation — reads agent docs, detects OS, runtime, toolchain, and binary, discovers non-interactive flags and config. Saves the result as the CLI environment profile for reuse by cli-agent-evaluate and other skills. Run once per CLI before starting evaluations.
- 1時間の導入数
- 1
- GitHub Stars
- 9
- 更新日
- 8月7日
cli-agent-readiness
Score how proactively agent-ready a CLI is across five dimensions — documentation quality, self-description, pre-built integrations, setup reproducibility, and workflow coverage. Complements cli-agent-evaluate-batch (which scores what breaks) with a positive readiness score (what the CLI provides). Requires CLI access and an environment profile from cli-agent-onboard.
- 1時間の導入数
- 1
- GitHub Stars
- 9
- 更新日
- 8月7日
cli-agent-report
Generate a perspective-specific report from existing CLI evaluation findings. Five modes — dev (fix list for CLI authors), agent-dev (integration guide for agent builders), runtime (operational brief for AI agents), issues (concrete bugs and gaps an agent will hit), all (runs all four, saves to files, generates an index and a LinkedIn post). Requires findings from cli-agent-evaluate or cli-agent-evaluate-batch.
- 1時間の導入数
- 1
- GitHub Stars
- 9
- 更新日
- 8月7日
validate-links
Validate all cross-links in the CLI Agent Spec specification — broken file links, missing schema sections, and schema↔requirement symmetry. Use when files have been added or edited, or to check the project is internally consistent.
- 1時間の導入数
- 1
- GitHub Stars
- 9
- 更新日
- 8月7日
