skills
anthropics
Public repository for Agent Skills
REVIEW SCORECARD
✓ 无Risky检出 · 自动化扫描结果仅供参考,非官方背书
AI DEEP REVIEW
Well-documented agent skill with strong benchmark claims and broad provider support, but installs via a tarball URL and
README documents a structured CLI with doctor/uninstall/help commands, versioned releases, and a source-install path, but no CI, test suite, or repo structure is shown to confirm engineering rigor.
Installation uses `npm install -g` from a GitHub release tarball URL and requires Node, Python with PyYAML, and Bash, but no plaintext secrets or excessive permissions are evident, so a neutral score applies given limited information.
It targets a real and common pain point in agentic coding (task failures) and claims a measured reduction from 29 to 16 failures on Terminal-Bench 2.1, though the README itself notes the ~3x time and ~2x token cost are unmeasured estimates.
Last updated 2026-09-09, not archived, at v2.0.0 with 1085 stars and an active releases page, indicating ongoing maintenance.
README provides install steps, requirements, a support table with tested versions for 11 agents, benchmark details with stated evidence boundaries, and translations into five languages, though the install command field is marked unknown.
Generated by AI after reading the project README, as a decision aid; neutral scores are given when information is thin. Not an official endorsement.
正在读取 GitHub README...
README 暂时无法读取。
前往仓库PROJECT TOPICS
VALIDATION LADDER
FAQ
Autoprompt is a coding-agent skill that cuts failures by 45% on agentic coding tasks.
autoprompt-skill has 1,085 stars and 70 forks on GitHub, last updated 2026-09-09.
autoprompt-skill is distributed under the MIT license.
autoprompt-skill is listed in the DSH Universe directory as a tool for DeepSeek Harness. This plugin is listed in the DSH Universe directory and covered by its validation pipeline.
CLASSIFICATION EVIDENCE
System reads GitHub Topics first, then compares against the in-site category dictionary and word-root rules. Current match:agent-skills。