| Skill | Added | Review |
|---|---|---|
script.automate agentsociety/custom/skills/script.automate/SKILL.md Automate a small repetitive computer task. | — | |
shop.run agentsociety/custom/skills/shop.run/SKILL.md Run ordinary shop work and customer service. | — | |
sketch.draw agentsociety/custom/skills/sketch.draw/SKILL.md Draw or sketch a quiet observation. | — | |
skill-creator jiuwenclaw/jiuwenclaw/resources/agent/jiuwenclaw_workspace/skills/skill-creator/SKILL.md Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | 68 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: 753f067 | |
skill-gen-4-enterprise-doc jiuwenclaw/jiuwenclaw/resources/agent/jiuwenclaw_workspace/skills/skill-gen-4-enterprise-doc/SKILL.md Turn SOPs, URLs, or stated intent into an installed skill package. Use when the user asks to generate a skill from a document, link, or workflow. Follow SKILL.md, reference/sop-structure-pipeline.md, and reference/generator-worker-spec.md; finish by promoting the draft into the runtime skills directory (see reference/operator-playbook.md) in the same turn. | 64 Impact — No eval scenarios have been run Securityby Medium Suggest reviewing before use Version: 753f067 | |
skvm-general jiuwenclaw/jiuwenclaw/resources/agent/jiuwenclaw_workspace/skills/skvm-general/SKILL.md Drive the skvm CLI on behalf of a user to profile models, AOT-compile skills, run skill-assisted tasks, run benchmarks, and manage compiled proposals. Trigger when the user asks to "profile", "aot-compile", "bench", "run a single ad-hoc task with a skill", or asks about skvm proposals. Do NOT trigger for `jit-optimize` or when the user wants to optimize/improve a skill — use the sibling `skvm-jit` skill instead. | 76 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 753f067 | |
skvm-jit jiuwenclaw/jiuwenclaw/resources/agent/jiuwenclaw_workspace/skills/skvm-jit/SKILL.md Trigger `skvm jit-optimize` with post-task evidence so it generates a reviewable optimization proposal for a skill. Use after finishing a task that was driven by any skill (not just SkVM-compiled ones) when the outcome was a failure, was partial, or the skill's instructions clearly caused confusion or an unnecessary detour. Clean successful runs usually do not need an optimization pass. For general skvm usage (profile/aot-compile/bench/proposals), use the sibling `skvm-general` skill instead. | 68 Impact — No eval scenarios have been run Securityby Critical Do not install without reviewing Version: 753f067 | |
social.matchmake agentsociety/custom/skills/social.matchmake/SKILL.md Connect two people who may help each other. | — | |
social.reply agentsociety/custom/skills/social.reply/SKILL.md Reply to a recent direct or group message without inventing unrelated movement. | — | |
stall.run agentsociety/custom/skills/stall.run/SKILL.md Run a market stall and handle daily stall tasks. | — | |
story.localpast agentsociety/custom/skills/story.localpast/SKILL.md Share a story from the local past. | — | |
teamskill-creator jiuwenclaw/jiuwenclaw/resources/agent/jiuwenclaw_workspace/skills/teamskill-creator/SKILL.md Creates, converts, or modifies Teamskills — the multi-role extension of the Skills standard (specialized roles + workflow + bind constraints). Use when the user wants to author a multi-role agent team, convert a single-agent skill into one, or refactor an existing team. Do NOT use for single-agent Skills — use create-skill instead. | 64 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 753f067 | |
tools.repair agentsociety/custom/skills/tools.repair/SKILL.md Inspect and repair a practical tool or device. | — | |
ui_e2e jiuwenclaw/tests/ui_e2e/SKILL.md 运行 JiuwenClaw Web UI 端到端测试并收集截图、日志、report.md、report.json。用于验证 Todo 和 Cron Web UI 流程、复现浏览器交互问题、选择运行解释器、准备 Playwright 环境,或返回可操作的失败证据时。 | — | |
vegetable.source agentsociety/custom/skills/vegetable.source/SKILL.md Source vegetables and practical food supplies. | — | |
writing.feedback agentsociety/custom/skills/writing.feedback/SKILL.md Give clear feedback on a piece of writing. | — | |
writing.hand agentsociety/custom/skills/writing.hand/SKILL.md Write something by hand with care and attention. | — | |
youth.communicate agentsociety/custom/skills/youth.communicate/SKILL.md Communicate with youth in a patient supportive way. | — |