Skills for Real Engineers. Straight from my .agents directory.
39 skills
skill-upper
Agent skill from
Capture and review Agent Skill observations, and create, run, diagnose, or iteratively improve Skill evaluations (evals) with the skill-up CLI. Use when the user asks to record explicitly attributed Skill usage or feedback; review observations or user-supplied traces/transcripts; turn an approved observation into a regression case; evaluate, test, regress, verify, fix, improve, iterate, or evolve a Skill; add or strengthen eval cases; write eval.yaml/case.yaml; run skill-up run/validate/list-cases/report/import/init; or migrate from Anthropic evals.json. Plugin observation capture/review require either the Codex skill-up plugin or an observer-enabled DSH skill-up plugin. User-supplied external evidence can be reviewed without a plugin; evaluation remains multi-engine.
How to install skill-upper
install skill-upper
# install the skill-up pack with the skills CLI
npx skills add alibaba/skill-up# or add only this skill to Claude Code: copy the folder
skills/skill-upper/
# into
~/.claude/skills/skill-upper/ (all projects)
.claude/skills/skill-upper/ (one project)
1# use-skill-up-cli23Help the user evaluate and evolve Agent Skills through the `skill-up` CLI.45Manual: <https://alibaba.github.io/skill-up/>67## Language Policy89**Default to English when responding to the user. If the user writes in Chinese (or any other language), switch to that language and stay consistent with the user's input throughout the session.**1011Detection rules (highest priority first):12131. The user explicitly specifies a language in the current message (e.g. "answer in English" or "reply in Chinese") → follow the user's instruction.142. The natural language used in the user's current message → match it.153. None of the above → use English (default).1617Regardless of the response language, technical identifiers in this SKILL — CLI commands, `eval.yaml` / `case.yaml` field names, report field names, etc. — MUST stay in their original English form. Do not translate them.1819### Language Rules for Generated Artifacts2021Use the user's current language for replies, newly authored explanatory prose,22and YAML comments. Preserve the language and semantics of test inputs, expected23output literals, identifiers, commands, paths, and existing regression cases.24Do not translate a deterministic assertion merely because the conversation25language changed. When testing localized behavior, keep the original business26text even in an English conversation.2728Treat `assets/*.tmpl` as structural references: adapt placeholder prose and29…
Excerpt shown under the repository's Apache-2.0 license.
More skills in skill-up
Keep exploring
Similar skill repositories
An agentic skills framework & software development methodology that works.
15 skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
CC1 skill
Public repository for Agent Skills
20 skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
CCCU6 skills
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
CCCXGHGM+135 skills