用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/vamseeachanta/workspace-hub --skill usage-tracker-1-basic-usage-logging命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
Write outbound email and external messages in Vamsee Achanta's voice — a subtle offer to help, never bold or rash claims. Load before drafting ANY email, LinkedIn/Collide reply, proposal note, or outreach sent under his name.
Save/publish analysis or computation results from ANY ecosystem repo to Hugging Face as a queryable, viewer-renderable dataset. Use when the user wants to "save results to hugging face", "publish dataset to HF", "hugging face data saving", "save analysis results", "hf dataset", "make results queryable", or "render via datasets-server API". Reshapes nested results into flat parquet tables, writes a dataset card with a viewer `configs:` block and provenance, applies license/public-vs-private routing, enforces a domain data-quality gate (faithful-to-source != correct), publishes to `aceengineer/<repo>-<projection>`, and verifies via the datasets-server API.
Clone, create, fork, configure, and manage GitHub repositories. Manage remotes, secrets, releases, and workflows. Works with gh CLI or falls back to git + GitHub REST API via curl.
正在显示 SKILL.md
基于 SOC 职业分类
| name | usage-tracker-1-basic-usage-logging |
| description | Sub-skill of usage-tracker: 1. Basic Usage Logging (+1). |
| version | 1.0.0 |
| category | _core |
| type | reference |
| scripts_exempt | true |
Pipe-delimited log format for easy parsing:
#!/bin/bash
# ABOUTME: Basic usage tracking with timestamped logs
# ABOUTME: Pattern from workspace-hub check_claude_usage.sh
# Configuration
USAGE_LOG="${HOME}/.workspace-hub/usage.log"
USAGE_DIR="$(dirname "$USAGE_LOG")"
# Ensure directory exists
mkdir -p "$USAGE_DIR"
# Initialize log if needed
if [[ ! -f "$USAGE_LOG" ]]; then
cat > "$USAGE_LOG" << EOF
# Usage Log
# Format: TIMESTAMP|CATEGORY|ITEM|VALUE|METADATA
# Created: $(date)
EOF
fi
# Log a usage event
log_usage() {
local category="$1"
local item="$2"
local value="${3:-1}"
local metadata="${4:-}"
local timestamp=$(date '+%Y-%m-%d_%H:%M:%S')
echo "${timestamp}|${category}|${item}|${value}|${metadata}" >> "$USAGE_LOG"
}
# Examples
log_usage "model" "opus" "1" "task:architecture"
log_usage "model" "sonnet" "1" "task:implementation"
log_usage "api" "requests" "100" "endpoint:/data"
log_usage "tokens" "input" "2500" "model:opus"
Aggregate usage by time period:
#!/bin/bash
# ABOUTME: Usage aggregation functions
# ABOUTME: Summarize by day, week, month
# Get usage for a specific period
get_usage_period() {
local period="$1" # today, week, month
local category="${2:-}"
local filter_date
case "$period" in
today)
filter_date=$(date +%Y-%m-%d)
;;
week)
filter_date=$(date -d '7 days ago' +%Y-%m-%d)
;;
month)
filter_date=$(date -d '30 days ago' +%Y-%m-%d)
;;
*)
filter_date=$(date +%Y-%m-%d)
;;
esac
if [[ -n "$category" ]]; then
grep "$filter_date" "$USAGE_LOG" 2>/dev/null | grep "|${category}|" || true
else
grep "$filter_date" "$USAGE_LOG" 2>/dev/null || true
fi
}
# Count usage by category
count_by_category() {
local period="$1"
get_usage_period | \
awk -F | \
-k2 -nr
}
() {
period=
category=
get_usage_period | \
awk -F | \
-k2 -nr
}
() {
period=
category=
get_usage_period | \
awk -F
}