skills.rest
Kgan01
Kgan01COMMUNITY
Explore all skills by this author →
GitHub

time-perception

Inject timestamps and elapsed time into LLM prompts with JSONL logging.

6|Updated Apr 7, 2026
Search Tags:#logging#hooks#llm#prompts#time-tracking#time-context
One-click install
npx skills add https://github.com/Kgan01/ghengis-skills --skill time-perception
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: time-perception
Source: https://github.com/Kgan01/ghengis-skills/tree/main/plugins/ghengis-skills/skills/time-perception
Command: npx skills add https://github.com/Kgan01/ghengis-skills --skill time-perception

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Time awareness for long-running LLM workflows, enabling timing data to be injected into prompts and tracked across projects.

Core Features & Use Cases

  • Time-context injection: automatically append a compact timestamp and elapsed time to every prompt.
  • Global and per-project logs: store time events in time-log.jsonl, task-durations.jsonl, and per-project files for later analysis.
  • Portable API: includes a Python TimeContext module to wrap LLM calls and expose summaries.

Quick Start

Stamp your prompts to enable time awareness and watch Claude inject a compact time context into every reply.

Frequently Asked Questions about time-perception

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I track elapsed time across multiple LLM prompt sessions?▼

Injecting time context into LLM prompts involves appending a compact timestamp and elapsed time data to every prompt, allowing the model to understand time awareness during long-running workflows and multi-session tasks.

How do I inject time context into LLM prompts automatically?▼

Injecting time context into LLM prompts involves appending a compact timestamp and elapsed time data to every prompt, allowing the model to understand time awareness during long-running workflows and multi-session tasks.

What is the best way to log time tracking data for separate AI projects?▼

Yes, you can use a portable Python TimeContext module to wrap LLM calls, which handles time-context injection and exposes timing summaries without requiring external dependencies beyond the standard environment.

Can I use a Python module to measure LLM task durations?▼

Yes, you can use a portable Python TimeContext module to wrap LLM calls, which handles time-context injection and exposes timing summaries without requiring external dependencies beyond the standard environment.

Does time tracking for LLM workflows require any external dependencies?▼

Time tracking for LLM workflows requires no external dependencies, relying solely on built-in hooks like UserPromptSubmit and Stop to capture timing events and write them to local JSON and JSONL data files.

How do hooks measure project switches during long-running AI workflows?▼

Hooks measure project switches by capturing UserPromptSubmit and Stop events to calculate elapsed time, logging the durations to time-data.json and per-project JSONL files to map out workflow transitions.

Related Skills

Explore More Software Engineering Skills→
pur3v4d3rpur3v4d3r
6

claude-settings-expert

Configure Claude Code settings.json, permissions, sandbox, environment variables, and hooks.

Community
Advanced
OpenSourceSamOpenSourceSam

finish-work

Enforce minimum work durations before allowing AI agent task completion.

Community
Intermediate
qiushibangqiushibang

planning-with-files

Persist task plans, findings, and progress in markdown files across sessions.

Community
Advanced
chiptoe-svgchiptoe-svg

add-dashboard

Add a local monitoring dashboard for NanoClaw deployments.

Community
Intermediate