Energy Peak Finder

Turn several days of observation into a simple energy pattern review with likely peak windows, low windows, disruptors, task matching, and a one-week experim...

Security Scan

The skill's code and instructions are coherent with its description: it analyzes user-provided text to identify energy windows, asks for no credentials, and performs no network or privileged actions.

Purpose & Capability

Name/description (finding energy peaks from observation notes) matches the code and SKILL.md. The code only parses text, scores time blocks, reports disruptors, and produces a one-week experiment. There are no unrelated env vars, binaries, or surprising capabilities.

Instruction Scope

SKILL.md instructs the agent to analyze user-provided observations; handler.py implements that workflow. The runtime only reads the bundled SKILL.md file and the provided input text; it does not access calendars, wearables, external APIs, or other system paths.

Install Mechanism

No install specification or external downloads. This is effectively an instruction-only skill with small local Python code and tests, so nothing is pulled from the network or written to the system outside the skill package.

Credentials

The skill declares no required environment variables, credentials, or config paths and the code does not read environment secrets. All operations are local string processing; requested privileges are minimal and proportionate.

Persistence & Privilege

always is false and the skill does not modify other skills or system-wide settings. It performs no persistent installs or daemonization.

Assessment

This skill appears low-risk and does what its description promises: it analyzes text notes to suggest energy windows and a one-week experiment. Before installing or using it, consider: (1) It uses simple keyword heuristics — results are heuristic, not clinical; validate suggestions yourself. (2) Verify where the skill runs in your environment (local vs remote agent) because any user text you submit could be logged or transmitted by the hosting agent/platform — the skill itself contains no network calls. (3) Don't submit sensitive health or identifying information in observations you don't want stored or transmitted. (4) If you have concerns, review handler.py and run the included tests locally to confirm behavior.

Overview

Use this skill to spot when the user's energy actually supports focus, creativity, stamina, and recovery. It helps the user observe repeated peaks and troughs, separate sustainable energy from urgency or caffeine spikes, and match task types to the most realistic time windows.

This skill is descriptive only. It does not use wearables, calendars, biometrics, or analytics backends.

Trigger

Use this skill when the user wants to:

• find their best window for deep work
• understand daily energy slumps
• distinguish true energy from urgency or caffeine buzz
• match task type to time of day
• run a one-week experiment before locking in a schedule

Example prompts

• "Help me figure out when my energy peaks"
• "I keep doing hard work at the wrong time of day"
• "Map my focus windows from these notes"
• "Turn my energy observations into a weekly experiment"

Workflow

1. Review several days of energy, alertness, mood, hunger, and interruptions.
2. Divide the day into simple time blocks.
3. Identify repeated peaks, troughs, and false peaks.
4. Note confounders like sleep, meals, workouts, caffeine, and interruptions.
5. Match task types to each energy band.
6. Suggest a one-week experiment to validate the pattern.

Inputs

The user can provide any mix of:

• notes about mornings, afternoons, and evenings
• focus, creativity, stamina, or crash periods
• sleep quality, meals, caffeine, or workout context
• interruptions from work or family
• task types that feel easier or harder at different times
• notes from several days or one rough week

Outputs

Return a markdown energy review with:

• observation summary
• task matching by energy band
• hypotheses about what boosts or drains energy
• one seven-day experiment

Safety

• Use repeated observations when possible, not one unusually good or bad day.
• Separate energy from mood, panic, or deadline urgency.
• Keep recommendations flexible when family, health, or work obligations limit ideal scheduling.
• Do not turn the pattern into a fixed identity label too quickly.

Acceptance Criteria

• Return markdown text.
• Identify a best window, lowest window, and common disruptors.
• Match peak, medium, and low-energy tasks to usable time bands.
• End with a one-week experiment.