Skip to content
Back to skills

Daily Advisor

ASecurity

Answers "what should I do today?" with a readiness-aware decision. Load when the user asks about today's workout, today's training, whether to go hard or easy, or when /coach-today runs.

  • 4 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added May 26, 2026
ai-agentsgo

Security analysis

A100/100

Scanned May 27, 2026

npx -y skills add ace4seven/GC-MCP --skill daily-advisor --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Daily Advisor?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Daily Advisor
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ace4seven-daily-advisor/badge)](https://www.skillsdirectory.com/skills/ace4seven-daily-advisor)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: daily-advisor
description: Answers "what should I do today?" with a readiness-aware decision. Load when the user asks about today's workout, today's training, whether to go hard or easy, or when /coach-today runs.
---

# Daily advisor — what should I do today

Follow this decision tree every time. Always output one primary recommendation + one fallback.

## Steps

1. **Read state** — call `coach_state` for `profile`, `weekly_plan`, `flags`, and `daily_log` (no date → last 7 days).
2. **Get readiness** — call `coach_compute_readiness_synthesis` for today.
3. **Cross-check yesterday** — what was the session? What was the RPE? Any soreness mention?
4. **Match against the weekly plan** — what was scheduled?
5. **Apply flag constraints** — never prescribe past an active flag.

## Decision logic

- `recommendation_tier = go_hard` AND no flags AND yesterday wasn't hard → run today's scheduled session as planned.
- `tier = go_hard` AND yesterday was hard → reduce intensity 1 step (e.g., threshold → tempo).
- `tier = moderate` → swap quality work for endurance-volume; push quality to the next high-readiness day.
- `tier = easy` → easy Z2 only, by time not by distance. Mention recovery levers from `recovery-advisor`.
- `tier = rest` → no structured session. Active-recovery alternatives (mobility, walk, sleep).
- Active flag → constrain by the flag's `Action` line. The flag wins.

## Output shape

> *Readiness <N>. <Primary driver and brief reason>. Plan said <X>; recommendation: <Y>. Fallback if <constraint>: <Z>. <Optional: flag note if changed>.*

If the recommendation diverges from the plan, call `coach_state` `write` `weekly_plan` to update the markdown.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.