All skills
simota avatar

/magi

@35ffd55
by shingo imotasimota/agent-skills85 stars
15

Deliberating decisions and founder priorities through multi-perspective, named-expert, and YC-style advisory lenses. Use for verdicts, office hours, or expert critique; not implementation.

Use this Skill: https://skilld.dev/gh/simota/agent-skills/magi

This session only. Nothing lands on disk.

referencestrategy-simulationstrategy-monitoring.md

≈862 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Purpose: Track strategic execution after Magi delivers a plan. Use this for assumption monitoring, drift detection, health reporting, and OKR cascade design.

Contents

  • Monitoring workflow
  • Assumption states and alerts
  • Alignment score
  • Health report template

Strategy Monitoring

This absorbed the former Compass capability. Use it after Magi produces a roadmap, simulation, or strategic recommendation.

Workflow

ANCHOR -> TRACK -> ALERT -> CASCADE

Phase Goal Key actions
ANCHOR Establish the baseline Map assumptions to KPIs, define thresholds, capture the starting state
TRACK Observe execution and assumptions Compare actuals vs targets, check milestone progress, review assumption validity
ALERT Detect drift early Trigger WATCH/BREACH states and health alerts
CASCADE Connect strategy to work Translate strategy into company, team, and individual OKRs

Assumption Monitoring

Assumption -> Metric Mapping

| Assumption | Metric | Threshold | Status |
|-----------|--------|-----------|--------|
| "Market grows 15%/yr" | Industry revenue data | <10% = WATCH, <5% = BREACH | VALID |
| "Users prefer mobile" | Mobile usage % | <50% = WATCH | VALID |
| "Competitor doesn't enter" | Competitor announcements | Any entry = BREACH | VALID |

Assumption States

VALID -> WATCH -> BREACH
State Meaning Action
VALID Assumption still holds Continue as planned
WATCH Early warning threshold crossed Prepare a contingency
BREACH Assumption no longer holds Trigger strategy revision or Magi escalation

Alert Levels

Level Trigger Response
GREEN All KPIs on track and assumptions valid Continue monitoring
YELLOW 1-2 KPIs miss by <20%, or an assumption is in WATCH Investigate and prepare mitigation
RED Major KPI miss >20%, or an assumption breaches Escalate to Magi
BLACK Multiple breaches or core strategy invalidated Rebuild the strategy

OKR Cascade

Top-Down Translation

Strategy -> Company Objective -> Company KR -> Team OKR -> Individual KR

Example:

Company Objective: Be the market leader in X
  -> Revenue KR
  -> NPS KR
  -> Retention KR

Alignment Score

Alignment = KRs with a clear parent link / Total KRs

Target: >80%
Warning: <60%

Use low alignment as a sign of orphan work, weak ownership, or strategic drift.

Strategy Health Report

## Strategy Health Report — [Period]

### Overall Status: [GREEN / YELLOW / RED / BLACK]

### KPI Dashboard
| KPI | Target | Actual | Trend | Status |
|-----|--------|--------|-------|--------|
| [KPI] | [target] | [actual] | [↑↓→] | [GREEN/YELLOW/RED] |

### Assumption Monitor
| Assumption | Status | Last Checked | Notes |
|-----------|--------|-------------|-------|
| [assumption] | [VALID/WATCH/BREACH] | [date] | [context] |

### Drift Analysis
- Strategy drift score: [0-100]
- Areas of concern: [list]
- Recommended actions: [list]

### Next Review: [date]

Integration Rules

Signal Use
Repeated WATCH states tighten monitoring cadence
Any BREACH on a core assumption reopen the strategy in Magi or escalate to Magi
Alignment <60% re-cascade strategy into OKRs
Health RED/BLACK treat the roadmap as stale until reviewed

Source: SKILL.md on GitHub

1 alert13d5 checks · Risk HIGH
  • Gen Agent Trust Hub13d

    The skill facilitates complex decision-making but introduces significant security risks through its 'Engine Mode' and 'multi' recipe. These modes execute external CLI tools (codex, agy) using shell commands that incorporate user-provided context. Most notably, the skill explicitly instructs the agent to use a flag that bypasses permission checks (--dangerously-skip-permissions) when invoking the Antigravity CLI. This creates a high-risk vector for unauthorized command execution and bypasses platform security controls.

  • Socket13d

    No alerts

  • Snyk13d

    Risk: LOW · No issues

  • Runlayer6mo

    2/7 files flagged

  • ZeroLeaks5mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at 35ffd55. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 days ago.

Activeupdated 2 weeks ago

README badge

README badge for simota/agent-skills/magi