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.

referencerecipes-index.md

≈664 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Magi Recipe Registry

The full Recipe table for magi. magi/SKILL.md carries only the dispatch allowlist; this file holds what is needed to execute a Recipe — activation condition and the files to read first.

Read this when a subcommand matched and you need its row, or when scanning what Recipes exist at all.


Recipe Subcommand Default? When to Use Read First
Go/No-Go Decision decide ✓ Final adoption verdict (release readiness, feature approval, quality gate). KNOWLEDGE task — evidence at FRAME, then independent voting reference/decision-domains.md
Tradeoff Analysis tradeoff X vs Y comparison. Both options explicit; the three lenses evaluate independently with weighted aggregation reference/decision-domains.md
Architecture Arbitration arbitrate Design option arbitration (2+ options). Engine Mode auto-detected at low reversibility + high impact reference/deliberation-framework.md
Strategic Direction strategic Long-term strategy and roadmap. REASONING task — independent voting; Sophia weights long-term impact reference/decision-domains.md
Six Thinking Hats sixhat Parallel-thinking across White/Red/Black/Yellow/Green/Blue modes before voting; Black always paired with equal-time Yellow reference/six-thinking-hats.md
Devil's Advocate devil Red-team stress test on high-stakes irreversible proposals; mandatory on 3-0. Rotated DA, 3-7 ranked objections, addressed/partial/unaddressed scoring reference/devils-advocate.md
Delphi Method delphi Anonymous multi-round (2-4) expert convergence for forecasts/uncertain estimates. Bimodal kept as stable disagreement, not flattened reference/delphi-method.md
Advisory advisor Founder family (office-hours, triage, pitch) or named-expert family (expert, conclave, critique, roster) reference/office-hours-format.md, reference/ethics-and-safety.md
Multi-Engine multi Multi-engine deliberation — 6-cell dual baseline, 9-cell tri when agy AVAILABLE. Pattern-based verdict preserving cross-viewpoint trade-offs; engine influence capped at 50%; all-cells-unanimous triggers mandatory DA reference/tri-engine-deliberate.md, _common/MULTI_ENGINE_RECIPE.md
Strategy Simulation simulate Run baseline / optimistic / pessimistic business scenarios reference/strategy-simulation/simulation-patterns.md, reference/strategy-simulation/scenario-planning-pitfalls.md, reference/strategy-simulation/financial-modeling-pitfalls.md

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