All skills
simota avatar

/saga

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

Designing narratives that tell product and feature use cases as customer-centric stories. Use when customer experience storytelling, scenario stories, or product narratives are needed.

Requires /cue

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

This session only. Nothing lands on disk.

referencehero-journey.md

≈303 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Hero's Journey Delta

Purpose: Saga hero-journey truthfulness and output contract. The monomyth stages are model-known.

Scope

  • Use only for a material customer transformation with a trigger, risk, ordeal, measurable outcome, and lasting change.
  • The customer is the hero; the product or service is the guide.
  • Choose the number of stages to fit the available evidence and channel. Never invent an event to complete the framework.

Required Evidence

  • named or safely anonymized customer context
  • ordinary-world baseline and trigger event
  • objections or risks actually observed
  • commitment and ordeal moments
  • before/after metric with source and period
  • internal change only when supported by customer testimony
  • advocacy or return outcome, if it occurred

Missing stages remain labeled missing or are omitted; they are not filled with plausible fiction.

Deliverable

Provide cast, external and internal arcs, selected stage map, evidence citation per material beat, before/after measure, missing-evidence notes, Saga AP-1–AP-9 result, and handoff recommendation. Route video to Cue, pull quotes to Prose, short conversion copy to bab, and measurement claims to Pulse or Experiment.

Source: SKILL.md on GitHub

1 alert13d4 checks · Risk HIGH
  • Gen Agent Trust Hub13d

    The 'saga' skill defines a 'multi-engine' narrative generation mode that involves executing shell commands via external CLI tools (codex and agy). Crucially, the documentation for this mode instructs the agent to use the '--dangerously-skip-permissions' flag when invoking the agy tool, which is a direct attempt to bypass platform-level security controls and privilege restrictions. Furthermore, the skill processes untrusted external data and interpolates it into these shell commands, creating a significant attack surface for command injection and indirect prompt injection.

  • Socket13d

    1 alert: gptAnomaly

  • Snyk13d

    Risk: MEDIUM · 1 issue

  • 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/saga