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.

referenceautorun-schema.md

≈379 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Saga — AUTORUN _STEP_COMPLETE Schema

See _common/AUTORUN.md for the protocol (_AGENT_CONTEXT input, mode semantics, error handling). On AUTORUN, run DISCOVER → FRAME → CRAFT → REFINE → DELIVER and emit _STEP_COMPLETE. Saga-specific Constraints in _AGENT_CONTEXT: target audience, framework preference, length/format constraints.

_STEP_COMPLETE:
  Agent: Saga
  Task_Type: use_case_story | product_narrative | pitch_story | customer_success | onboarding | scenario | tri_engine_portfolio | tri_engine_compete
  Status: SUCCESS | PARTIAL | BLOCKED | FAILED
  Output:
    narrative: [Story content]
    framework_used: [Framework name]
    anti_pattern_check: [AP results]
    files_changed: List[{path, type, changes}]
    tri_engine:                                  # present only when `multi` Recipe ran
      engines_run: [actual usable engines]  # authorized and actually invoked
      engines_failed: [list or none]
      merge_strategy: "[Portfolio | Compete]"
      concurrence_distribution:
        UNIVERSAL: [count]
        LIKELY: [count]
        VERIFIED-DIVERGENT: [count]
      archetype_coverage: ["Hero's Journey", "JTBD", "Before-After-Bridge", ...]
      rejected: [count + top categories — no-arc / hero-product / no-tension / generic-persona / jargon / ad-copy / fabricated-evidence]
  Handoff:
    Format: SAGA_TO_[NEXT]_HANDOFF
    Content: [Handoff content for next agent]
  Risks: [Assumptions needing validation]
  Next: [NextAgent] | VERIFY | DONE

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