All skills
simota avatar

/summon

@16a3f28
by shingo imotasimota/agent-skills85 stars
15

Channeling the documented thinking of named notable figures (an 'itako' medium) — their mental models, heuristics, and decision-style as advisory lenses. Not for decisions (Magi) or personas (Cast).

Requires /echo

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

This session only. Nothing lands on disk.

referenceautorun-schema.md

≈196 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Summon — AUTORUN _STEP_COMPLETE Schema

See _common/AUTORUN.md for the protocol (_AGENT_CONTEXT input, mode semantics, error handling).

Summon-specific _STEP_COMPLETE.Output schema:

_STEP_COMPLETE:
  Agent: Summon
  Status: SUCCESS | PARTIAL | BLOCKED | FAILED
  Output:
    deliverable: [reading path or inline]
    artifact_type: "[Channeled Reading | Conclave | Critique | Figure Roster]"
    parameters:
      recipe: "[channel | conclave | critique | roster]"
      figures: "[names]"
      attestation_mix: "[# ATTESTED / # INFERRED / # SPECULATIVE]"
      ethics_gate: "[passed | refused | escalated]"
  Validations:
    quotes_fabricated: "none"
    disclaimer_present: "[yes | no]"
  Next: Magi | Riff | Scribe | DONE
  Reason: [Why this next step]

Source: SKILL.md on GitHub

No alerts1mo3 checks · Risk SAFE
  • Gen Agent Trust Hub1mo

    The 'Summon' skill is a highly disciplined agent designed for emulating the documented mental models of notable figures. It includes an integrated 'Ethics Gate' to prevent impersonation and a multi-tiered attestation system to ensure transparency regarding the source of its reasoning. No malicious technical patterns were identified.

  • Socket1mo

    No alerts

  • Snyk1mo

    Risk: LOW · No issues

Signed by skilld at 16a3f28. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 3 days ago.

Activeupdated last month

README badge

README badge for simota/agent-skills/summon