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.

referenceconclave-protocol.md

≈629 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Conclave Protocol

Purpose: Channel a panel of 2-5 figures on one question and surface their genuine contrasts — without flattening disagreement into a fake consensus. Read when: You are running the conclave recipe (multi-figure panel).

Principle

A conclave's value is divergence, not agreement. If three figures would genuinely clash, the clash is the deliverable. Summon never resolves the clash into a verdict — that is Magi's job. Hand off when the user actually needs to decide.

Protocol

  1. Select 2-5 figures with meaningfully different mental models on the question. Pure agreement is a weak panel; aim for productive tension. Refuse/ask per the ethics gate for each figure individually.
  2. Channel each figure independently (full GROUND → CHANNEL → ATTEST per channeling-method.md). Do not let one reading anchor the next — channel them blind to each other, then compare. (Same independence logic Magi uses for its lenses.)
  3. Build the contrast map only after all readings exist:
    • Where do they converge? (shared conclusion, possibly different reasons)
    • Where do they diverge? Name the underlying values/trade-off driving the split.
    • What question would settle it between them?
  4. Preserve disagreement. Never average two readings into a mushy middle. A 2-vs-1 split stays a split.
  5. Offer the handoff. If the user must choose, route the panel to Magi (SUMMON_TO_MAGI) for arbitration, or back to the user. Summon advises.

Output shape

## Conclave — {Figure A}, {Figure B}, {Figure C} on {problem}

### {Figure A}  — {one-line stance}
{reading} · Attestation: A[n] I[n] S[n]

### {Figure B}  — {one-line stance}
{reading} · Attestation: A[n] I[n] S[n]

### {Figure C}  — {one-line stance}
{reading} · Attestation: A[n] I[n] S[n]

### Contrast map
- Converge on: …
- Diverge on: … (driven by: {value/trade-off})
- Would-settle-it question: …

**Disclaimer:** emulation of documented thinking, not the real persons' statements.
**Next:** decide → Magi/user · deepen one lens → channel · write-up → Scribe

Anti-patterns

  • Forced consensus — manufacturing agreement the figures would not share.
  • Sequential contamination — channeling B in light of A's reading instead of independently.
  • Stacked panel — picking 3 figures who all think alike, producing no real contrast.
  • Verdict creep — declaring a winner. Surface the tension; let Magi/user decide.

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 2 days ago.

Activeupdated last month

README badge

README badge for simota/agent-skills/summon