magi SKILL.md skillA
magi from simota/agent-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add simota/agent-skills/magi@git:20261019.e7cdf45Pins git:20261019.e7cdf45 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- simota/agent-skills
- Path
magi/SKILL.md- Versions recorded
- 12
- Latest version
- git:20261019.e7cdf45, committed Oct 19, 2026
- First version recorded
- Aug 20, 2026
- Size
- 24,430 bytes
- Repository stars
- 99
- License
- MIT
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.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
<!-- CAPABILITIES_SUMMARY: - multi_perspective_deliberation: Three-lens evaluation (Logos/Pathos/Sophia) for balanced decisions - architecture_arbitration: Tech stack selection, pattern evaluation, system design decisions - trade_off_resolution: Confidence-scored verdicts on competing quality attributes - go_no_go_verdict: Release readiness, feature approval, quality gate decisions - strategy_decision: Build vs buy, refactor vs rewrite, invest vs defer - priority_arbitration: Competing requirements ordering and resource allocation - confidence_weighted_voting: 4 consensus patterns (3-0, 2-1, 1-1-1, 0-3) - engine_mode_deliberation: Three-engine deliberation for high-stakes decisions with physical independence - dissent_documentation: Minority perspective recording and risk register generation - decision_audit_trail: Full deliberation transcript, traceable end to end - escalation_routing: Split decisions escalated to human judgment - cognitive_bias_detection: Anchoring, confirmation, sunk cost, groupthink detection with consider-the-opposite debiasing - collaborative_calibration: Iterative confidence adjustment across multiple agent assessments …
Read the whole file at its exact version.
How to install
mdr add simota/agent-skills/magi@sha256:eb28a63254817821The line at the top of this page pins the label git:20261019.e7cdf45, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_apbqcpqwzebquo5f)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 12 versions of this file, between Aug 20, 2026 and Oct 19, 2026, about one every 5 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261019.e7cdf45 latest | 2026-10-19 | e7cdf45 | 24,430 B | A | view · diff |
| git:20261014.350ad2b | 2026-10-14 | 350ad2b | 24,441 B | A | view · diff |
| git:20261012.27f6d8a | 2026-10-12 | 27f6d8a | 24,444 B | A | view · diff |
| git:20261009.4537a3e | 2026-10-09 | 4537a3e | 24,480 B | A | view · diff |
| git:20261009.1e21383 | 2026-10-09 | 1e21383 | 24,469 B | A | view · diff |
| git:20261009.b9c0da0 | 2026-10-09 | b9c0da0 | 24,524 B | A | view · diff |
| git:20260916.35ffd55 | 2026-09-16 | 35ffd55 | 24,504 B | A | view · diff |
| git:20260820.4d4eeea | 2026-08-20 | 4d4eeea | 24,678 B | A | view · diff |
| git:20260820.e942f01 | 2026-08-20 | e942f01 | 24,655 B | A | view · diff |
| git:20260820.22a71d0 | 2026-08-20 | 22a71d0 | 28,005 B | A | view · diff |
| git:20260820.640d1a0 | 2026-08-20 | 640d1a0 | 29,998 B | A | view · diff |
| git:20260820.9805aa1 | 2026-08-20 | 9805aa1 | 32,434 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (24430 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
simota/agent-skills · 99 stars · license MIT · pushed 2026-10-26 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_apbqcpqwzebquo5f GET https://markdownregistry.com/api/v1/resolve?ref=simota/agent-skills/magi GET https://markdownregistry.com/api/v1/blob/eb28a632548178218c93056fb5c0bf7343c13b48d583ad63240bbf5412d0ab8a
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from simota/agent-skills
Every file in simota/agent-skills