magi-research
Skill4 starsChanged 20 days agoMITView on GitHub
Run research with three agents in fixed roles, the helpers living in adash terminals (adash's private tmux server): the main session (Claude Opus) plans, decides and edits; a permanent Argon session (Antigravity agy, Gemini 4 Argon) proposes options, designs and mockups; a permanent Astra session (omp, GPT-6-Astra; Codex fallback) criticizes and corrects. Use when a research task needs fresh alternatives (figure redesign, section structure, framing, experiment design: \"제안 받아봐\", \"창의적인 대안\", \"원점에서 다시\", \"다른 방식은 없어?\") or a hard check (\"검토받아\", \"비판해줘\", \"수락받아\", \"검토자들과 논의해봐\"), or when the user says magi. Use peer-agent-review alone for a single sign-off by one reviewer; this skill decides which agent to ask, in what order, and how to merge their answers.
In this repository38 other files it gives its agents.
- academic-cvSkill
- academic-jobsSkill
- academic-proseSkill
- adversarial-reviewSkill
- bibtex-genSkill
- chrome-sessionSkill
- clickup-cliSkill
- clickup-todaySkill
- commit-triageSkill
- concept-explainerSkill
- contact-emailSkill
- cover-letterSkill
- dropboxSkill
- handdrawn-schematicSkill
- hep-rumor-millSkill
- journal-club-reviewSkill
- md2pdf-typoraSkill
- morgenSkill
- overleaf-section-workflowSkill
- overleapSkill
- peer-agent-reviewSkill
- proton-mailSkill
- reference-searchSkill
- remarkable-syncSkill
- research-backupSkill
- research-boardSkill
- research-logSkill
- research-portalSkill
- research-proposalSkill
- research-reportSkill
- research-statementSkill
- scienceplot-pySkill
- vastaiSkill
- wide-slide-illustratorSkill
- workshop-paper-reviewSkill
- xkcd-pySkill
- zai-web-searchSkill
- zoom-summarySkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 61
Run the two asks in the background and keep working.
- Distinctive: line 99
When an agent says "your claim is wrong", check the file first.
- Distinctive: line 101
Keep the user's style rules and decisions in each brief.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
magi-research: propose with Argon, criticize with Astra, decide in the main session
Three roles, one rule: ask Argon when you need options, ask Astra when you need judgment, and keep every decision and every file edit in the main session.
Built on adash terminals. The proposer and the critic are permanent sessions in adash
terminals (windows of adash's private tmux server) opened in the current worktree, reached
through adash term. magi.py stops with exit 6 when adash is not on PATH, or when the caller
is neither in an adash terminal ($ADASH_HANDLE unset) nor has tmux; there is no headless
substitute for the roles.
| Role | Agent | Good at | Weak at |
| Main (decider) | Claude Opus, this session | plans, verifies, edits, talks to the user | anchoring on its first idea; defends its own draft |
| Proposer | Argon: agy, gemini-4-argon-<level>, target argon | breaking out of the current form, reframing axes and structure, building runnable mockups (figures, scripts) fast | long and confident prose, overstated wording ("완벽히", "원천 차단"), invented section names or line numbers, slow (3 to 15 min) |
| Critic | Astra: omp, gpt-6-astra, target astra; fallback Codex (codex -s read-only, target codex) when omp is missing or the Astra session cannot be resolved or reached | fact and number checks, claim scope, statistical fairness, citation scope, counterexamples, exact replacement sentences | conservative: improves the current form rather than replacing it |
Observed on a PRX manuscript revision (2026-10): Astra caught a wrong claim in the main session's draft (a shared lookup table read as "unused when out of window"), a pooled band that inflated a figure's count fourfold, and a statistically wrong "within error" sentence. Argon twice produced the figure the author picked after the main session and Astra had only iterated on the existing layout. Argon's prose also contained a fabricated subsection list and a misquoted line; every Argon fact must be checked before use.
Transport
scripts/magi.py routes by role on top of peer-agent-review (same skill repo), which keeps one
permanent session per target in the worktree, so each agent remembers its earlier answers.
M=<skills repo>/magi-research/scripts/magi.py
python3 $M propose --brief _guide/<topic>_brief_<date>.md --marker '<topic> propose' # Argon (agy)
python3 $M critique --brief _guide/<topic>_apply_<date>.md --marker '<topic> v1 check' # Astra (omp), accept
python3 $M critique --mode discuss --brief _guide/<topic>_brief_<date>.md --marker '<topic> critique'
python3 $M both --brief _guide/<topic>_brief_<date>.md --marker '<topic> debate' --out-dir _guide/answers/<topic>- Critic fallback:
critiqueuses Astra through omp; ifompis not installed, orpeer_review.pyexits 2 (cannot resolve or launch) or 3 (not delivered), it re-sends the same brief to a read-only Codex session (marker suffixed(codex)). Report which critic answered. - Proposer: Argon through agy only. If agy is unavailable, say so and ask the user rather than
substituting another model silently.
magi.pylaunches Argon with--dangerously-skip-permissions(tool calls auto-approved, so mockups run unattended);MAGI_ARGON_SAFE=1keeps the prompting launch. The flag applies when the session is launched: an Argon session already registered keeps its old launch untilpeer_review.py close -t argonand the nextmagi.py propose. - Lower level, same transport:
python3 <skills repo>/peer-agent-review/scripts/peer_review.py targetsshows whatastra,argonandcodexresolve to here;ask -t <target> --mode …sends directly. proposeis the only non-hostile mode: alternatives with specs, trade-offs, risks and one recommendation, mockups only in the folder the brief names. Use it for Argon.acceptanddiscussare hostile by design. Use them for Astra.- Argon answers through a file (
~/.cache/peer-agent-review/answers/argon/<marker>.md); the helper waits for it. Never use a wrapper whose pointer forces "첫 줄은 수락 또는 수정 필요" on a proposal request: Argon then writes a verdict line and argues for it instead of proposing. - Run the two asks in the background and keep working; send to both in parallel when the user asks for a discussion ("논의해봐").
- A marker is single use. Briefs live in the project (
_guide/…), never/tmp.
Which loop to run
1. Open problem (design, structure, framing, figure concept): propose → critique → decide
- Frame (main). Write one brief: the user's words verbatim with date, the goal stated as the message the reader must get, hard constraints (author rules, data that exists, page budget), and what is not fixed. Say explicitly that the current form is not a constraint when the user says the work is biased toward it.
- Propose (Argon,
propose). Ask for 2 to 3 distinct options with specs, required reader knowledge, risks, and mockups in<scratch>/<topic>/argon/. Optionally ask Astra indiscussmode in parallel for its own option; Astra's option is the conservative baseline. - Screen (main). Open every mockup yourself. Verify every number and quotation Argon used against the files. Drop options that break a hard constraint. Show the user the survivors as images with paths and your recommendation; the user picks.
- Critique (Astra,
discussoraccept). Send the chosen option as implemented (not the raw proposal): what changed, files, backups, and the questions you are unsure about. - Apply and close (main). Verify each required fix, apply it, re-send
vN 확인to Astra until 수락. Optional suggestions: apply or say why not.
2. Change to existing work (text edit, translation, merge): edit → critique
Main edits, Astra checks in accept mode until 수락. Add Argon only as a second reader when
the change is large; treat its "수락" as weak evidence (it has approved text Astra rejected).
3. Disagreement or a decision the user wants debated
Send the same discuss brief to both. Merge by role: Astra's factual corrections override
Argon's; Argon's alternatives widen the option list; where they recommend different options,
show the user both with the reason each gives and your own pick. Never average the two.
Main-session duties (do not delegate)
- Re-derive every number either agent reports before you forward it or write it into the work. Agreement between two agents that read the same file is shared sourcing, not corroboration.
- When an agent says "your claim is wrong", check the file first; when it is right, say so to the user plainly, including when it corrected your own proposal.
- Keep the user's style rules and decisions in each brief; agents do not see the conversation.
- Report to the user: what each agent proposed or corrected, what you chose and why, what is still unverified. Do not paste the agents' answers.
Brief checklist
- User instruction verbatim with date.
- Message or acceptance criterion in one sentence.
- Files to read (paths), backups of previous versions, data that may be used.
- Hard constraints (style rules, page or figure budget, no new measurements).
- Output contract:
proposefor Argon (folder for mockups),accept/discussfor Astra. - Numbered questions you are unsure about.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

