minimax-ai/mcode-stack

trajectory-review

Review how an agent reached its result, not only whether the result passed, covering tools called, detours, unverified assumptions and wasted round trips, and turn the findings into concrete harness or prompt fixes.

Ver código-fonte

Como usar

  1. Copie o comando e verifique o pacote antes de instalar no seu ambiente de agente.
  2. Consulte no original as ferramentas, credenciais e ambientes necessários.
  3. Descreva os dados de entrada e a entrega esperada; confira a saída com as fontes.
npx skills add https://github.com/minimax-ai/mcode-stack --skill trajectory-review

Antes de começar

  • A instalação não inclui assinatura de modelo, franquia API ou acesso aos seus arquivos.
  • Estrelas e instalações indicam atividade, não um teste independente de qualidade ou segurança.
Documento original do Skill

Renderizado do repositório de origem, preservando títulos, exemplos, código, tabelas, links e imagens.

Trajectory Review

A passing result can hide a fragile process: an assumption that happened to hold, a lucky retry, ten round trips where two would do. A failing result usually has its cause several steps before the error. Review the path, not only the end point.

1. Get the real trajectory

Use the actual record of the run: the session transcript, tool-call log, or eval trace. Note the model, settings and repository state. Do not reconstruct the run from memory.

2. Walk it step by step

Build a compact timeline. For each step: what the agent intended, which tool it called with which key arguments, what came back, and what it decided next.

While walking, mark:

  • Unverified assumptions. The agent states or acts on something it never

checked ("callers already validate this", "the test passes").

  • Detours. Loops, repeated searches with changing keywords, re-reading the

same file, retries without a change in approach.

  • Wrong tool or wrong arguments. Including tools it could not find.
  • Context waste. Large outputs pulled in and never used, polling instead of

waiting for a notification.

  • Missed signals. Errors, warnings or test failures it saw and ignored.
  • Instruction drift. Earlier constraints it later broke, often after

compaction.

3. Find the first point where it went wrong

For a failure, find the earliest step after which success became unlikely. For a pass, find the riskiest step: where a slightly different input would have broken it.

4. Turn findings into fixes

Map each finding to the cheapest durable fix:

FindingTypical fix
Assumption never checkedA verification step in a skill or project rules
Could not find or picked the wrong toolTool description, naming or grouping (see tool-budget-audit)
Lost an earlier constraintWrite it into a file the agent reloads (see long-session-check)
Polling or waiting idleBackground tasks with notification (see long-command-check)
Repeated per-turn overheadContext injection review (see context-tax-audit)
Model limitationRecord it; re-check after the next model upgrade

Keep one-off quirks out of project-wide rules. Only propose a rule for something that has happened more than once or caused real damage.

5. Confirm

A fix is a harness change, so check it with harness-experiment: rerun the same task several times and compare the trajectory, not only the outcome.

Output

The compact timeline with marked steps, the first wrong (or riskiest) step, and a short list of proposed fixes, each tied to a specific step.

do mesmo repositório

Mais Skills

Todos os Skills
minimax-ai
Comunidade

engineering-code-review

Use when reviewing code, pull requests, patches, CLs, diffs, or proposed implementations for engineering quality, code health, design, functionality, tests, maintainability, specialist risk, or approval risk. TRIGGER on "review this PR", "code review", "LGTM?", "approve?", "is this code/diff/change safe to merge/deploy?", and local diff reviews. DO NOT TRIGGER for PR descriptions, PR splitting, author review-feedback responses, or non-code safety questions unless code review is requested.

Instalações / 1h
1
GitHub Stars
685
Atualizado
10 de nov.
minimax-ai
Comunidade

evidence-first-review

Review an agent's finished work by reading the evidence before its summary, naming what each check proves and what it misses, pulling out the decisions it made silently, and trying to falsify the result before accepting it. Use when a MiniMax Code session, subagent or cloud agent reports a task done, before merging its PR or acting on its analysis.

Instalações / 1h
1
GitHub Stars
685
Atualizado
10 de nov.
minimax-ai
Comunidade

handoff-doc

Write a hand-off document so a fresh session or another person can continue the current task without the chat history. Use when switching tasks, after several compactions, before clearing a session, or when asked to write a handoff, brief, or progress doc.

Instalações / 1h
1
GitHub Stars
685
Atualizado
10 de nov.
minimax-ai
Comunidade

harness-experiment

Run a harness change as a controlled experiment, with a small end-to-end eval, one change at a time, repeated runs, and looking at flipped tasks, request count, tokens and cache hits, not just the average score. Use before and after changing prompts, tools, skills, subagent layout, compaction or other agent scaffolding, or when asked whether a change helped.

Instalações / 1h
1
GitHub Stars
685
Atualizado
10 de nov.