一键在 Manus 中运行任何 Skill

terminal-agent-improvement-loop

星标495

分支36

更新时间2026年4月14日 01:57

Run a benchmark-driven improvement loop for Con's terminal agent. Use when iterating on pane awareness, SSH/tmux behavior, coding-cli flows, benchmark scoring, or progress tracking across many runs.

安装

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

在 Manus 中运行

来源

nowledge-co

nowledge-co/con-terminal

打开 GitHub 仓库查看创作者相关仓库

下载

在 Manus 中运行

相关职业SOC

基于 SOC 职业分类

软件开发工程师计算机与数学类职业·SOC 15-1252

SKILL.md

readonly

同仓库更多 Skills

同仓库

con-cli-e2e

nowledge-co/con-terminal

Validate Con's local socket control plane against a real running app session, and write/run con-test integration tests. Use when testing con-cli, the Unix socket API, pane control, tmux control, in-session agent calls, or when writing E2E test cases in crates/con-test/testdata/.

2026-05-08495

changelog-release-notes

nowledge-co/con-terminal

Maintain Con's CHANGELOG.md and release notes. Use when updating changelog entries, preparing a beta/dev release, reviewing PR release-note coverage, or ensuring contributor PR credit is present.

2026-05-07495

terminal-agent-benchmark

nowledge-co/con-terminal

Run and maintain Con's terminal-agent benchmark against a live app session. Use when validating con-cli, SSH workspace reuse, tmux awareness, agent-target preparation, or when collecting benchmark evidence for regressions and release notes.

2026-04-30495

Terminal Agent Improvement Loop

Use this skill when improving Con as a terminal-native agent, not just fixing a one-off bug.

Primary references:

Workflow

Choose the smallest operator profile that matches the problem.

Run the benchmark on an idle tab:

python3 benchmarks/terminal-agent/run.py --profile operator-local-codex-devloop --suite operator
for repeated clean iterations, prefer python3 benchmarks/terminal-agent/iterate.py ...

Score the resulting run with the matching rubric:

python3 benchmarks/terminal-agent/score.py --profile ... --record ... --score ...
or ask the built-in agent to judge the raw record and transcript first: python3 benchmarks/terminal-agent/judge_llm.py --profile ... --record ... --socket /tmp/con.sock
then turn that judge artifact into a normal scorecard: python3 benchmarks/terminal-agent/score.py --profile ... --record ... --judge-file ...

Record one short summary, a few lessons, and a few next-focus bullets in the score record.

Append the scorecard to the tracked improvement log:

python3 benchmarks/terminal-agent/log_iteration.py --scorecard ... --change "..."

Make one focused product change.

Re-run the same operator profile.

Generate a report when you need to inspect trend:

python3 benchmarks/terminal-agent/report.py

Rules

Use strict suites to protect the floor and operator suites to judge real workflows.

Prefer operator profiles that start a fresh conversation and have bounded step timeouts.

Prefer typed control-plane improvements over prompt-only fixes.

Do not overfit to a single benchmark phrase or one host layout.

Keep unknowns honest when the backend cannot prove more.

When benchmark infra changes, say whether the product improved or the measurement improved.

Keep iteration notes concise and comparable across runs.

Keep docs/impl/terminal-agent-improvement-log.md useful to a human reader; it should explain what changed, not just repeat the numeric score.

If you use the LLM judge, feed it the raw record and transcript, not only the generated report. The report is a summary, not primary evidence.

Terminal Agent Improvement Loop

Use this skill when improving Con as a terminal-native agent, not just fixing a one-off bug.

Primary references:

Workflow

Choose the smallest operator profile that matches the problem.

Run the benchmark on an idle tab:

python3 benchmarks/terminal-agent/run.py --profile operator-local-codex-devloop --suite operator
for repeated clean iterations, prefer python3 benchmarks/terminal-agent/iterate.py ...

Score the resulting run with the matching rubric:

python3 benchmarks/terminal-agent/score.py --profile ... --record ... --score ...
or ask the built-in agent to judge the raw record and transcript first: python3 benchmarks/terminal-agent/judge_llm.py --profile ... --record ... --socket /tmp/con.sock
then turn that judge artifact into a normal scorecard: python3 benchmarks/terminal-agent/score.py --profile ... --record ... --judge-file ...

Record one short summary, a few lessons, and a few next-focus bullets in the score record.

Append the scorecard to the tracked improvement log:

python3 benchmarks/terminal-agent/log_iteration.py --scorecard ... --change "..."

Make one focused product change.

Re-run the same operator profile.

Generate a report when you need to inspect trend:

python3 benchmarks/terminal-agent/report.py

Rules

Use strict suites to protect the floor and operator suites to judge real workflows.

Prefer operator profiles that start a fresh conversation and have bounded step timeouts.

Prefer typed control-plane improvements over prompt-only fixes.

Do not overfit to a single benchmark phrase or one host layout.

Keep unknowns honest when the backend cannot prove more.

When benchmark infra changes, say whether the product improved or the measurement improved.

Keep iteration notes concise and comparable across runs.

Keep docs/impl/terminal-agent-improvement-log.md useful to a human reader; it should explain what changed, not just repeat the numeric score.

If you use the LLM judge, feed it the raw record and transcript, not only the generated report. The report is a summary, not primary evidence.

name	terminal-agent-improvement-loop
description	Run a benchmark-driven improvement loop for Con's terminal agent. Use when iterating on pane awareness, SSH/tmux behavior, coding-cli flows, benchmark scoring, or progress tracking across many runs.