Skip to main content
在 Manus 中运行任何 Skill
一键导入
GitHub 仓库

aegis-cli

aegis-cli 收录了来自 rtmx-ai 的 10 个 skills,并提供仓库级职业覆盖和站内 skill 详情页。

已收集 skills
10
Stars
4
更新
2026-06-23
Forks
0
职业覆盖
4 个职业分类 · 已分类 100%
仓库浏览

这个仓库中的 skills

discovery
项目管理专家

Integrate continuous discovery/framing (design thinking) into the rtmx delivery loop. Use this whenever deciding WHAT to build next, before authoring requirements, when reviewing parked work or metrics to reframe, or any time you are tempted to let the loop invent its own work. Pairs with decomposition (the split mechanics) — this owns the framing discipline.

2026-06-23
airgap-hygiene
软件开发工程师

Write code that makes ZERO external network calls — only loopback to the local model endpoint is permitted — and be able to prove it. Use this whenever you add a dependency, touch config, write anything that could open a socket, or wire up CI's egress gate. Trigger it on any import, any URL, any default that could phone home, and any time you need to demonstrate the build is closed.

2026-06-23
build-to-spec
软件开发工程师

The core implementation discipline — claim ONE requirement, make the minimal change that satisfies its acceptance test, run the test, verify, release. Use this every time you implement a requirement: it is the inner loop. Trigger it whenever you are about to write code, and especially when you feel the pull to fix a nearby thing, refactor "while you're here", or tweak a test that's in your way.

2026-06-23
context-discipline
软件开发工程师

Keep context lean for a small, CPU-bound local MoE (~4B active) — prefer LSP/grep/symbol lookup over dumping whole files, scope to one requirement, spend tokens like they're metered. Use this whenever you gather context to work a requirement: reading code, searching, deciding what to put in the prompt. Trigger it any time you're about to read a whole file, paste large output, or widen scope beyond the one requirement in hand.

2026-06-23
decomposition
软件开发工程师

Break a coarse requirement into atomic children — as PROPOSALS a human approves, never as work the machine authors and then grades itself on. Use this whenever a requirement is too big to close in one scoped pass, when splitting work into atomic units, or when running `aegis propose`. Trigger it any time the agent is tempted to invent sub-requirements, write its own acceptance criteria, or decide on its own what "atomic" means.

2026-06-23
go-conventions
软件开发工程师

aegis-cli's Go style — one static air-gappable binary, std-lib-first, vendored deps, no CGO unless a serving probe needs it, and no telemetry ever. Use this whenever you write or review Go in this repo: choosing a dependency, structuring a package, deciding whether logic belongs here at all. Trigger it before reaching for a third-party library, before adding a build tag, and any time a task starts to feel like harness logic.

2026-06-23
metrics-eval
软件质量保证分析师与测试员

Run the golden set through the real loop in a network-captured sandbox and compute/interpret the CI metrics — ACR (north star), TCVR, FPVR, MTC, WCR, TCR, ESC — and enforce the hard gates. Use this whenever you measure aegis-cli: a CI run, a model/harness bake-off, investigating a regression, or interpreting a dashboard move. Trigger it before claiming something "works", and any time you swap the model, harness, or prompt.

2026-06-23
rtmx-loop
软件开发工程师

Talk to rtmx safely — list the next requirement, claim it atomically, do the work, write the verify result back to the CSV, and release. Use this whenever the loop touches rtmx: `rtmx next`, claim/release, `rtmx verify`, status writeback, or recovering claims after an interruption. Trigger it before any step that reads or mutates requirement state, and any time you are tempted to hold more than one claim or skip the writeback.

2026-06-23
serving-calibration
网络与计算机系统管理员

Tune the local inference worker to the host, govern compute contention, and profile per-stage timing — calibrate (don't guess), place (don't schedule), separate generate from verify in time. Use this whenever you touch serving: launching the endpoint, setting thread/batch/offload, diagnosing slow WCR, or bringing up a new target. Trigger it before any launch (uncalibrated is a hard error) and any time two heavy stages might run at once.

2026-06-23
unattended-operation
软件开发工程师

Run the backlog unattended — drain it continuously, park on escalation instead of waiting, break the circuit on repeated failure, and stay inside a run budget. Use this whenever the loop runs without a human watching: overnight runs, CI-driven drains, "leave it working while I'm away", or any `aegis run` without `--once`. Trigger it before starting an unattended session and when deciding how the loop should behave on failure, escalation, or a stuck requirement.

2026-06-23