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

agent-smith

agent-smith 收录了来自 tonitienda 的 11 个 skills,并提供仓库级职业覆盖和站内 skill 详情页。

已收集 skills
11
Stars
1
更新
2026-06-30
Forks
0
职业覆盖
2 个职业分类 · 已分类 100%
仓库浏览

这个仓库中的 skills

ticket-implementer
软件开发工程师

Start an Agent Smith ticket the right way — read the ticket, its dependencies, the PRD Decision Log, and the affected architecture/docs before editing. Use when picking up an AS-NNN ticket, deciding what to work on next, or before touching code for a backlog item. Triggers: "work on AS-", "start a ticket", "implement the ticket", "what should I work on next", "pick a ticket".

2026-06-30
pr-workflow
软件开发工程师

Agent Smith pull-request lifecycle — open a PR, subscribe to activity, reply to and resolve every review thread, handle the Gemini/Copilot review order, and auto-merge when clean. Use when work on a branch is committed and pushed, when a PR exists for the branch, or when handling review comments or CI on a PR. Triggers: "open a PR", "PR review", "review comment", "CI failed on the PR", "merge the PR", "is the PR ready".

2026-06-30
reflect-artifacts
软件质量保证分析师与测试员

Reflect phase — produce the three success artifacts (a measurable success metric, an instrumentation diff, a check-back ticket draft) without ever reading shipped-app runtime data.

2026-06-24
find-side-effects
软件开发工程师

Analyse phase — trace what else the change touches: callers, shared state, persisted formats, and cross-package contracts.

2026-06-21
grill-gaps
软件开发工程师

Analyse phase — interrogate the request for missing requirements, unstated assumptions, and unhandled cases before any code is written.

2026-06-21
plan-review
软件开发工程师

Plan phase — pressure-test the proposed plan: smallest viable change, ordering, and the test that will prove it.

2026-06-21
reflect-notes
软件开发工程师

Reflect phase — capture what was learned as durable, grounded notes: surprises, follow-on tickets, and method tweaks.

2026-06-21
verify-checklist
软件开发工程师

Verify phase — confirm the change actually works: tests run, gate passes, acceptance criteria met, claims grounded in output.

2026-06-21
ci-failure-triage
软件开发工程师

Map a failing Agent Smith CI job to the local harness command that reproduces it and produce the shortest reproduction plan. Use when a GitHub Actions check is red, a PR's CI failed, or someone asks why CI broke and how to fix it locally. Triggers: "CI failed", "check is red", "reproduce the CI failure", "why did the build break", "make CI green".

2026-06-20
quality-gate-runner
软件质量保证分析师与测试员

Choose, run, and interpret the Agent Smith harness quality gates when finishing or handing off code changes. Use when you have edited Go code and need to validate it, when deciding between the quick/full/arch checks, when a gate fails and you must classify the failure, or when a command can't run in the current environment. Triggers: "run the gate", "quality gate", "before commit", "is this ready to push", "harness check", "make test/vet/lint".

2026-06-20
caveman
软件开发工程师

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Drops articles, filler, hedging, pleasantries. Preserves all code, technical terms, error strings verbatim. Supports intensity levels: lite, full (default), ultra, wenyan variants. Use when user says "caveman", "caveman mode", "talk like caveman", "less tokens", or invokes /caveman.

2026-06-15