Token导航 LogoToken导航

Agent Skill · 研究检索

forge-idiomatic-engineer(锻造惯用工程师)

forge-idiomatic-engineer 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

forge-idiomatic-engineer 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为操作浏览器;许可证信息还不明确,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 8,251。

总安装 16,817周安装 715GitHub Stars 80下载 5,892核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:forge-idiomatic-engineer(锻造惯用工程师)
来源仓库:https://github.com/isala404/forge
仓库路径:skills/forge-idiomatic-engineer
安装命令:
npx skills add https://github.com/isala404/forge --skill forge-idiomatic-engineer
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/isala404/forge --skill forge-idiomatic-engineer

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中快速定位候选结果。适用于关键词搜索、任务场景匹配或来源线索追踪等研究检索场景。通过 npx skills add 命令从指定 GitHub 仓库安装并使用。安装前需确认权限范围、维护状态,注意是否触发联网或文件操作。

建议结合原始 README 和仓库内容进一步验证具体功能和使用方式。

来源仓库内路径:skills/forge-idiomatic-engineer

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/isala404/forge --skill forge-idiomatic-enginee…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要操作浏览器,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

forge-idiomatic-engineer 怎么安装?

在终端执行 npx skills add https://github.com/isala404/forge --skill forge-idiomatic-engineer。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

forge-idiomatic-engineer 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

forge-idiomatic-engineer 需要什么权限?

权限级别是操作浏览器。该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

forge-idiomatic-engineer 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

forge-idiomatic-engineer 用的人多吗?

公开数据是累计安装 16,817 次,近一周安装 715 次,下载 5,892 次,GitHub 80 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

forge-idiomatic-engineer 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
forge-idiomatic-engineer

锻造惯用工程师 · 本页

16,81780操作浏览器未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Forge Idiomatic Engineer

Full-stack Rust framework. Single binary, PostgreSQL-backed. Axum + Tokio + SQLx. Macros generate runtime wiring and frontend bindings; each handler must be registered in src/main.rs (macros alone do not wire it in).

Compile-Loop Hard Rules

These cause hours of wasted debugging if missed. Internalize before writing code.

  • SQLX_OFFLINE=true is mandatory for any cargo check / cargo build you run by hand. CI sets it globally. Without it, sqlx tries to validate every sqlx::query!() against your live DATABASE_URL — including queries inside published forge-runtime crate files you cannot edit — and you get a wall of "column does not exist" errors in third-party code. The simplest fix is eval "$(forge env)" in your shell rc; otherwise export SQLX_OFFLINE=true by hand.
  • forge check auto-prepares the offline cache. It detects when src/ is newer than .sqlx/ and runs cargo sqlx prepare --workspace before the rest of the pipeline, so you don't need to think about prepare ordering. (For raw cargo check, you still need to run forge migrate prepare after editing any sqlx::query!().) Pass --no-prepare in CI where the cache should already be correct.
  • forge migrate prepare hard-fails if cargo-sqlx is missing. Install with cargo install sqlx-cli --no-default-features --features postgres and re-run.
  • All forge commands walk up to find forge.toml. Run them from any subdirectory; the resolved root is printed at start. No need to cd first.
  • If anything in the compile loop feels off, run forge doctor first. It checks rustc, cargo-sqlx, SQLX_OFFLINE, DATABASE_URL reachability, Docker, frontend tooling, forge.toml syntax, .sqlx/ freshness, and the latest migration's @up/@down markers in one shot.
  • A passing cargo sqlx prepare is a passing compile. Don't run forge check purely to "confirm" what prepare just proved — prepare invokes a full cargo check internally. Run forge check only when you have new edits since the last prepare, or to exercise the rest of the validation suite (registration, schema, clippy).

Session Start: Read Once, Trust Memory

Run bash docs/skills/forge-idiomatic-engineer/scripts/orient.sh first. The script walks up to find forge.toml, then prints a structured dump: project name + auth mode + frontend, environment readiness (SQLX_OFFLINE, DATABASE_URL, cargo-sqlx, Docker), .sqlx/ cache freshness, the contents of src/main.rs / src/functions/mod.rs / src/schema/mod.rs, every registered handler grouped by kind, the latest migration, reactivity-enabled tables, and concrete NEXT action hints. One invocation replaces five separate reads.

Always read references/pitfalls.md and references/resilience.md once per session — the script doesn't print them.

Fallback when the script is unavailable (older checkout, sandboxed env): read forge.toml, Cargo.toml, src/main.rs, src/functions/mod.rs, and the most recent file under migrations/.

These files change only when you write to them — re-reading mid-session is almost always wasted context.

After auto-compaction, trust the summary's file inventory. Don't re-read main.rs / mod.rs to confirm something the summary already documented — only re-read if you're about to write to them and need exact current content. If a compaction attaches a file as an <attachment>, treat it as already in context; don't issue a fresh Read.

When you do need to read a file, read it fully in one call. Don't issue overlapping ranges (offset 200 then offset 1) — combine into a single read at offset 1 with a wide limit. Forge handler files are rarely larger than 600 lines.

Handler Types

ConceptMacroStruct suffixRegistration
Read-only query#[forge::query]Query.register_query::<FnNameQuery>()
Data mutation#[forge::mutation]Mutation.register_mutation::<FnNameMutation>()
Background job#[forge::job]Job.register_job::<FnNameJob>()
Scheduled task#[forge::cron]Cron.register_cron::<FnNameCron>()
Durable workflow#[forge::workflow]Workflow.register_workflow::<FnNameWorkflow>()
Long-running process#[forge::daemon]Daemon.register_daemon::<FnNameDaemon>()
External HTTP event#[forge::webhook]Webhook.register_webhook::<FnNameWebhook>()
AI agent tool#[forge::mcp_tool]McpTool.register_mcp_tool::<FnNameMcpTool>()

Or use .auto_register() to pick up all handlers via inventory.

Naming Rules

  • pub async fn handlers only — private functions fail codegen.
  • snake_case fn names → macro generates PascalCase + type suffix. Do not include the type in the fn name (heartbeat, not heartbeat_daemon, or you get HeartbeatDaemonDaemon).
  • #[forge::model] must be the first attribute on a struct.

Context API at a Glance

Memorize so you don't reach into the forge-core source mid-implementation:

  • ctx.db() → ForgeDb (a sqlx::Executor). Pass directly to query macros: sqlx::query_as!(...).fetch_one(ctx.db()).await?.
  • ctx.conn().await? → ForgeConn<'_> (transactional, mutations only). Pass &mut conn to query macros.
  • ctx.user_id() → Result<Uuid> on QueryContext and MutationContext. Returns ForgeError::Unauthorized if no principal. There is no ctx.auth() method on MutationContext.
  • ctx.db_conn() → DbConn<'_> for shared helpers that must work in both queries and mutations. DbConn has an inverted convention (call .fetch_* on the DbConn, passing the query) — see references/patterns.md.
  • Let type inference name the bindings (let mut conn = ctx.conn().await?). Don't import ForgeConn / ForgeDb / DbConn and write explicit types unless a helper signature requires it.

Workflow

  1. Orient — read the session-start file list above plus references/pitfalls.md and references/resilience.md. Detect frontend via frontend/package.json (Svelte) or frontend/Cargo.toml (Dioxus).
  2. Plan the slice — decide which handlers, migrations, and frontend changes belong in this PR before writing code. Surgical, vertical, one feature.
  3. Checkpoint loop, one handler at a time:

1. Run forge new <kind> <name> instead of writing the file by hand. It scaffolds the right macro defaults, appends pub mod <name>; to src/functions/mod.rs, and inserts mod functions; in src/main.rs if missing. Kinds: query, mutation, job, cron, workflow, daemon, webhook, mcp_tool, model, enum. 2. Edit the scaffolded file: replace placeholder SQL/business logic with the real implementation. 3. forge check. It auto-prepares the .sqlx/ cache when sources are newer, so you don't need a separate forge migrate prepare step in the common case. 4. If it fails, fix the root cause and re-run only the failing step. Do not write the next handler with errors outstanding. 5. Move to the next handler.

  1. forge generate after backend changes settle. Never edit generated files.
  2. Frontend — wire the UI against the generated bindings. forge test for Playwright E2E.
  3. Final pass — forge check clean, forge test green, write a brief change summary.

When the user says "fix it" / "can you fix it" after you've diagnosed a problem, fix it — don't ask for re-confirmation. Only pause to confirm for destructive actions (data deletion, schema drops, force pushes).

Architectural Defaults (choose upfront)

  • Auth: Social OAuth, password + HS256, or RS256 — pick before coding (see patterns.md). Social logins must link via the user_identities table.
  • Env: ctx.env_require() / ctx.env_or(), never std::env::var().
  • HTTP: ctx.http() for RPC, ctx.raw_http() when you need bytes_stream() or custom redirect policy.
  • SQL: sqlx::query!() / query_as!() bang-macros only. Run forge migrate prepare after schema or query changes — see Compile-Loop Hard Rules.
  • Jobs/workflows: dispatch only inside mutations (transactions are on by default). Never set transactional = false on a mutation that dispatches.
  • Shared logic: extract to src/utils/ the moment two handlers need it.

Reference Selection Guide

TaskReference
Any new handler (mandatory read)references/resilience.md
Macros, context, errors, configuration, CLIreferences/api.md
Backend patterns: jobs, workflows, auth, webhooks, compile loopreferences/patterns.md
Copy-paste recipes (user fetch, plan gating, email, S3, payments, AI)references/recipes.md
Frontend principles (reactivity, subscriptions, errors, uploads)references/frontend.md
SvelteKit specifics (runes, stores, auth helper)references/frontend/svelte.md
Dioxus specifics (hooks, signals, auth keying)references/frontend/dioxus.md
Writing tests (backend builders + Playwright scenarios)references/testing.md
Debugging build or runtime errorsreferences/pitfalls.md

Engineering Principles

  • Design for failure: auth drops, entities vanish, networks fail. See resilience.md.
  • Zero dead code: delete unused code and replaced patterns entirely. Workspace lints deny dead_code, unwrap_used, panic, indexing_slicing, unsafe_code.
  • Surgical diffs: thin vertical slice per PR.
  • Boundary validation: validate at handler entry, return ForgeError variants (never unwrap/expect/panic!).
  • Scope enforcement (compile-time enforced by the macro): private queries must filter by user_id / owner_id. ctx.user_id() for the principal. Opt out with #[query(unscoped)] only for shared/admin data.
  • Transactional dispatch (compile-time enforced): dispatch_job and start_workflow require a transactional mutation. Since transactions are on by default, just don't set transactional = false on mutations that dispatch.
  • System tables are off-limits (forge check enforced): never INSERT/UPDATE/DELETE on forge_* tables. Use dispatch_job, start_workflow, record_signal.
  • Migrations: -- @up / -- @down markers. Enable reactivity with SELECT forge_enable_reactivity('table_name');. No IF NOT EXISTS.
  • Not-found handling: fetch_optional().await?.ok_or_else(|| ForgeError::NotFound(format!(...))).

Output Contract

On completion, report:

  • Changes: files touched, failure modes handled, tests added (include failure paths).
  • Verification: commands run, blockers, final forge check result.
  • Review: resilience gaps, assumptions.

Every handler must survive revoked auth, deleted entities, concurrent modification, and network drops.

平台分布

Codex

38.87%
按下载量换算2,290

Claude

29.72%
按下载量换算1,751

Cursor

19.32%
按下载量换算1,138

Gemini CLI

8.82%
按下载量换算520

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

操作浏览器

该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills