pp-sec-edgar

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese
<!-- GENERATED FILE — DO NOT EDIT. This file is a verbatim mirror of library/developer-tools/sec-edgar/SKILL.md, regenerated post-merge by tools/generate-skills/. Hand-edits here are silently overwritten on the next regen. Edit the library/ source instead. See AGENTS.md "Generated artifacts: registry.json, cli-skills/". -->
<!-- 生成文件 — 请勿编辑。 此文件是library/developer-tools/sec-edgar/SKILL.md的完全镜像, 在合并后由tools/generate-skills/重新生成。此处的手动编辑会在下次重新生成时被自动覆盖。请改为编辑library/源文件。 请参阅AGENTS.md中的“生成产物:registry.json, cli-skills/”。 -->

SEC EDGAR — Printing Press CLI

SEC EDGAR — Printing Press CLI

Prerequisites: Install the CLI

前提条件:安装CLI

This skill drives the
sec-edgar-pp-cli
binary. You must verify the CLI is installed before invoking any command from this skill. If it is missing, install it first:
  1. Install via the Printing Press installer:
    bash
    npx -y @mvanhorn/printing-press install sec-edgar --cli-only
  2. Verify:
    sec-edgar-pp-cli --version
  3. Ensure
    $GOPATH/bin
    (or
    $HOME/go/bin
    ) is on
    $PATH
    .
If the
npx
install fails (no Node, offline, etc.), fall back to a direct Go install (requires Go 1.26.3 or newer):
bash
go install github.com/mvanhorn/printing-press-library/library/developer-tools/sec-edgar/cmd/sec-edgar-pp-cli@latest
If
--version
reports "command not found" after install, the install step did not put the binary on
$PATH
. Do not proceed with skill commands until verification succeeds.
An agent-native CLI for the entire SEC EDGAR surface — data.sec.gov XBRL, efts.sec.gov full-text search, and the live Atom feed. The synced SQLite store enables joins no single SEC endpoint supports: insider-cluster detection across issuers, XBRL peer-group benchmarks by SIC, 13F holdings deltas across quarters, and live filing watches with multi-dimensional filters. All free — SEC provides no API key, just a mandatory User-Agent header.
本Skill驱动
sec-edgar-pp-cli
二进制文件。在调用本Skill的任何命令之前,你必须确认CLI已安装。 如果未安装,请先执行以下步骤安装:
  1. 通过Printing Press安装程序安装:
    bash
    npx -y @mvanhorn/printing-press install sec-edgar --cli-only
  2. 验证安装:
    sec-edgar-pp-cli --version
  3. 确保
    $GOPATH/bin
    (或
    $HOME/go/bin
    )已添加到
    $PATH
    环境变量中。
如果
npx
安装失败(无Node环境、离线等情况),可以回退到直接使用Go安装(要求Go 1.26.3或更高版本):
bash
go install github.com/mvanhorn/printing-press-library/library/developer-tools/sec-edgar/cmd/sec-edgar-pp-cli@latest
如果安装后执行
--version
提示“command not found”,说明安装步骤未将二进制文件添加到
$PATH
中。在验证成功前,请不要继续执行Skill命令。
这是一款原生支持Agent的CLI工具,覆盖SEC EDGAR的全功能范围——包括data.sec.gov的XBRL数据、efts.sec.gov的全文搜索,以及实时Atom订阅源。同步后的SQLite存储支持单个SEC端点无法实现的关联查询:跨发行人的内幕交易集群检测、按SIC分类的XBRL同行组基准、跨季度的13F持仓变化,以及支持多维过滤的实时文件监控。所有功能完全免费——SEC不要求API密钥,仅需设置必填的User-Agent请求头。

When to Use This CLI

何时使用此CLI

Pick this CLI when an agent needs to query SEC filings, XBRL financial facts, insider trading (Form 4), or institutional holdings (13F) across many companies or many periods — anything that benefits from a local SQLite store rather than a per-call API roundtrip. For one-off single-filing reads, the typed endpoint mirrors (filings get, facts get) work without sync. For cross-company pivots, insider clustering, peer-group benchmarks, or live filing watches, the transcendence commands turn what would be ten API calls + a Python loop into one CLI invocation.
当Agent需要跨多家公司或多个时间段查询SEC文件、XBRL财务数据、内幕交易(Form 4)或机构持仓(13F)时,选择此CLI——任何受益于本地SQLite存储而非每次调用API往返的场景都适用。对于一次性单文件读取,类型化端点镜像(filings get、facts get)无需同步即可使用。对于跨公司数据透视、内幕交易集群分析、同行组基准对比或实时文件监控,相关命令可以将原本需要十次API调用加Python循环的操作简化为一次CLI调用。

When Not to Use This CLI

何时不使用此CLI

Do not activate this CLI for requests that require creating, updating, deleting, publishing, commenting, upvoting, inviting, ordering, sending messages, booking, purchasing, or changing remote state. This printed CLI exposes read-only commands for inspection, export, sync, and analysis.
请勿针对需要创建、更新、删除、发布、评论、点赞、邀请、下单、发送消息、预订、购买或更改远程状态的请求激活此CLI。本CLI仅提供用于检查、导出、同步和分析的只读命令。

Unique Capabilities

独特功能

These capabilities aren't available in any other tool for this API.
这些功能是其他同类型API工具所不具备的。

Local state that compounds

可累积的本地状态

  • watchlist items
    — Across a saved watchlist of CIKs, surface 8-Ks filed in the window grouped by Item code (2.05 restructuring, 5.02 exec change, 4.02 non-reliance).
    Equity analysts triage filings by Item code, not by company. Pick this when an agent needs cross-company 8-K filtering by Item.
    bash
    sec-edgar-pp-cli watchlist items --since 30d --item 2.05,5.02,4.02 --cik 0000320193,0000789019,0001652044 --json
  • insider-cluster
    — Flag issuers where 3+ distinct insiders filed Form 4 with the same transaction code (open-market buy or sale) within a rolling N-day window.
    Clustered insider selling is a textbook forensic signal. Pick this when an agent needs derived signals over raw Form 4 data.
    bash
    sec-edgar-pp-cli insider-cluster --within 5d --min-insiders 3 --code S --since 90d --json
  • industry-bench
    — Take an XBRL concept for one reporting period, group by SIC code, and emit percentile statistics (p10/p50/p90) across every public-company filer in that SIC.
    Quant researchers and equity analysts need peer-group benchmarks. Pick this when an agent should answer 'how does X compare to its industry peers'.
    bash
    sec-edgar-pp-cli industry-bench --tag us-gaap:Revenues --period CY2024Q4 --sic 7372 --stat p50,p90 --json
  • cross-section
    — Pivot a single XBRL concept across an explicit company list and the last N reporting periods. Output as a wide pivot table (one row per company, one column per period).
    Comp-set analysis is one of the highest-frequency analyst rituals. Pick this when an agent compares fundamentals across an explicit ticker list.
    bash
    sec-edgar-pp-cli cross-section --tag us-gaap:Revenues --ticker AAPL,MSFT,GOOGL --periods last8 --json
  • holdings delta
    — Diff an institutional investor's 13F holdings across two consecutive quarters. Categorize each issuer as ADD / EXIT / INCREASE / DECREASE with share-count delta.
    Tracking institutional money flow is a classic factor signal. Pick this when an agent compares a fund's positioning across quarters.
    bash
    sec-edgar-pp-cli holdings delta --filer-cik 0001067983 --period 2024Q4 --vs 2024Q3 --json
  • watchlist items
    — 在已保存的CIK观察列表中,按Item代码(2.05重组、5.02高管变动、4.02不再依赖前期财报)分组展示指定时间窗口内提交的8-K文件。
    股票分析师会按Item代码而非公司来筛选文件。当Agent需要跨公司按Item代码过滤8-K文件时,选择此功能。
    bash
    sec-edgar-pp-cli watchlist items --since 30d --item 2.05,5.02,4.02 --cik 0000320193,0000789019,0001652044 --json
  • insider-cluster
    — 标记在滚动N天窗口内有3名以上不同内部人员提交相同交易代码(公开市场买入或卖出)Form 4文件的发行人。
    集中式内幕交易是典型的法务信号。当Agent需要从原始Form 4数据中提取衍生信号时,选择此功能。
    bash
    sec-edgar-pp-cli insider-cluster --within 5d --min-insiders 3 --code S --since 90d --json
  • industry-bench
    — 获取某一报告期的XBRL概念数据,按SIC代码分组,并输出该SIC分类下所有上市公司的百分位统计数据(p10/p50/p90)。
    量化研究员和股票分析师需要同行组基准数据。当Agent需要回答“X与其行业同行相比表现如何”这类问题时,选择此功能。
    bash
    sec-edgar-pp-cli industry-bench --tag us-gaap:Revenues --period CY2024Q4 --sic 7372 --stat p50,p90 --json
  • cross-section
    — 在指定公司列表和最近N个报告期内对单个XBRL概念进行数据透视。输出为宽格式透视表(每行代表一家公司,每列代表一个报告期)。
    竞品分析是分析师最频繁的工作之一。当Agent需要对比指定股票列表的基本面数据时,选择此功能。
    bash
    sec-edgar-pp-cli cross-section --tag us-gaap:Revenues --ticker AAPL,MSFT,GOOGL --periods last8 --json
  • holdings delta
    — 对比机构投资者连续两个季度的13F持仓变化。将每个发行人归类为新增/退出/增持/减持,并显示股份数量变化。
    追踪机构资金流向是经典的因子信号。当Agent需要对比基金不同季度的持仓情况时,选择此功能。
    bash
    sec-edgar-pp-cli holdings delta --filer-cik 0001067983 --period 2024Q4 --vs 2024Q3 --json

Agent-native plumbing

原生Agent适配

  • watch
    — Stream the SEC Atom getcurrent feed with multi-dimensional filtering: form type, 8-K item, CIK watchlist, and keyword regex. Emits one NDJSON line per match.
    Agents that monitor for specific filing events should subscribe to this stream rather than polling submissions per CIK.
    bash
    sec-edgar-pp-cli watch --form 8-K --item 2.05 --cik 0000320193,0000789019 --keyword 'going concern' --one-shot --json
  • watch
    — 流式获取SEC Atom getcurrent订阅源,并支持多维过滤:文件类型、8-K Item、CIK观察列表和关键词正则表达式。匹配到结果时输出一行NDJSON数据。
    需要监控特定文件事件的Agent应订阅此流,而非按CIK轮询提交记录。
    bash
    sec-edgar-pp-cli watch --form 8-K --item 2.05 --cik 0000320193,0000789019 --keyword 'going concern' --one-shot --json

SEC-specific signals

SEC专属信号

  • restatements
    — Surface 8-K Item 4.02 (non-reliance on prior financials) plus all 10-K/A and 10-Q/A amendments filed in the window — the textbook accounting-irregularity signal.
    Forensic accounting agents look for restatements as a leading indicator of trouble. Pick this when an agent needs accounting-quality signals.
    bash
    sec-edgar-pp-cli restatements --since 90d --json
  • late-filers
    — Find issuers that filed an NT 10-K, NT 10-Q, or NT 20-F in the window — the SEC's 'I'm going to miss my reporting deadline' notification.
    Late filings are leading indicators of operational or accounting trouble. Pick this when an agent needs to flag at-risk companies.
    bash
    sec-edgar-pp-cli late-filers --since 90d --form 10-K --json
  • restatements
    — 展示指定时间窗口内提交的8-K Item 4.02(不再依赖前期财报)以及所有10-K/A和10-Q/A修订文件——这是典型的会计违规信号。
    法务会计Agent会将财报重述视为潜在风险的领先指标。当Agent需要会计质量信号时,选择此功能。
    bash
    sec-edgar-pp-cli restatements --since 90d --json
  • late-filers
    — 查找在指定时间窗口内提交NT 10-K、NT 10-Q或NT 20-F文件的发行人——这是SEC规定的“将错过报告截止日期”的通知文件。
    延迟提交文件是运营或会计问题的领先指标。当Agent需要标记高风险公司时,选择此功能。
    bash
    sec-edgar-pp-cli late-filers --since 90d --form 10-K --json

Command Reference

命令参考

companies — Company directory (ticker → CIK → name)
  • sec-edgar-pp-cli companies tickers
    — Full ticker-to-CIK map for every public-equity issuer with a listed ticker (~10k entries)
  • sec-edgar-pp-cli companies tickers_exchange
    — Ticker-to-CIK map keyed by exchange (Nasdaq, NYSE, etc.)
  • sec-edgar-pp-cli companies tickers_mf
    — Mutual fund ticker-to-CIK map (one row per share class)
facts — XBRL financial facts (data.sec.gov)
  • sec-edgar-pp-cli facts company
    — Get all XBRL facts for a company across every reporting period
  • sec-edgar-pp-cli facts frame
    — Get one XBRL concept value reported by every public filer for one period (cross-company slice)
  • sec-edgar-pp-cli facts get
    — Get a single XBRL concept time series for one company (one tag across all of its filings)
submissions — Filer (company) filing history
  • sec-edgar-pp-cli submissions <cik>
    — Get full submissions history for a filer by 10-digit zero-padded CIK
companies — 公司目录(股票代码 → CIK → 公司名称)
  • sec-edgar-pp-cli companies tickers
    — 获取所有上市发行人的股票代码到CIK的完整映射(约10000条记录)
  • sec-edgar-pp-cli companies tickers_exchange
    — 按交易所(纳斯达克、纽交所等)分类的股票代码到CIK映射
  • sec-edgar-pp-cli companies tickers_mf
    — 共同基金股票代码到CIK映射(每个份额类别对应一行)
facts — XBRL财务数据(data.sec.gov)
  • sec-edgar-pp-cli facts company
    — 获取某家公司所有报告期的全部XBRL数据
  • sec-edgar-pp-cli facts frame
    — 获取所有公开发行人在某一报告期内的某一XBRL概念数据(跨公司切片)
  • sec-edgar-pp-cli facts get
    — 获取某家公司单个XBRL概念的时间序列数据(某一标签在其所有文件中的数据)
submissions — 申报人(公司)的文件提交历史
  • sec-edgar-pp-cli submissions <cik>
    — 通过10位补零的CIK获取申报人的完整提交历史

Finding the right command

查找合适的命令

When you know what you want to do but not which command does it, ask the CLI directly:
bash
sec-edgar-pp-cli which "<capability in your own words>"
which
resolves a natural-language capability query to the best matching command from this CLI's curated feature index. Exit code
0
means at least one match; exit code
2
means no confident match — fall back to
--help
or use a narrower query.
当你知道要执行的操作但不知道对应命令时,可以直接询问CLI:
bash
sec-edgar-pp-cli which "<用你自己的话描述所需功能>"
which
命令会将自然语言的功能查询解析为CLI精选功能索引中最匹配的命令。退出码
0
表示至少找到一个匹配项;退出码
2
表示没有可信匹配项——此时可以回退到使用
--help
或缩小查询范围。

Recipes

使用示例

Apple income-statement trend, agent-friendly

苹果公司利润表趋势(Agent友好格式)

bash
sec-edgar-pp-cli facts statement --cik 0000320193 --kind income --periods last8 --agent --select 'facts.us-gaap.Revenues,facts.us-gaap.OperatingIncomeLoss,facts.us-gaap.NetIncomeLoss'
XBRL responses are deeply nested; --select with dotted paths picks only the three concepts the agent needs across the last 8 periods.
bash
sec-edgar-pp-cli facts statement --cik 0000320193 --kind income --periods last8 --agent --select 'facts.us-gaap.Revenues,facts.us-gaap.OperatingIncomeLoss,facts.us-gaap.NetIncomeLoss'
XBRL响应结构嵌套较深;使用--select和点路径仅保留Agent需要的三个概念在最近8个报告期的数据。

Cluster-buying watchlist scan

观察列表集中买入扫描

bash
sec-edgar-pp-cli insider-cluster --within 14d --min-insiders 3 --code P --since 90d --json
Open-market insider buying (Form 4 code P) clustered across 3+ insiders in 14 days, last 90 days. The store-backed JOIN is what makes this one command.
bash
sec-edgar-pp-cli insider-cluster --within 14d --min-insiders 3 --code P --since 90d --json
查找最近90天内,14天窗口中有3名以上内部人员集中进行公开市场买入(Form 4代码P)的情况。基于存储的关联查询是此命令能实现该功能的关键。

Quarterly comp-set revenue pivot

季度竞品收入透视

bash
sec-edgar-pp-cli cross-section --tag us-gaap:Revenues --cik 0000320193,0000789019,0001652044 --periods last8 --json
Apple vs Microsoft vs Alphabet revenue, last 8 quarters, as a single pivot. Both axes constrained — neither edgartools nor the frames endpoint covers this shape.
bash
sec-edgar-pp-cli cross-section --tag us-gaap:Revenues --cik 0000320193,0000789019,0001652044 --periods last8 --json
对比苹果、微软和谷歌最近8个季度的收入,输出为单个透视表。此结构同时限制了两个维度——edgartools或frames端点均不支持此类查询。

Watchlist Monday triage

观察列表周一筛选

bash
sec-edgar-pp-cli watchlist items --since 30d --item 2.05,5.02,4.02 --cik 0000320193,0000789019,0001652044 --json --agent
Cross-CIK 8-K Item pivot — Maya's exact Monday ritual. The watchlist file is one CIK per line.
bash
sec-edgar-pp-cli watchlist items --since 30d --item 2.05,5.02,4.02 --cik 0000320193,0000789019,0001652044 --json --agent
跨CIK的8-K Item透视——这正是Maya每周一的常规工作流程。观察列表文件为每行一个CIK。

Late-filer compliance scan

延迟提交合规扫描

bash
sec-edgar-pp-cli late-filers --since 60d --form 10-K --json
Surfaces NT 10-K filings (companies that warned they'd miss their reporting deadline). Single SELECT against the local filings table.
bash
sec-edgar-pp-cli late-filers --since 60d --form 10-K --json
展示NT 10-K文件(即警告将错过报告截止日期的公司)。只需对本地文件表执行一次查询即可完成。

Auth Setup

认证设置

SEC EDGAR requires no API key. Every request must include a User-Agent header naming a human and contact email (e.g. 'Alex Researcher alex@example.com'). Set SEC_EDGAR_USER_AGENT in your environment; the CLI refuses to run without it. The SEC enforces a 10-req/sec rate cap per host; this CLI caps itself at 8 req/sec with jitter.
Run
sec-edgar-pp-cli doctor
to verify setup.
SEC EDGAR不需要API密钥。每个请求必须包含一个User-Agent请求头,注明联系人姓名和邮箱(例如:'Alex Researcher alex@example.com')。请在环境变量中设置SEC_EDGAR_USER_AGENT;如果未设置,CLI将无法运行。SEC对每个主机强制执行每秒10次请求的速率限制;本CLI将自身速率限制为每秒8次请求,并添加了随机抖动。
执行
sec-edgar-pp-cli doctor
验证设置是否正确。

Agent Mode

Agent模式

Add
--agent
to any command. Expands to:
--json --compact --no-input --no-color --yes
.
  • Pipeable — JSON on stdout, errors on stderr
  • Filterable
    --select
    keeps a subset of fields. Dotted paths descend into nested structures; arrays traverse element-wise. Critical for keeping context small on verbose APIs:
    bash
    sec-edgar-pp-cli facts get --cik example-value --taxonomy example-value --tag example-value --agent --select id,name,status
  • Previewable
    --dry-run
    shows the request without sending
  • Offline-friendly — sync/search commands can use the local SQLite store when available
  • Non-interactive — never prompts, every input is a flag
  • Read-only — do not use this CLI for create, update, delete, publish, comment, upvote, invite, order, send, or other mutating requests
在任何命令后添加
--agent
参数。该参数等价于:
--json --compact --no-input --no-color --yes
  • 可管道化 — 标准输出为JSON,错误信息输出到标准错误
  • 可过滤
    --select
    参数保留字段子集。点路径可深入嵌套结构;数组会遍历每个元素。这对于在冗长API中缩小上下文范围至关重要:
    bash
    sec-edgar-pp-cli facts get --cik example-value --taxonomy example-value --tag example-value --agent --select id,name,status
  • 可预览
    --dry-run
    参数显示请求内容但不发送
  • 离线友好 — 同步/搜索命令在可用时可以使用本地SQLite存储
  • 非交互式 — 从不弹出提示,所有输入均通过参数传递
  • 只读 — 请勿使用此CLI执行创建、更新、删除、发布、评论、点赞、邀请、下单、发送或其他变更状态的请求

Response envelope

响应信封

Commands that read from the local store or the API wrap output in a provenance envelope:
json
{
  "meta": {"source": "live" | "local", "synced_at": "...", "reason": "..."},
  "results": <data>
}
Parse
.results
for data and
.meta.source
to know whether it's live or local. A human-readable
N results (live)
summary is printed to stderr only when stdout is a terminal — piped/agent consumers get pure JSON on stdout.
从本地存储或API读取数据的命令会将输出包装在来源信封中:
json
{
  "meta": {"source": "live" | "local", "synced_at": "...", "reason": "..."},
  "results": <data>
}
解析
.results
字段获取数据,
.meta.source
字段表示数据是实时获取还是来自本地存储。只有当标准输出为终端时,才会在标准错误中打印人类可读的
N results (live)
摘要;管道/Agent消费者只会在标准输出中获取纯JSON数据。

Agent Feedback

Agent反馈

When you (or the agent) notice something off about this CLI, record it:
sec-edgar-pp-cli feedback "the --since flag is inclusive but docs say exclusive"
sec-edgar-pp-cli feedback --stdin < notes.txt
sec-edgar-pp-cli feedback list --json --limit 10
Entries are stored locally at
~/.sec-edgar-pp-cli/feedback.jsonl
. They are never POSTed unless
SEC_EDGAR_FEEDBACK_ENDPOINT
is set AND either
--send
is passed or
SEC_EDGAR_FEEDBACK_AUTO_SEND=true
. Default behavior is local-only.
Write what surprised you, not a bug report. Short, specific, one line: that is the part that compounds.
当你(或Agent)发现此CLI存在问题时,可以记录反馈:
sec-edgar-pp-cli feedback "the --since flag is inclusive but docs say exclusive"
sec-edgar-pp-cli feedback --stdin < notes.txt
sec-edgar-pp-cli feedback list --json --limit 10
反馈条目会本地存储在
~/.sec-edgar-pp-cli/feedback.jsonl
中。除非设置了
SEC_EDGAR_FEEDBACK_ENDPOINT
且传递了
--send
参数或设置
SEC_EDGAR_FEEDBACK_AUTO_SEND=true
,否则反馈不会被POST到远程服务器。默认行为仅本地存储。
请记录让你感到意外的内容,而非正式的错误报告。简短、具体、单行描述:这样的反馈才更有价值。

Output Delivery

输出交付

Every command accepts
--deliver <sink>
. The output goes to the named sink in addition to (or instead of) stdout, so agents can route command results without hand-piping. Three sinks are supported:
SinkEffect
stdout
Default; write to stdout only
file:<path>
Atomically write output to
<path>
(tmp + rename)
webhook:<url>
POST the output body to the URL (
application/json
or
application/x-ndjson
when
--compact
)
Unknown schemes are refused with a structured error naming the supported set. Webhook failures return non-zero and log the URL + HTTP status on stderr.
每个命令都支持
--deliver <sink>
参数。输出会发送到指定的接收端,同时(或替代)输出到标准输出,因此Agent无需手动管道即可路由命令结果。支持三种接收端:
接收端效果
stdout
默认值;仅输出到标准输出
file:<path>
原子性地将输出写入
<path>
(先写入临时文件再重命名)
webhook:<url>
将输出主体POST到指定URL(当使用
--compact
时,内容类型为
application/json
application/x-ndjson
不支持的协议会返回结构化错误,并列出支持的类型。Webhook失败时会返回非零退出码,并在标准错误中记录URL和HTTP状态码。

Named Profiles

命名配置文件

A profile is a saved set of flag values, reused across invocations. Use it when a scheduled agent calls the same command every run with the same configuration - HeyGen's "Beacon" pattern.
sec-edgar-pp-cli profile save briefing --json
sec-edgar-pp-cli --profile briefing facts get --cik example-value --taxonomy example-value --tag example-value
sec-edgar-pp-cli profile list --json
sec-edgar-pp-cli profile show briefing
sec-edgar-pp-cli profile delete briefing --yes
Explicit flags always win over profile values; profile values win over defaults.
agent-context
lists all available profiles under
available_profiles
so introspecting agents discover them at runtime.
配置文件是一组保存的参数值,可在多次调用中复用。当定时Agent每次运行都使用相同配置调用同一命令时,可以使用此功能——即HeyGen的“Beacon”模式。
sec-edgar-pp-cli profile save briefing --json
sec-edgar-pp-cli --profile briefing facts get --cik example-value --taxonomy example-value --tag example-value
sec-edgar-pp-cli profile list --json
sec-edgar-pp-cli profile show briefing
sec-edgar-pp-cli profile delete briefing --yes
显式参数始终优先于配置文件中的值;配置文件中的值优先于默认值。
agent-context
会在
available_profiles
下列出所有可用配置文件,因此Agent可以在运行时自动发现这些配置。

Exit Codes

退出码

CodeMeaning
0Success
2Usage error (wrong arguments)
3Resource not found
4Authentication required
5API error (upstream issue)
7Rate limited (wait and retry)
10Config error
代码含义
0成功
2使用错误(参数错误)
3资源未找到
4需要认证
5API错误(上游问题)
7速率限制(请等待后重试)
10配置错误

Argument Parsing

参数解析

Parse
$ARGUMENTS
:
  1. Empty,
    help
    , or
    --help
    → show
    sec-edgar-pp-cli --help
    output
  2. Starts with
    install
    → ends with
    mcp
    → MCP installation; otherwise → see Prerequisites above
  3. Anything else → Direct Use (execute as CLI command with
    --agent
    )
解析
$ARGUMENTS
的规则:
  1. 为空、
    help
    --help
    → 显示
    sec-edgar-pp-cli --help
    输出
  2. install
    开头
    → 如果结尾为
    mcp
    → 安装MCP;否则 → 参见上方前提条件中的安装步骤
  3. 其他情况 → 直接使用(添加
    --agent
    参数执行CLI命令)

MCP Server Installation

MCP服务器安装

  1. Install the MCP server:
    bash
    go install github.com/mvanhorn/printing-press-library/library/developer-tools/sec-edgar/cmd/sec-edgar-pp-mcp@latest
  2. Register with Claude Code:
    bash
    claude mcp add sec-edgar-pp-mcp -- sec-edgar-pp-mcp
  3. Verify:
    claude mcp list
  1. 安装MCP服务器:
    bash
    go install github.com/mvanhorn/printing-press-library/library/developer-tools/sec-edgar/cmd/sec-edgar-pp-mcp@latest
  2. 在Claude Code中注册:
    bash
    claude mcp add sec-edgar-pp-mcp -- sec-edgar-pp-mcp
  3. 验证:
    claude mcp list

Direct Use

直接使用

  1. Check if installed:
    which sec-edgar-pp-cli
    If not found, offer to install (see Prerequisites at the top of this skill).
  2. Match the user query to the best command from the Unique Capabilities and Command Reference above.
  3. Execute with the
    --agent
    flag:
    bash
    sec-edgar-pp-cli <command> [subcommand] [args] --agent
  4. If ambiguous, drill into subcommand help:
    sec-edgar-pp-cli <command> --help
    .
  1. 检查是否已安装:
    which sec-edgar-pp-cli
    如果未找到,提供安装选项(参见本文档开头的前提条件)。
  2. 将用户查询与上方独特功能和命令参考中最匹配的命令进行匹配。
  3. 添加
    --agent
    参数执行命令:
    bash
    sec-edgar-pp-cli <command> [subcommand] [args] --agent
  4. 如果存在歧义,查看子命令帮助:
    sec-edgar-pp-cli <command> --help
    。",