pp-edgar
An agent-native CLI for SEC EDGAR — six sanctioned endpoints, SQLite-cached filings with FTS5, and LODESTAR-shaped... Trigger phrases: `primary sources for <ticker>`, `insider summary <ticker>`, `recheck delta for <ticker>`, `eightk items <ticker>`, `xbrl pivot`, `use edgar-pp-cli`, `run edgar`.
What this skill does
<!-- GENERATED FILE — DO NOT EDIT.
This file is a verbatim mirror of library/other/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 the repository agent guide, section "Generated artifacts: registry.json, cli-skills/". -->
# SEC EDGAR — Printing Press CLI
## Prerequisites: Install the CLI
This skill drives the `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. It defaults binaries to `$HOME/.local/bin` on macOS/Linux and `%LOCALAPPDATA%\Programs\PrintingPress\bin` on Windows:
```bash
npx -y @mvanhorn/printing-press-library install edgar --cli-only
```
2. Verify: `edgar-pp-cli --version`
3. Ensure the reported install directory is on `$PATH` for the agent/runtime that will invoke this skill.
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/other/edgar/cmd/edgar-pp-cli@latest
```
If `--version` reports "command not found" after install, the runtime cannot see the binary directory on `$PATH`. Do not proceed with skill commands until verification succeeds.
## When to Use This CLI
Use edgar-pp-cli when an agent needs structured SEC filing data shaped for token-efficient consumption — primary-source bundles, insider-summary with S/F discrimination, cross-quarter MD&A diffs, or local FTS5 over cached filings. The compound primary-sources command is the LODESTAR shape: one call returns the full evidence pack for a Gate 1/2/3 thesis. Do not use this CLI for Federal Register searches, regulations.gov dockets, activist short reports, or NASDAQ short interest — those are out of scope and handled elsewhere.
## When Not to Use This CLI
Do not activate this CLI for requests that require creating, updating, deleting, publishing, commenting, upvoting, inviting, ordering, sending messages, booking, purchasing, or changing remote state. This printed CLI exposes read-only commands for inspection, export, sync, and analysis.
## Unique Capabilities
These capabilities aren't available in any other tool for this API.
### Local state that compounds
- **`since`** — Return only the filings filed since a given timestamp, using a per-CIK local cursor — the entire LODESTAR /$recheck loop in one call.
_For quarterly thesis rechecks, reach for this before fetching the full submissions index — it eliminates re-paying token cost on filings already seen._
```bash
edgar-pp-cli since AAPL --as-of 2026-05-08 --json
```
- **`fts`** — Full-text search over locally-cached filing bodies via FTS5 — ticker- and form-scoped — with snippet windows and byte offsets for precise re-read.
_Reach for fts during deep-dives where you re-query the same filing body multiple times; reach for the absorbed `efts` command for the first lookup or for cross-issuer queries._
```bash
edgar-pp-cli fts "going concern" --ticker AAPL --form 10-Q --json
```
### Service-specific content patterns
- **`eightk-items`** — Enumerate 8-Ks with parsed Item numbers and a --material-only flag that excludes exhibits-only (Item 9.01 alone) refilings.
_Use this instead of pulling 8-K bodies when you need 'has anything material happened?' — answers in one call without reading filing text._
```bash
edgar-pp-cli eightk-items AAPL --since 2026-05-08 --material-only --json
```
- **`ownership-crosses`** — Enumerate 13D and 13G filings against an issuer (when someone else crosses 5% of the ticker), with filer name, percent owned, and filed-at.
_Use in LODESTAR Gate 3 asymmetric-structure checks to spot activist or institutional concentration without scrolling submissions._
```bash
edgar-pp-cli ownership-crosses AAPL --json
```
- **`governance-flags`** — Compose three independent service-specific signals into one call: 8-K Item 4.01 auditor changes, Item 4.02 non-reliance restatements, and NT-10-K late-filing notices (Form 12b-25).
_Use as an early disqualifier check — if any flag fires, surface to LODESTAR before spending tokens on the full thesis._
```bash
edgar-pp-cli governance-flags AAPL --since 2y --json
```
### Cross-entity joins
- **`insider-followthrough`** — For every senior-officer code-S sale of ≥$1M, scan the next 90 days of 8-Ks for material items and emit (sale, subsequent material 8-K, days-between) pairs.
_Reach for this in LODESTAR Gate 2 execution-validation when an insider sale precedes material disclosures — surface management exits before bad news._
```bash
edgar-pp-cli insider-followthrough AAPL --json
```
**Form 4 ingest cap.** `insider-summary`, `insider-followthrough`, and `primary-sources` ingest Form 4 filings through a shared `--max-form4 N` cap (default `200`) that bounds DB/API pressure on high-volume filers. When the cap clips older filings, the output surfaces `form4_truncated: true` and `form4_total_in_window: <N>` under `form4_skipped` plus a stderr WARN — never silent. Pass `--max-form4 0` to disable; pass a larger value to widen the window.
- **`xbrl-pivot`** — Multi-ticker XBRL pivot that resolves concept aliases (Revenues ↔ RevenueFromContractWithCustomerExcludingAssessedTax ↔ SalesRevenueNet) into a flat ticker×quarter×concept table.
_For cross-sectional quality screens — pivot before parsing 50 companyfacts JSON blobs by hand._
```bash
edgar-pp-cli xbrl-pivot --tickers AAPL,MSFT,GOOGL --concepts Revenues,NetIncomeLoss --quarters 8 --csv
```
### Token-efficient extraction
- **`sections`** — Extract requested Items from a 10-K or 10-Q with byte-offset boundaries; emits ONLY the requested items in compact JSON instead of the full 100KB-10MB HTML body.
_Use this instead of fetching the raw 10-K body — saves an order of magnitude in tokens when you only need Risk Factors and MD&A._
```bash
edgar-pp-cli sections AAPL --form 10-K --items 1A,7,7A --json
```
## Command Reference
**companies** — Company identifiers (ticker → CIK) and per-issuer submissions index
- `edgar-pp-cli companies lookup` — Resolve ticker → CIK (and company name + SIC) from SEC's nightly index. Cache 24h in local SQLite.
- `edgar-pp-cli companies submissions` — Structured submissions index for a company (filing history with accession numbers, form types, filed-at).
**companyfacts** — XBRL company facts (financial concepts: revenue, net income, assets, cash flow, etc.) for a CIK
- `edgar-pp-cli companyfacts <cik>` — All XBRL company facts for a CIK. Optionally filter to a single concept client-side.
**efts** — EDGAR full-text search across all filings (efts.sec.gov). For offline FTS5 over cached filing bodies, use the offline `fts` command instead.
- `edgar-pp-cli efts <q>` — Online full-text search across EDGAR filings. For offline FTS5 over cached bodies, use `edgar-pp-cli fts`.
**filings** — Per-form-type filing retrieval and individual filing document fetch
- `edgar-pp-cli filings browse` — EDGAR filing index for a CIK + form type. Returns HTML/Atom; the generator wraps it but parsing happens in the...
- `edgar-pp-cli filings get` — Fetch raw filing index page or document for a specific accession. Accession must be the no-dashes form (e.g.,...
### Finding the right command
When you know what you want to do but not which command does it, ask the CLI directly:
```bash
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.
## Recipes
### Full LODESTAR research pull
```bash
edgar-pp-cli primary-sources AAPL --json --select shares_outstanding,senior_insider_saRelated in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.