earnings-analysis SKILL.md skillA
This file is byte-identical to the first copy the registry indexed. Same content hash, so the same checks give both the same grade.
earnings-analysis from hhfinai/claude-equity-research-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add hhfinai/claude-equity-research-skills/earnings-analysis@v1.4.1Pins v1.4.1 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- hhfinai/claude-equity-research-skills
- Path
earnings-analysis/SKILL.md- Versions recorded
- 1
- Latest version
- v1.4.1, committed Apr 15, 2026
- Size
- 24,555 bytes
- Repository stars
- 10
- License
- MIT
Institutional-quality earnings analysis for public equities. Parses 10-Qs, earnings releases, and call transcripts into a 4-layer framework (Parse → Compare → Diagnose → Decide), runs a mechanical scoring engine that produces a composite verdict across beat quality, operational health, and management signals, and outputs a one-page earnings sheet, full memo (Word doc), risk map, or trade note. Use when asked to analyse earnings, review quarterly results, parse a 10-Q, summarise an earnings…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Earnings Analysis: Institutional-Quality Quarterly Review Framework ## Overview This skill transforms raw earnings materials (filings, releases, transcripts) into structured investment-grade analysis. It moves beyond simple beat/miss reporting to diagnose *why* results deviated, *what matters* for the forward thesis, and *what action* follows — the way a senior buyside analyst processes a quarter. **Philosophy**: The market doesn't pay for knowing what happened. It pays for knowing what changed, whether it's repeatable, and what's mispriced. Every earnings analysis must answer: "So what? What do I do now?" **Two-part architecture.** The skill is a four-layer analytical framework (Parse → Compare → Diagnose → Decide) anchored by a Python scoring engine at `scripts/score_earnings.py` that produces a mechanical composite verdict, flag inventory, and expectations regime classification. The scorer runs at the end of Step 2 and anchors the judgment work in Steps 3 and 4 — it is an input to the diagnosis, not a replacement for it. ## Input Types & Parsing Priority The skill handles these inputs, in priority order: | Input Type | What to Extract | How to Access | …
Read the whole file at its exact version.
How to install
mdr add hhfinai/claude-equity-research-skills/earnings-analysis@sha256:c4995eff7938d9ecThe line at the top of this page pins the label v1.4.1, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_7t63hcy5kkzvnqwq)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Apr 15, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (24555 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
hhfinai/claude-equity-research-skills · 10 stars · license MIT · pushed 2026-10-21 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_7t63hcy5kkzvnqwq GET https://markdownregistry.com/api/v1/resolve?ref=hhfinai/claude-equity-research-skills/earnings-analysis GET https://markdownregistry.com/api/v1/blob/c4995eff7938d9ec0287636455030d3e306d9274142b928098ca8a4700a90169
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from hhfinai/claude-equity-research-skills
Every file in hhfinai/claude-equity-research-skills