explainability-for-live-trading-signals SKILL.md skillA
explainability-for-live-trading-signals from himanshuj16/algo-trading-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add himanshuj16/algo-trading-skills/explainability-for-live-trading-signals@v2.0.0Pins v2.0.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- himanshuj16/algo-trading-skills
- Path
skills/explainability-for-live-trading-signals/SKILL.md- Versions recorded
- 5
- Latest version
- v2.0.0, committed Sep 3, 2026
- First version recorded
- Jul 24, 2026
- Size
- 10,637 bytes
- Repository stars
- 50
- License
- Apache-2.0
Use when a live model score must later be explained to a risk officer or model reviewer; reconciles supplied feature attributions against the score the model actually emitted, ranks the drivers and writes a readable audit record.
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
## When to Use
Invoke this whenever a black-box or complex quantitative model emits live trading signals and someone — a risk officer during an incident, a model-governance reviewer, a supervisor requesting records — will later need to know *which inputs produced this specific score*. A raw $+0.82$ Buy with no attribution is unreviewable after the fact.
The skill consumes an attribution vector $\{\phi_i\}$ produced by an upstream explainer (SHAP, Captum, an EBM shape function, or a linear model's $w_i x_i$), **reconciles it against the score the model actually emitted**, ranks the drivers, narrates them, and writes an append-only audit record. Reconciliation is the point: an attribution vector that does not reproduce the model's output is not an explanation of that signal, and a log full of unreconciled explanations is worse than no log because it looks authoritative.
## When NOT to Use
- **As a substitute for computing attributions.** This module does not run SHAP. If you have no $\phi_i$, you have nothing to reconcile.
…Read the whole file at its exact version.
How to install
mdr add himanshuj16/algo-trading-skills/explainability-for-live-trading-signals@sha256:117b8b723abc2dadThe line at the top of this page pins the label v2.0.0, 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_ixe5uc7rxfv7bmp2)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Jul 24, 2026 and Sep 3, 2026, about one every 10 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v2.0.0 latest | 2026-09-03 | 8527a51 | 10,637 B | A | view · diff |
| v2.0.0 | 2026-08-25 | 7e72405 | 10,614 B | A | view · diff |
| v1.0.0 | 2026-08-07 | 89d1436 | 3,751 B | A | view · diff |
| v1.0 | 2026-07-30 | dfc60c7 | 3,749 B | A | view · diff |
| v1.0 | 2026-07-24 | 707e275 | 3,762 B | A | view |
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 (10637 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
himanshuj16/algo-trading-skills · 50 stars · license Apache-2.0 · pushed 2026-09-14 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ixe5uc7rxfv7bmp2 GET https://markdownregistry.com/api/v1/resolve?ref=himanshuj16/algo-trading-skills/explainability-for-live-trading-signals GET https://markdownregistry.com/api/v1/blob/117b8b723abc2dadd4f39d98ac99570700d52aaf0e313118b077e77c48a8a771
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.