xai-check SKILL.md skillA
xai-check from haabe/mycelium is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add haabe/mycelium/xai-check@git:20261028.9a8e9a1Pins git:20261028.9a8e9a1 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- haabe/mycelium
- Path
plugins/mycelium/skills/xai-check/SKILL.md- Versions recorded
- 8
- Latest version
- git:20261028.9a8e9a1, committed Oct 28, 2026
- First version recorded
- May 22, 2026
- Size
- 13,880 bytes
- Repository stars
- 51
- License
- MIT
Explainability (XAI) audit for products containing AI components. Five-stage tier-scaled check: risk classification, stakeholder×question matrix, fidelity audit, system card, recourse path. Honest about what was validated functionally vs what needs user testing.
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
# XAI Check Skill Operational gate for the Explainability Theory Gate (Gate 13). Audits whether a product's AI components meet a defensible XAI bar — disclosure, decision-explanation, recourse, fidelity, system card — scaled to the AI Act risk tier. This skill is **functionally-grounded** in Doshi-Velez & Kim's (2017) sense: it operates on artifacts and configuration, not on real users with real tasks. Output explicitly distinguishes `validated_functionally` from `needs_user_testing`. The honest tag is what passes Gate 13; user-grounded validation is recommended but not blocking. **The gate reads this skill's record (v0.331.0).** On a product with AI components detected, an Explainability pass counts only when a `services[].xai` block holds a verdict for each stage the scale asks: at an L3 the tier (Stage 1); at an L4 or L5 every stage, with `recourse.verdict` asked from the `limited` tier up. A stage that does not apply takes a verdict saying so (`not_applicable`). The scale-lock gate and the release gate name the stage that is missing. Until 0.331.0 the gate passed on the status word. ## When to Use …
Read the whole file at its exact version.
How to install
mdr add haabe/mycelium/xai-check@sha256:3506feb2be897d99The line at the top of this page pins the label git:20261028.9a8e9a1, 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_lpn5cm5srsixpbld)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 8 versions of this file, between May 22, 2026 and Oct 28, 2026, about one every 23 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261028.9a8e9a1 latest | 2026-10-28 | 9a8e9a1 | 13,880 B | A | view · diff |
| git:20261007.33e0656 | 2026-10-07 | 33e0656 | 13,362 B | A | view · diff |
| git:20261001.39266c6 | 2026-10-01 | 39266c6 | 13,347 B | A | view · diff |
| git:20260726.151b371 | 2026-07-26 | 151b371 | 13,365 B | A | view · diff |
| git:20260704.7639f18 | 2026-07-04 | 7639f18 | 13,266 B | A | view · diff |
| git:20260605.3fd0a52 | 2026-06-05 | 3fd0a52 | 13,266 B | A | view · diff |
| git:20260525.9fac942 | 2026-05-25 | 9fac942 | 12,411 B | A | view · diff |
| git:20260522.1825b22 | 2026-05-22 | 1825b22 | 12,101 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 (13880 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
haabe/mycelium · 51 stars · license MIT · pushed 2026-11-06 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_lpn5cm5srsixpbld GET https://markdownregistry.com/api/v1/resolve?ref=haabe/mycelium/xai-check GET https://markdownregistry.com/api/v1/blob/3506feb2be897d99e279bff7b7d1501da1234d34752c0a355efd0f5f3ee6b8b1
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.