nw-cross-cutting-evidence-instrumentation SKILL.md skillA
nw-cross-cutting-evidence-instrumentation from nwave-ai/nwave is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add nwave-ai/nwave/nw-cross-cutting-evidence-instrumentation@git:20261102.c67d57bPins git:20261102.c67d57b in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- nwave-ai/nwave
- Path
nWave/skills/nw-cross-cutting-evidence-instrumentation/SKILL.md- Versions recorded
- 1
- Latest version
- git:20261102.c67d57b, committed Nov 2, 2026
- Size
- 11,129 bytes
- Repository stars
- 633
- License
- MIT
KNOWLEDGE — use when evaluating a claim, check, measurement, or shared-log count.
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
# Evidence and Instrumentation **Composition:** Load with `nw-cross-cutting-invariants`; no forced sequence; return to its routing table for other concerns. ## `claim:falsify-before-asserting` — the cheapest check precedes the conclusion (STANDING) Before concluding that something cannot work, is missing, or is broken, run the cheapest check that would falsify that conclusion, then state only what the check showed. Name a cause only if you observed it — never infer one from a shared symptom. Absence in one place is not absence in the tree: measure on the scope the claim is actually ABOUT, not the subset you happened to look at (the enumerator gap above is the architectural form of this same failure). The asymmetry that justifies the discipline: the check costs seconds; an unfalsified conclusion, once acted on, costs an order of magnitude more to undo. ## `check:unfired-is-not-evidence` — a check you have not seen FAIL is not evidence (STANDING) A passing check has two indistinguishable explanations: the property holds, or the check cannot detect its violation. Green discriminates between them only AFTER the check has been observed …
Read the whole file at its exact version.
How to install
mdr add nwave-ai/nwave/nw-cross-cutting-evidence-instrumentation@sha256:c1e9c0ce0fb221a9The line at the top of this page pins the label git:20261102.c67d57b, 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_q54h43nbtjv6ph6r)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Nov 2, 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 (11129 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
nwave-ai/nwave · 633 stars · license MIT · pushed 2026-11-07 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_q54h43nbtjv6ph6r GET https://markdownregistry.com/api/v1/resolve?ref=nwave-ai/nwave/nw-cross-cutting-evidence-instrumentation GET https://markdownregistry.com/api/v1/blob/c1e9c0ce0fb221a910ed88c2f7e358377f791fa799639f5ddbc163b5a80158eb
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.