calibrate-adversarial-confidence SKILL.md skillA
calibrate-adversarial-confidence from yogsoth-ai/de-anthropocentric-research-engine is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add yogsoth-ai/de-anthropocentric-research-engine/calibrate-adversarial-confidence@git:20260923.cbc38aaPins git:20260923.cbc38aa in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- yogsoth-ai/de-anthropocentric-research-engine
- Path
skills/calibrate-adversarial-confidence/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260923.cbc38aa, committed Sep 23, 2026
- Size
- 1,593 bytes
- Repository stars
- 508
- License
- Apache-2.0
Track confidence in competing claims/roles across adversarial rounds and update confidence only when evidence or argument quality warrants it.
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
# calibrate-adversarial-confidence ## Purpose Track confidence in competing claims or roles across adversarial rounds and update only when evidence or argument quality warrants it. ## Input contract ```yaml required: [round_records, competing_claims, update_rule] optional: [prior_confidence, calibration_history] constraints: [every update cites evidence or argument-quality change] ``` ## Procedure 1. Record each round's claims, arguments, and evidence. 2. Apply the declared update rule and preserve dissent. 3. Mark escalation, continuation, termination, or saturation with rationale. ## Output contract ```yaml produces: [confidence_trace, update_rationale, round_status, unresolved_dissent] delta_fields: [findings, evidence_updates, uncertainties, decisions] ``` ## Quality gates - A-class calibration: declared universe = all completed debate rounds; numerator = rounds with evidence-linked updates; batch increment = one round; stopping reason = confidence stabilizes or unresolved dissent is explicit; source references = round/evidence IDs; direction/threshold reason = update only toward claims supported by new evidence or stronger argument. ## Failure and counterexamples …
Read the whole file at its exact version.
How to install
mdr add yogsoth-ai/de-anthropocentric-research-engine/calibrate-adversarial-confidence@sha256:e141e735d2165875The line at the top of this page pins the label git:20260923.cbc38aa, 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_krsj4gomw5u7ps6m)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Sep 23, 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 (1593 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
yogsoth-ai/de-anthropocentric-research-engine · 508 stars · license Apache-2.0 · pushed 2026-10-23 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_krsj4gomw5u7ps6m GET https://markdownregistry.com/api/v1/resolve?ref=yogsoth-ai/de-anthropocentric-research-engine/calibrate-adversarial-confidence GET https://markdownregistry.com/api/v1/blob/e141e735d216587552455abe4c84fc097502cb933ad74ac4cd2af74d6abdb3f1
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.