perf-calibration SKILL.md skillA
perf-calibration from amey-thakur/ai-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add amey-thakur/ai-skills/perf-calibration@git:20260728.fac4544Pins git:20260728.fac4544 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- amey-thakur/ai-skills
- Path
skills/big-tech-processes/perf-calibration/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260728.fac4544, committed Jul 28, 2026
- First version recorded
- Jul 18, 2026
- Size
- 3,333 bytes
- Repository stars
- 14
- License
- MIT
Run a performance calibration meeting so ratings across a group rest on comparable evidence and a consistent bar, not one manager's advocacy. Use when managers are finalizing performance ratings for a team or org and you need consistency and bias control before results are delivered.
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
# Performance calibration Calibration exists because a rating set by a single manager reflects that manager's standards, generosity, and blind spots as much as the employee's work. Putting managers in one room to defend ratings against a shared rubric surfaces the inconsistencies and the biases before anything reaches an employee. Done badly, it just hands the outcome to whoever argues hardest. ## Method 1. **Bring evidence, not adjectives.** Each manager arrives with specific, dated examples tied to the rubric's dimensions: what was delivered, its scope, its impact. "She's a rock star" is not calibratable; "she owned the X launch at senior scope, with result Y" is. Rule out claims no one can check. 2. **Anchor every rating to the rubric level.** Read the written definition of each rating band and place people against it, not against each other's vibes. When two managers rate similar work differently, resolve it by returning to the anchor, so the standard is the rubric and not the room's mood. 3. **Compare like work across managers.** Line up people at the same level and ask whether a "meets" from one team would be a "meets" on another. This …
Read the whole file at its exact version.
How to install
mdr add amey-thakur/ai-skills/perf-calibration@sha256:1411748d1d3e580eThe line at the top of this page pins the label git:20260728.fac4544, 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_q4kv5qgpjpnoigzu)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Jul 18, 2026 and Jul 28, 2026, about one every 10 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260728.fac4544 latest | 2026-07-28 | fac4544 | 3,333 B | A | view · diff |
| git:20260718.7c1285c | 2026-07-18 | 7c1285c | 3,333 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 (3333 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
amey-thakur/ai-skills · 14 stars · license MIT · pushed 2026-09-06 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_q4kv5qgpjpnoigzu GET https://markdownregistry.com/api/v1/resolve?ref=amey-thakur/ai-skills/perf-calibration GET https://markdownregistry.com/api/v1/blob/1411748d1d3e580ef008b6e334b3f26578c86f3cf5da99393a4b5ef803c7d50e
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.