AI Skill MartBrowse skillsPromptsProgramsLearnWhat is a Skill?
 
← Back to list

Analytical Method Validation (AMV)

Picks the governing framework (ICH Q2(R2)/M10, USP, CLSI, ISO 17025), then plans the validation study, runs the correct statistics, and structures the protocol and report.

Data & AnalyticsAdvanced★ 56,496⑂ 4,969AI score 9/10Last updated: Nov 2, 2026

What it does

  • Fixes the governing framework first: ICH Q2(R2)/Q14, ICH M10 bioanalytical, USP <1220>/<1225>/<1226>, CLSI EP, or ISO/IEC 17025 — preventing hybrid protocols that satisfy none of them.
  • Generates protocols: derives required characteristics from the measured attribute (assay, quantitative impurity, limit test, identity) per Q2(R2) Table 1, lays out the study, and deliberately leaves acceptance criteria blank so they are stated before data collection.
  • Computes the statistics properly: six stdlib-only Python scripts cover calibration lack-of-fit testing, one-way random-effects separation of repeatability vs. intermediate precision, multiple DL/QL approaches with confirmation, ICH M10 run acceptance, and method comparison via TOST, Deming and Passing–Bablok.
  • Blocks classic findings: r² as proof of linearity, post hoc acceptance criteria, repeatability reported as procedure precision, and "not significant therefore equivalent" at method transfer.

Who it's for

  • Pharma/biotech QC and analytical development staff writing validation protocols and reports
  • CRO scientists running PK/TK bioanalysis under ICH M10
  • Clinical labs doing method comparison (CLSI EP) or ISO 17025 accreditation work
  • QA and auditors re-reviewing validation data packages

Examples

  1. "Draft an ICH Q2(R2) validation protocol for an HPLC assay" → plan_validation.py --framework ich-q2r2 --attribute assay --protocol > protocol.md.
  2. "My calibration curve has r² = 0.983 — is it linear?" → check_response.py returns lack-of-fit p = 1.5e-06 and −9% back-calculated error at the low end.
  3. "Are the sending and receiving labs equivalent within ±2%?" → compare_methods.py --margin 2 --relative gives a TOST verdict alongside Deming and Passing–Bablok slopes.

Note: USP, CLSI and ISO thresholds are copyrighted, so the skill supplies designations and sourcing guidance only — never invented numbers.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/HEAD/skills/analytical-method-validation/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on AI Skill Mart.
Copy the skills/analytical-method-validation folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/analytical-method-validation/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/K-Dense-AI/scientific-agent-skills.git && mkdir -p ~/.claude/skills && cp -r scientific-agent-skills/skills/analytical-method-validation ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal (macOS Terminal, or WSL/Git Bash on Windows).
  2. Confirm Python 3.11+ is available: python3 --version.
  3. Clone the repo: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  4. Create the skills folder: mkdir -p ~/.claude/skills
  5. Copy just this skill: cp -r scientific-agent-skills/skills/analytical-method-validation ~/.claude/skills/
  6. Restart Claude Code and try a prompt like "Plan an ICH Q2(R2) validation for an HPLC assay" — the skill triggers on terms such as method validation, LOQ, TOST, or ICH M10.
  7. To run the scripts directly: cd ~/.claude/skills/analytical-method-validation/scripts && python3 plan_validation.py --list-frameworks.
View source on GitHub ↗License: MIT