selection-toolkit — Claude Code skill: Excel for procurement and appraisal
selection-toolkit is a Claude Code skill that builds Excel workbooks for selection and multi-criteria appraisal, with weighted scoring based on published criteria.
no license 135 installs ★ 3 updated 2026-11-11
npx skills add gasserane/personal-skills --skill selection-toolkit -a claude-codeWhat selection-toolkit does
This skill generates the complete set of Excel files needed to run a selection between a published ToR and award. In procurement mode, it produces a master workbook and one scorer workbook per panel member; in appraisal mode, it builds a generic comparison tool for any weighted decision. All criteria, weights and thresholds come from the source document — nothing is invented.
The workflow has four steps. read extracts criteria from the document and flags gaps (what the ToR did not specify: thresholds, panel roster, compliance checks). You fill the spec with Ane and delete the gap list. build generates the files. verify injects test data into Excel via COM and asserts computed means, thresholds and rankings against the same engine that wrote the formulas. This catches the failure mode where a workbook looks right but calculates wrong.
The tool handles ToRs in English, French, Spanish, Romanian or German. Once scorer files are distributed and scored, they stay in place — the skill refuses to regenerate an existing toolkit, preserving the scores and edit history.
What it helps with
- prepare independent scoring workbooks for panel members
- translate ToR criteria and weights into Excel formulas without error
- verify that computed scores and rankings are arithmetically correct
- maintain an audit trail linking each weight to its source
Example prompts for the agent
- Parse criteria from our ToR into a JSON spec and flag what's missing
- Build scorer workbooks for five panel members from this spec
- Check that mean scores in the master workbook calculate correctly
How to install selection-toolkit
1Skills CLI (Vercel)
npx skills add gasserane/personal-skills --skill selection-toolkit -a claude-code2Manually: put the files in place
~/.claude/skills/selection-toolkit/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/selection-toolkit/
1Skills CLI (Vercel)
npx skills add gasserane/personal-skills --skill selection-toolkit -a codex2Manually: put the files in place
.agents/skills/selection-toolkit/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add gasserane/personal-skills --skill selection-toolkit -a cursor2Manually: put the files in place
.cursor/skills/selection-toolkit/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install gasserane/personal-skills skills/selection-toolkit2Manually: put the files in place
.github/skills/selection-toolkit/SKILL.md1Skills CLI (Vercel)
npx skills add gasserane/personal-skills --skill selection-toolkit -a gemini-cli2Platform CLI
gemini skills install https://github.com/gasserane/personal-skills --path skills/selection-toolkitManually: put the files in place
.devin/skills/selection-toolkit/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add gasserane/personal-skills --skill selection-toolkit -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about selection-toolkit
How do I install selection-toolkit in Claude Code?
Run npx skills add gasserane/personal-skills --skill selection-toolkit -a claude-code, then open ~/.claude/skills/selection-toolkit/SKILL.md.
What does selection-toolkit do?
It generates Excel files for running a selection or appraisal: a master workbook and separate scorer workbooks for each panel member. It reads criteria and weights from the source document, validates them, builds formulas, and tests the calculations.
Can I edit the workbooks after they are built?
Yes. Once distributed, the scorer files are edited in place and never regenerated. This preserves the scores and audit trail of changes made during the evaluation.