agentleFS
CharleneTStrainCharleneTStrain/product-ops-skills/skills/vendor-evaluation-scorecard/SKILL.md

vendor-evaluation-scorecard

Skill0 starsChanged 19 days agoMITView on GitHub

Compare two or more vendors or tools against the same weighted criteria, using evidence from demos, trials, docs, and pricing, and produce a scorecard and recommendation the team can defend. Use when someone is choosing between tools, running a software selection or RFP, comparing vendors, needs evaluation criteria, or wants to turn demo notes into a decision.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Look up current pricing and features rather than relying on memory, since both change often.

    line 42
  2. Distinctive:

    No evidence scores 1, not 3.

    line 56
  3. Distinctive:

    If the scores are close, say so.

    line 83

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Vendor evaluation scorecard

Tool decisions often get made on the best demo or the loudest opinion. A scorecard forces every vendor through the same questions, weighted by what actually matters to this team.

Before you start

If .agents/product-ops-context.md exists (or .claude/product-ops-context.md), read it first. Use the team, owners, tools, meetings, and metric definitions it already has, and only ask for what's missing or specific to this task. If it doesn't exist, go ahead with what you're given, and suggest running product-ops-context once so the next skill doesn't have to ask.

Step 1: Set criteria before looking at vendors

Agree on criteria and weights first, so they aren't bent to favor a vendor someone already likes. Start from the job the tool must do:

  • Must-haves: pass/fail. A vendor that fails one is out, regardless of score.
  • Weighted criteria: typically 5 to 8, weights adding to 100

Common criteria, to adapt:

CriterionWhat to check
Core job fitDoes it do the main job well, with our real workflow?
Ease of useCan the people who'll use it daily work it without training?
IntegrationsConnects to the tools we already depend on
Admin and securityPermissions, SSO, data handling, compliance needs
Total costLicense, seats, add-ons, implementation, renewal increases
Implementation effortTime and people to set up and migrate
Vendor strengthSupport quality, roadmap, stability
ReportingCan we get our data out and see what we need?

Let the person set the weights. Suggest them only if asked, and say they're suggestions.

Step 2: Gather evidence per vendor

For every criterion, record the evidence and its source: a demo note, trial result, doc page, quote, reference call. "Sales said so" is weaker evidence than "we tested it in the trial." Note which.

Look up current pricing and features rather than relying on memory, since both change often. Cite where each fact came from.

Step 3: Score

Score each criterion 1 to 5:

ScoreMeaning
5Clearly exceeds what we need, with strong evidence
4Fully meets it
3Meets it with workarounds
2Partly meets it
1Doesn't meet it, or no evidence

No evidence scores 1, not 3. Compute weighted totals with real arithmetic.

Output

# Vendor evaluation: [Job] — [Date]

## Must-haves
| Must-have | [Vendor A] | [Vendor B] | [Vendor C] |
Eliminated: [vendor] — failed [must-have]

## Scorecard
| Criterion | Weight | [A] | [B] | [C] |
| **Weighted total** | 100 | | | |

## Evidence
### [Vendor A]
- [Criterion]: [score] — [evidence, source]

## Recommendation
[Vendor], because [reasons tied to the highest-weighted criteria].
Risks: [what could go wrong]. Runner-up: [vendor], if [condition].

## Gaps in evidence
- [What we still don't know and how to find out]

If the scores are close, say so. A two-point gap isn't a clear winner; the recommendation should name what would break the tie.

Related skills

  • tool-stack-audit — check what you already pay for first
  • decision-log — record the pick and why
  • raci-builder — decide who owns the new tool

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.