agentleFS
Future-CXFuture-CX/AI-Architecture-Toolkit/skills/assess-solution/SKILL.md

assess-solution

Skill8 starsChanged 6 months agoMITView on GitHub

Interview the user to assess a proposed or existing solution against architecture principles and a selected capability overview or solution architecture design. Use when the user asks to review, assess, self-assess, validate, or score a solution against principles, capability fit, or an existing solution design.

The file

We split this skill into the rules it gives an agent

12 rules. About 0 are common, 12 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈12

    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:

    Run an interview-based assessment of a proposed or existing solution against:

    line 10
  2. Distinctive:

    Start in interview mode. Ask one question at a time and do not generate the final assessment until the interview is complete.

    line 30
  3. Distinctive:

    After each topic, summarize captured facts, assumptions, missing evidence, and follow-up questions.

    line 40
  4. Distinctive:

    Before writing the report or scorecard, summarize the evidence collected and ask the user to confirm whether to proceed or answer remaining …

    line 41
  5. Distinctive:

    Create the simple 5-star scorecard only after the interview is complete and the user has confirmed there is enough evidence.

    line 43
  6. Distinctive:

    Use concise, stakeholder-readable Markdown:

    line 53
  7. Distinctive:

    Start with the business outcome and decision impact before technical findings.

    line 70
  8. Distinctive:

    Keep the assessment evidence-based.

    line 71
  9. Distinctive:

    Treat missing evidence as an assessment result, not as permission to guess.

    line 73
  10. Distinctive:

    Keep the scorecard easy to scan.

    line 77
  11. Distinctive:

    Prefer concrete remediation actions over generic advice.

    line 78
  12. Distinctive:

    Keep company-confidential solution details out of this public toolkit repository.

    line 79

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Assess Solution

Quick Start

Run an interview-based assessment of a proposed or existing solution against:

  1. The architecture principles available in principles/.
  2. One user-selected baseline:
    • A capability overview under capabilities/<slug>/.
    • A solution architecture design under solution-architectures/<slug>/.

If the user has not identified the capability overview or solution design, ask which one to use before starting the assessment. Use the selected baseline and principles to ask focused questions. Do not produce the final report until the user has answered the interview topics and confirmed that the assessment evidence is complete enough.

Required Inputs

  • Solution description, proposal, implementation notes, or path to an existing solution document, gathered or confirmed through the interview.
  • Solution supplier, vendor, product company, or implementation partner when the solution depends on an external company.
  • Customer references, case studies, testimonials, analyst notes, or reference-call findings when available.
  • Assessment baseline: one capability overview or one solution architecture design.
  • Architecture principles to assess against. Prefer all principle documents under principles/ unless the user names a subset.
  • Target audience and desired depth, if different from architecture and delivery stakeholders.

Workflow

  1. Start in interview mode. Ask one question at a time and do not generate the final assessment until the interview is complete.
  2. Confirm the solution, supplier, and whether to assess against a capability overview or solution architecture design when the baseline is not explicit.
  3. Locate and read the selected baseline and architecture principles. If multiple baselines match, ask the user to choose one.
  4. Extract baseline expectations to build the interview plan:
    • Business outcome and scope boundary.
    • Main business features or requirements, users, processes, data, integrations, systems, and dependencies.
    • Security, privacy, compliance, non-functional, operational, and lifecycle expectations.
    • Explicit risks, assumptions, constraints, open questions, and design decisions.
  5. Interview the user for each main business feature or requirement. Ask for fit, evidence, known gaps, user impact, operational impact, and required action.
  6. Interview the user on each assessment topic: ease of use, other features, integrations, target architecture alignment, principle alignment, supplier, references, price indication, risks, constraints, and open questions.
  7. After each topic, summarize captured facts, assumptions, missing evidence, and follow-up questions. Ask follow-ups when answers are vague or unsupported. When there is a strong evidence-based suggestion, include it with the question and ask the user to confirm, correct, or reject it.
  8. Before writing the report or scorecard, summarize the evidence collected and ask the user to confirm whether to proceed or answer remaining questions.
  9. Assess principle alignment using Aligned, Partly aligned, Misaligned, or Not enough evidence.
  10. Create the simple 5-star scorecard only after the interview is complete and the user has confirmed there is enough evidence. Use whole stars only; do not use half-star symbols.
  11. Identify gaps, risks, trade-offs, and open questions. Do not invent missing facts.
  12. Give a practical recommendation:
    • Proceed when only minor issues remain.
    • Proceed with conditions when risks or gaps need tracked mitigation.
    • Revise before approval when material conflicts or missing decisions remain.
    • Do not proceed when the solution conflicts with critical principles or baseline expectations.

Output

Use concise, stakeholder-readable Markdown:

  1. Metadata table at the top: | Field | Value |, | --- | --- |, | Confluence Link | Not published yet |, | Last Update | <today's date> |.
  2. Assessment Summary - decision recommendation, main reason, and operational impact.
  3. Assessment Baseline - linked capability overview or solution architecture design, plus principle source used.
  4. Scorecard - simple 5-star table with only these rows: Ease of Use, Main Business Features Fit, Other Features Provided, Integrations, and Architecture Fit. Include Price Indication and Overall rows when the information is available. Show whole-star ratings only, for example ★★★★☆; if nuance is needed, write it in the evidence note. In evidence notes, italicize negative or critical clauses, for example *Mobile was not shown.*
  5. Main Business Features - use one heading per business requirement found in the capability overview or solution design. Under each heading, use separate paragraphs labelled **Baseline fit:**, **Insight:**, **Gap:**, and **Recommended action:**.
  6. Architectural Fit - technical insights with subsections: Target Architecture Alignment for target-state fit and constraints, Principle Alignment for principle rating, evidence, and required change, and Integration Alignment for interfaces, dependencies, contracts, data flow, error handling, observability, and ownership.
  7. Solution Supplier - general company information, strengths, cautions, and due diligence needs.
  8. References - other customers using the solution, their context, recommendation or experience, relevance, and evidence quality.
  9. Risks and Trade-offs - material risks, impact, mitigation, and owner when known.
  10. Open Questions - answerable questions needed to complete the assessment.
  11. Recommendation - proceed status, conditions, and next actions.

Guidance

  • Start with the business outcome and decision impact before technical findings.
  • Keep the assessment evidence-based. Cite source sections or filenames where possible.
  • Separate facts from assumptions.
  • Treat missing evidence as an assessment result, not as permission to guess.
  • During the interview, offer strong suggestions when the baseline, principles, or prior answers clearly support them. Label suggestions as suggestions, not facts, until the user confirms them.
  • For supplier commentary, use neutral language and distinguish known facts from market perception, assumptions, or missing due diligence.
  • For references, identify the source and comparability. Do not present supplier marketing claims as independent customer experience.
  • Keep the scorecard easy to scan. Do not create, draft, preview, or estimate scorecard ratings before the interview is complete. Do not add extra scorecard categories unless the user asks.
  • Prefer concrete remediation actions over generic advice.
  • Keep company-confidential solution details out of this public toolkit repository. Assess real company solutions in a private company lab repository.

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.