chaussky/ainalyst/value-recommend
Claude Code and agent skill by chaussky/ainalyst
- community
Checking that the SKILL.md file is still in the repository.
BABOK 7.6 skill — Analyze Potential Value and Recommend Solution. Use this skill when the BA wants to assess the ROI of design options from 7.5, compare them by value, and produce a formal recommendation for the sponsor. Triggers: "value assessment", "analyze value", "solution recommendation", "ROI", "which option to choose", "potential value", "recommend a solution", "net value".
Install
npx vskill@latest install chaussky/ainalyst/value-recommendSKILL.md
SKILL: Analyze Potential Value and Recommend Solution (BABOK 7.6)
What this task is about
You help the BA assess the potential value of each design option from 7.5 and produce a formal recommendation for the sponsor.
Value = Benefits − Costs − Risks
This is the final task of Chapter 7. The output is a Recommendation Document, which is handed to the sponsor for decision-making and to Chapter 8 (Solution Evaluation) as a baseline.
Four legitimate outcomes
| Type | When | |
|---|---|---|
recommend_option | One option is clearly better | |
recommend_parallel | Two options are implemented in parallel | |
recommend_reanalyze | No option fits — a new analysis is needed | |
no_action | The change is not justified — benefits < costs + risks |
Pipeline (standard)
When to read references/
Read references/value_assessment_guide.md when:
- The BA asks how to classify a benefit or cost type
- You need to explain the Value Score formula
- The BA is unsure which
recommendation_typeto choose - You need examples of success_metrics
MCP tools
add_value_assessment
Assess one design option: benefits, costs, risks.
- Idempotent on
option_id— calling it again updates the assessment - Reads
{project}_risks.jsonif it exists (from 6.3) - Called once for each option from 7.5
compare_value
Automatic Value Score matrix across all options.
- Formula: Benefits×2.0 + Alignment×1.5 − Cost×1.5 − Risk_Penalty×1.0
- Reads business_context for Alignment_Score (optional)
- Outputs ranking and winner
check_value_readiness
Optional pre-flight check before save_recommendation.
- Checks completeness of assessments and data correctness
- Informational only — does not block
- Useful for complex projects with 3+ options
save_recommendation
Final Recommendation Document.
- Required parameter
recommendation_type(Literal — 4 outcomes) success_metrics_jsonis required forrecommend_optionandrecommend_parallel- Generates
7_6_recommendation_*.mdvia save_artifact
Tips for the BA
- Start with
add_value_assessmentfor each option before drawing conclusions no_actionandrecommend_reanalyzedon't needrecommended_option_id- Success metrics must be measurable — "improve NPS" doesn't qualify, "NPS > 8" does
- Risks can be passed manually if the 6.3 file doesn't exist
Task files
- Reads:
{project}_design_options.json(7.5),{project}_business_context.json(7.3),
{project}_architecture.json (7.4), {project}_risks.json (6.3, optional)
- Writes:
{project}_recommendation.json,7_6_recommendation_*.md
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/value_recommend/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/chaussky/ainalyst/value-recommend)