plugins/context-ledger/skills/making-decisions/SKILL.md
Use when transforming synthesis insights into explicit decisions with documented trade-offs. Guides interactive decision-making and risk identification.
npx skillsauth add synaptiai/synapti-marketplace making-decisionsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
This skill guides the creation of explicit decisions with full trade-off documentation.
/ledger-synthesize)03-synthesis/CROSS-SYNTHESIS.md exists with decision candidates03-synthesis/SYN-*.mdUse TodoWrite to track these mandatory steps:
<required> 1. Load decision candidates from cross-synthesis 2. For each candidate, gather evidence and options 3. Present trade-offs for user decision 4. Create decision entry with semantic ID 5. Identify risks created by each decision 6. Generate DECISIONS.yaml and RISKS.yaml 7. Validate decision quality gates </required>Read 03-synthesis/CROSS-SYNTHESIS.md to extract:
For each decision candidate:
decision_candidate:
topic: target-segment-priority
options:
- name: SMB-first
evidence:
- EV-users-smb-pain-points (0.80)
- EV-economics-smb-unit-economics (0.75)
- name: Enterprise-first
evidence:
- EV-market-enterprise-tam (0.85)
- EV-competitors-enterprise-gap (0.70)
For each decision, present:
Use AskUserQuestion to get user's decision.
Write entry to 04-decisions/DECISIONS.yaml using schema from references/decision-ledger-schema.md.
Each decision may create risks. For each identified risk:
05-risks/RISKS.yamlSee references/risk-ledger-schema.md for schema.
Write complete files:
04-decisions/DECISIONS.yaml05-risks/RISKS.yamlDecision quality gate:
Risk quality gate:
Use the AskUserQuestion tool for every decision:
Question: "Decision needed: [topic]"
Options:
- "[Option A] - supported by [evidence summary]"
- "[Option B] - supported by [evidence summary]"
- "[Option C] - supported by [evidence summary]"
- "Need more information before deciding"
Question: "You chose [option]. Confirming trade-offs:"
Options:
- "Yes, I accept these trade-offs"
- "Wait, I want to reconsider"
- "Explain the trade-offs more"
Question: "Should this decision be marked as:"
Options:
- "Accepted (committed)"
- "Provisional (may revisit)"
- "Need more research first"
Question: "This decision creates risk: [risk]. How severe?"
Options:
- "High - requires immediate mitigation"
- "Medium - should have mitigation plan"
- "Low - acceptable risk"
After decision-making:
## Decisions Complete
**Decisions Made:** [N]
**Status:** [X] accepted, [Y] provisional
**Risks Identified:** [Z]
### Decisions Summary
| ID | Decision | Status | Evidence Count |
|----|----------|--------|----------------|
| DEC-scope-smb-first | Target SMB first | accepted | 4 |
| DEC-pricing-freemium | Use freemium model | provisional | 3 |
| ... | ... | ... | ... |
### Risks Created
| ID | Risk | Severity | Linked Decision |
|----|------|----------|-----------------|
| RISK-market-smb-churn | SMB churn rate | medium | DEC-scope-smb-first |
| ... | ... | ... | ... |
### Quality Gate Status
- Decision gate: ✓ All decisions cite ≥2 evidence
- Risk gate: ✓ All risks have mitigations
### Next Step
Run `/ledger-spec` to generate constrained PRD and architecture.
tools
Validate a FlowWorkflow YAML at `plugins/flow/workflows/<id>.workflow.yaml` against `schemas/v1/workflow.schema.json` AND cross-reference the referenced skills/agents exist + every Tier 3 action is confirm-gated + no native /goal or /loop dependency is declared. Use when /flow:workflow validate is invoked, when CI runs the workflow schema gates, or when a new workflow is being authored. This skill MUST be consulted because schema validation alone catches shape errors; cross-reference validation catches the silent-correctness failures (typo'd skill name, Tier 3 escape, /goal dependency) that would otherwise ship to users.
tools
Verify UI-facing changes by running a screenshot-analyze-verify loop across configured viewports, with a browser-tool priority cascade (Playwright MCP → Chrome DevTools MCP → CLI fallback → external skill fallback) and bounded iteration. Use after build/runtime verification passes and the diff includes `.tsx`/`.jsx`/`.vue`/`.html`/`.css`/`.scss`/`.svelte` files OR the acceptance criteria mention UI/page/render/display/visual. This skill MUST be consulted because UI changes that pass build and unit tests can still ship blank pages, render-blocking console errors, or broken responsive layouts that no other verification phase catches.
data-ai
Coordinate agent teams for adversarial review (paired skeptic/verifier per facet, challenge round with disposition vocabulary, consolidated findings with confidence) or parallel implementation (task sizing 5-6 per teammate, non-overlapping files). Enforces independent analysis before shared conclusions. Reference only (`disable-model-invocation: true`); loaded only when `agentTeams: true` in settings.
development
Conduct two-stage code review: Stage 1 verifies spec compliance (criterion-to-code mapping), Stage 2 evaluates security, correctness, performance, and maintainability across 6 parallel facets with P1/P2/P3 synthesis and deduplication by file:line. Use when reviewing code changes or pull requests. This skill MUST be consulted because reviewing quality on broken logic is wasted effort, and unmet acceptance criteria must block merge.