plugins/context-ledger/skills/synthesizing-pillars/SKILL.md
Use when evidence collection is complete for a pillar and need to extract actionable insights. Transforms raw evidence into structured synthesis with patterns and contradictions identified.
npx skillsauth add synaptiai/synapti-marketplace synthesizing-pillarsInstall 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 transforms raw evidence objects into structured insights for a single research pillar.
02-evidence/<pillar>/Use TodoWrite to track these mandatory steps:
<required> 1. Load all evidence objects for the pillar 2. Identify patterns and themes 3. Resolve or document contradictions 4. Extract key insights 5. Generate synthesis document 6. Link insights to evidence IDs </required>Read all EV-<pillar>-*.yaml files from 02-evidence/<pillar>/.
For each evidence object, extract:
Build a working set of all claims.
Group evidence by theme:
Pattern identification:
Theme: Pricing
├── EV-market-pricing-smb-wtp (0.75) - SMB WTP $29
├── EV-market-pricing-enterprise-wtp (0.80) - Enterprise WTP $99
└── EV-competitors-pricing-benchmark (0.70) - Market avg $45
Insight: Pricing flexibility needed for multi-segment
For contradictory evidence:
### Contradiction: User Segment Priority
**EV-users-segment-power-users** (0.70): Power users drive retention
**EV-users-segment-casual** (0.65): Casual users drive growth
**Resolution:** Unresolved. Both valid for different goals.
**Recommendation:** Requires explicit decision (DEC-*)
For each theme, formulate 1-3 key insights:
Insight structure:
Write 03-synthesis/SYN-<pillar>.md using template from references/synthesis-template.md.
Required sections:
Every insight must cite evidence:
## Key Insight: Price Ceiling
SMB segment shows consistent willingness-to-pay ceiling around $30/month.
(EV-market-pricing-smb-wtp, EV-competitors-pricing-benchmark)
This suggests pricing above $30 requires additional value justification
or enterprise-focused features.
Use the AskUserQuestion tool when:
Question: "Evidence conflicts on [topic]. How should I resolve?"
Options:
- "Favor higher confidence source"
- "Favor more recent source"
- "Document both, defer to decision phase"
- "Help me assess the sources"
Question: "Evidence suggests [X]. Is this interpretation correct?"
Options:
- "Yes, that interpretation is correct"
- "No, the implication is different"
- "Need more context to interpret"
Question: "Synthesis reveals gap in [area]. How to handle?"
Options:
- "Note gap, proceed with available evidence"
- "Request additional research"
- "Critical gap - block until resolved"
After synthesis:
## Synthesis Complete: [pillar]
**Evidence Analyzed:** [N] objects
**Key Insights:** [M]
**Contradictions:** [X] ([Y] resolved, [Z] pending)
### Top Insights
1. [Insight with evidence citation]
2. [Insight with evidence citation]
3. [Insight with evidence citation]
### Decisions Needed
- [Topic requiring DEC-*]
- [Another decision point]
### Document Location
`03-synthesis/SYN-<pillar>.md`
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.