plugins/context-ledger/skills/initializing-ledger/SKILL.md
Use when starting a new product development project that needs traceable evidence and explicit decisions. Creates workspace structure from a project brief.
npx skillsauth add synaptiai/synapti-marketplace initializing-ledgerInstall 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 creates a complete Context Ledger workspace from a project brief.
./ledger/)Use TodoWrite to track these mandatory steps:
<required> 1. Parse the brief into structured components 2. Validate brief completeness (goals, constraints identifiable) 3. Create directory structure 4. Generate BRIEF.md 5. Generate PILLARS.md with default configuration 6. Confirm initialization complete </required>Extract from the user's input:
| Component | Description | Required | |-----------|-------------|----------| | Core idea | What is being built (1-2 sentences) | Yes | | Target users | Who will use this | Yes | | Key goals | What success looks like | Yes | | Constraints | What's explicitly out of scope | Recommended | | Context | Any domain-specific information | Optional |
If the brief is too vague, use AskUserQuestion to clarify:
Question: "Your brief mentions [X] but I need more clarity on [Y]. Can you specify?"
Options:
- "[Interpretation A]"
- "[Interpretation B]"
- "Let me provide more detail"
Check that the brief supports downstream work:
| Check | Pass Criteria | |-------|---------------| | Scope clarity | Can identify what's in/out | | User clarity | Can describe target users | | Goal measurability | At least one goal is falsifiable | | Constraint presence | At least one constraint stated |
If validation fails, prompt for missing information before proceeding.
Create the full ledger workspace. See references/pillar-definitions.md for pillar details.
mkdir -p ledger/{00-brief,01-pillars}
mkdir -p ledger/02-evidence/{market,users,tech,competitors,design,legal,ops,economics}
mkdir -p ledger/{03-synthesis,04-decisions,05-risks,06-prd,07-architecture,08-plan,09-brand,10-gtm-ops}
Write the parsed brief to 00-brief/BRIEF.md using the template in references/brief-template.md.
Critical constraints:
Create 01-pillars/PILLARS.md with:
Priority assignment logic:
Output summary:
/ledger-research)Use the AskUserQuestion tool when:
Question: "Your brief could be interpreted multiple ways. Which is closest?"
Options:
- "[Interpretation A focused on X]"
- "[Interpretation B focused on Y]"
- "Neither - let me clarify"
Question: "I couldn't identify [goals/constraints/users] from your brief. Can you specify?"
Options:
- "[Suggest likely answer based on context]"
- "[Alternative suggestion]"
- "Let me provide this information"
Question: "Based on your brief, which areas are most critical to research first?"
Options:
- "Market + Users (demand validation focus)"
- "Tech + Competitors (feasibility focus)"
- "All equally important"
- "Let me specify priorities"
Question: "Where should I create the ledger workspace?"
Options:
- "./ledger/ (current directory)" (Recommended)
- "~/projects/[project-name]/ledger/"
- "Let me specify a path"
After successful initialization:
## Ledger Initialized
**Path:** ./ledger/
**Brief:** [2-3 sentence summary]
**Pillar Priorities:**
1. [High priority pillars]
2. [Medium priority pillars]
3. [Lower priority pillars]
**Next step:** Run `/ledger-research` to begin evidence collection.
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.