From accelerator
Defines the JSON output format for plan review agents, including schema, severity emojis, and finding body structure.
How this skill is triggered — by the user, by Claude, or both
Slash command
/accelerator:plan-review-output-formatThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Return your analysis as a JSON code block. Do not include any text before or
Return your analysis as a JSON code block. Do not include any text before or after the JSON block — the orchestrator will parse this output directly.
{
"lens": "<lens-identifier>",
"summary": "2-3 sentence assessment from this lens perspective.",
"strengths": [
"Positive observation about what the plan gets right from this lens perspective"
],
"findings": [
{
"severity": "critical",
"confidence": "high",
"lens": "<lens-identifier>",
"location": "Phase 2, Section 3: Database Migration",
"title": "Brief finding title",
"body": "🔴 **<Lens Name>**\n\n[Issue description — 1-2 sentences with enough context to understand standalone].\n\n**Impact**: [Why this matters — 1 sentence].\n\n**Suggestion**: [Concrete fix — 1-2 sentences]."
}
]
}
"architecture", "security",
"test-coverage", "code-quality", "standards", "usability",
"performance", "documentation", "database", "correctness",
"compatibility", "portability", "safety")"critical", "major", "minor", "suggestion""high", "medium", "low"lens field).
Included on each finding so the orchestrator can attribute findings after
merging outputs from multiple agents.Use these actual Unicode emoji characters at the start of each finding body:
🔴 for "critical" severity🟡 for "major" severity🔵 for "minor" and "suggestion" severityIMPORTANT: Use the actual Unicode emoji characters shown above (🔴 🟡 🔵), NOT
text shortcodes like :red_circle:, :yellow_circle:, or :blue_circle:. The
output is rendered as markdown, not Slack/Discord, so shortcodes will appear as
literal text.
Each finding body should follow this structure:
[emoji] **[Lens Name]**
[Issue description — 1-2 sentences, standalone context].
**Impact**: [Why this matters].
**Suggestion**: [Concrete fix].
Example:
🔴 **Architecture**
The plan proposes a direct dependency from the API layer to the database schema
with no service abstraction. This couples the presentation layer to the data
model.
**Impact**: Database schema changes will ripple into the API layer, breaking
the dependency rule.
**Suggestion**: Introduce a service layer to mediate between the API handlers
and the data access layer.
Output only the JSON block — do not include additional prose, narrative analysis, or markdown outside the JSON code fence. The orchestrator parses your output as JSON.
npx claudepluginhub atomicinnovation/accelerator --plugin acceleratorSpecifies the JSON schema, field reference, severity emoji prefixes, and finding body format for work-item review agents. Used by review orchestrators only.
Provides standardized Markdown templates for research, planning, implementation, and review agent outputs. Use when generating or parsing agent responses in autonomous dev workflows.
Defines review standards for plan-reviewer agent: severity classification (BLOCKER/MAJOR/MINOR/NIT), decision matrix (APPROVED/NEEDS_CHANGES/REJECTED), and architecture compliance checks for plan validation.