rsil-plan

name	rsil-plan
description	Requirements-Synthesis Integration Loop (RSIL). Performs code-level gap analysis and creates remediation plans. Called after /synthesis ITERATE decision.
user-invocable	true
context	fork
model	opus
version	3.1.0
argument-hint	[--iteration <n>] [--auto-remediate] [--workload <slug>]
allowed-tools	["Read","Grep","Glob","Task","TaskCreate","TaskUpdate","TaskList","Write","mcp__sequential-thinking__sequentialthinking"]
hooks	{"Setup":[{"type":"command","command":"source /home/palantir/.claude/skills/shared/workload-files.sh && source /home/palantir/.claude/skills/shared/validation-feedback-loop.sh","timeout":5000}]}
agent_delegation	{"enabled":true,"default_mode":true,"max_sub_agents":3,"delegation_strategy":"phase-based","strategies":{"gap_verification":{"description":"Delegate code-level gap verification to explore agents"},"evidence_collection":{"description":"Delegate evidence collection from codebase"}},"output_paths":{"l1":".agent/prompts/{slug}/rsil-plan/l1_summary.yaml","l2":".agent/prompts/{slug}/rsil-plan/iteration_{n}.md","l3":".agent/prompts/{slug}/rsil-plan/l3_details/"}}
parallel_agent_config	{"enabled":true,"complexity_detection":"auto","agent_count_by_complexity":{"simple":1,"moderate":2,"complex":3},"gap_areas":["requirement_verification","code_evidence_collection","test_coverage_check"]}
agent_internal_feedback_loop	{"enabled":true,"max_iterations":3,"validation_criteria":{"completeness":["All requirements verified against codebase","Evidence collected for each finding"],"quality":["Code evidence includes file paths and snippets","Remediation recommendations specific"]}}
review_gate	{"enabled":true,"phase":"3.5","criteria":["requirement_alignment","design_flow_consistency","gap_detection","conclusion_clarity"]}
selective_feedback	{"enabled":true,"threshold":"MEDIUM"}

/rsil-plan - Requirements-Synthesis Integration Loop

Version: 3.1.0 | EFL Pattern: P1 + P2 + P5 + P6 Role: Gap Analysis and Remediation Planning Pipeline: After /synthesis ITERATE, before /orchestrate or /clarify

1. Purpose

RSIL handles iteration cycles when /synthesis returns ITERATE:

1. Verifies gaps at code level (not just keyword matching)
2. Collects evidence from codebase
3. Classifies gaps (COVERED/PARTIAL/MISSING)
4. Creates remediation tasks
5. Decides AUTO_REMEDIATE or ESCALATE

2. Invocation

/rsil-plan                          # Auto-detect iteration
/rsil-plan --iteration 2            # Specific iteration
/rsil-plan --auto-remediate         # Skip user confirmation
/rsil-plan --workload <slug>        # Explicit workload

3. Pipeline Integration

/synthesis
    |
    +-- ITERATE --> /rsil-plan <-- THIS SKILL
                        |
                        +-- Phase 1: Parallel Explore Agents (P2)
                        +-- Phase 2: L1 Aggregation
                        +-- Phase 3-A: L2 Horizontal Synthesis
                        +-- Phase 3-B: L3 Vertical Verification
                        +-- Phase 3.5: Review Gate (P5)
                        +-- Phase 4: Selective Feedback (P4)
                        +-- Phase 5: User Decision
                        |
                        +-- AUTO_REMEDIATE --> /orchestrate
                        +-- ESCALATE --> /clarify

4. L1/L2/L3 Output Format

L1 Summary (returned to main context)

taskId: rsil-{iteration}-{timestamp}
agentType: rsil-plan
status: success
summary: "RSIL complete: 3 gaps, 2 tasks, EFL verified"

priority: HIGH
decision: "AUTO_REMEDIATE"
gapStats:
  total: 3
  missing: 1