# Plan Map **Iteration:** 4, learning and Skills **Intent:** Make the agent a learning, adaptable solution through Skills. Fix the cheap defects the 2026-10-06 review found, then close the loop so each Execution can improve the next through a reviewed Skill change, then let new standards, clients and Cloud providers arrive as Skills and configuration. **Status:** planned; no step started **This directory covers:** steps 1 to 14 ## Sources of truth - Review report (2026-10-06): https://claude.ai/code/artifact/16b37169-1554-4eb7-bfcb-254315fa0518. Each step's `Report ref` names its enhancement number there. The report uses pre-iteration-3 paths. - `iter-02-solution-architect-agent/steps/step-8.md`: the evaluation figures quoted as evidence. - `docs/adr/0002-skills-are-the-portable-unit-of-behaviour.md`: every step must keep behaviour in Skills and vendored Skills unmodified. - `CONTEXT.md`: "every Execution starts clean". Learning arrives as a reviewed Skill change, never as memory carried between Executions. ## Status | Step | What | Group | Size | Status | |---|---|---|---|---| | 1 | Structured validator findings | A | S | planned | | 2 | Carry the draft through `needs_input` | A | S | planned | | 3 | Reuse pillar advice across Revisions | A | S | planned | | 4 | Single source for Deliverable contracts | A | S | planned | | 5 | Cap parallel Specialists | A | S | planned | | 6 | Orchestrator step order | A | S | planned | | 7 | Capture lesson candidates | B | M | planned | | 8 | Evaluation that can see improvement | B | M | planned | | 9 | ADR: the lessons loop and overlay Skills | B | S | planned, owner's decision | | 10 | Lessons Skill and lesson curator | B | L | planned | | 11 | IaC patterns Skill | B | M | planned | | 12 | Overlay Skills and an organisation standards Skill | C | M | planned | | 13 | Trim Specialist context | C | M | planned | | 14 | Provider-owned contracts | C | M | planned | Size: S under a day, M a few days, L a week or more. Group A is cheap fixes that also create signal. Group B is the learning loop. Group C is adaptability. ## Dependency graph - Steps 1 to 6: no dependencies; any order - Step 7: depends on step 1 - Step 8: no dependencies - Step 9: no dependencies - Step 10: depends on step 7, step 8, step 9 - Step 11: depends on step 8 - Step 12: depends on step 9 - Step 13: depends on step 8 - Step 14: depends on step 4 Step 8 comes before steps 10, 11 and 13 so each of them can be shown to help: same quality, fewer Revisions, seconds or tokens.