Paths: File paths (

shared/

,

references/

,

../ln-*

) are relative to skills repo root. If not found at CWD, locate this SKILL.md directory and go up one level for repo root. If

shared/

is missing, fetch files via WebFetch from

https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}

.

ln-814-optimization-executor

Overview

.hex-skills/optimization/{slug}/context.md

Workflow

Phase 0: Pre-flight Checks

Slug Resolution

• If invoked via Agent with contextStore containing

  slug

  — use directly.
• If invoked standalone — derive slug from context_file path or ask user.

Step 1: Load Context

.hex-skills/optimization/{slug}/context.md

Step 2: Pre-flight Validation

shared/references/git_worktree_fallback.md

shared/references/ci_tool_detection.md

E2E Safety Test

e2e_test_command

e2e_test_command

e2e_test_command = null

Phase 1: Establish Baseline

From Context File

performance_map.baseline

performance_map.test_command

.hex-skills/optimization/{slug}/context.md

test_command

baseline

Verification Run

test_command

test_command

baseline.wall_time_ms

Phase 2: Strike-First Execution

Step 1: Triage Hypotheses

conflicts_with

Step 2: Strike (Apply All Uncontested)

1. APPLY all uncontested hypotheses at once (all file edits)
2. VERIFY: Run full test suite
   IF tests FAIL:
     - IF fixable (typo, missing import) → fix & re-run ONCE
     - IF fundamental → BISECT (see Step 4)
3. E2E GATE (if e2e_test_command not null):
   IF FAIL → BISECT
4. MEASURE: 5 runs, median
5. COMPARE: improvement vs baseline
   IF improvement meets target → DONE. Commit all:
     git add {all_files}
     git commit -m "perf: apply optimizations H1,H2,H3,... (+{improvement}%)"
   IF no improvement → BISECT

Step 3: Contested Alternatives (A/B on top of strike)

FOR each contested hypothesis group:
  1. Apply alternative A → test → measure (5 runs, median)
  2. Revert alternative A, apply alternative B → test → measure
  3. KEEP the winner. Commit.
  4. Winner becomes part of the baseline for next contested group.

Step 4: Bisect (only on strike failure)

1. Revert all changes: git checkout -- . && git clean -fd
2. Binary search: apply first half of hypotheses → test
   - IF passes → problem in second half
   - IF fails → problem in first half
3. Narrow down to the breaking hypothesis
4. Remove it from strike, re-apply remaining → test → measure
5. Log removed hypothesis with reason

Scope Rules

Revert Protocol

git checkout -- . && git clean -fd

git checkout -- {files}

Safety Rules

Stop Conditions (Execution Loop)

Phase 3: Report Results

Report Schema

clean

bisected

failed

{ command, source, baseline_passed, final_passed }

Results Comparison (mandatory)

performance_map.baseline

| Metric | Baseline | After Strike | Improvement |
|--------|----------|-------------|-------------|
| Wall time | 7280ms | 3800ms | 47.8% (1.9x) |
| CPU time | 850ms | 720ms | 15.3% (1.2x) |
| Memory peak | 256MB | 245MB | 4.3% |
| HTTP round-trips | 13 | 2 | 84.6% (6.5x) |

Target: 5000ms → Achieved: 3800ms ✓ TARGET MET

Per-Function Delta (if instrumentation available)

instrumented_files

test_command

| Function | Before (ms) | After (ms) | Delta |
|----------|------------|------------|-------|
| mt_translate | 3500 | 450 | -87% (7.8x) |
| tikal_extract | 2800 | 2800 | 0% (unchanged) |

git checkout -- {instrumented_files}

Experiment Log

{project_root}/.hex-skills/optimization/{slug}/ln-814-log.tsv

strike

bisect

contested

applied

removed

alternative_a

alternative_b

Phase 4: Gap Analysis (If Target Not Met)

Error Handling

git checkout -- .

References

• optimization_categories.md — optimization pattern checklist

• shared/references/ci_tool_detection.md

  (test + benchmark detection)

• shared/references/git_worktree_fallback.md

  (worktree isolation)

Runtime Summary Artifact

shared/references/coordinator_summary_contract.md

.hex-skills/runtime-artifacts/runs/{run_id}/optimization-execution/{slug}.json

Definition of Done

• Baseline established using same metric type as observed problem
• Hypotheses triaged: uncontested vs contested
• Strike applied: all uncontested hypotheses implemented at once
• Tests pass after strike
• Contested alternatives A/B tested on top of full implementation
• Bisect performed only if strike fails (not preemptively)
• E2E safety test passes (or documented as unavailable)
• Experiment log written to

  .hex-skills/optimization/{slug}/ln-814-log.tsv

• Report returned with baseline, final, improvement%, strike result
• All changes on isolated branch, pushed to remote
• Gap analysis provided if target metric not met
• Optimization execution artifact written to the shared location