Skip to content

amazon-science/ammo / ai_cli_session/.codex/skills/ammo

Profile and optimize GPU kernels for vLLM inference on NVIDIA GPUs. Use when targeting a specific model, hardware, dtype, parallelism, and workload to improve latency.

FileKindSize
RUNTIME.mdmarkdown4.9 KB
SKILL.mdskill md18.5 KB
agents/ammo-auditor.mdmarkdown9.1 KB
agents/ammo-champion.mdmarkdown9.6 KB
agents/ammo-delegate.mdmarkdown3.2 KB
agents/ammo-implementer.mdmarkdown13.8 KB
agents/ammo-investigator.mdmarkdown4.0 KB
agents/ammo-report.mdmarkdown2.9 KB
agents/ammo-researcher.mdmarkdown10.3 KB
agents/ammo-resolver.mdmarkdown4.4 KB
agents/ammo-transcript-monitor.mdmarkdown7.8 KB
agents/openai.yamlexecutablescript313 B
data/ATTRIBUTION.mdmarkdown1.4 KB
data/gsm8k_full.jsonexecutablescript735.5 KB
data/gsm8k_subset.jsonexecutablescript116.8 KB
eval/EVAL-SKILL.mdexecutablescript21.8 KB
eval/agents/transcript_grader.mdexecutablescript18.0 KB
eval/causal/__init__.pyexecutablescript137 B
eval/causal/agents/causal_analyzer.mdexecutablescript10.5 KB
eval/causal/build_dag.pyexecutablescript21.6 KB
eval/causal/diff_versions.pyexecutablescript38.5 KB
eval/causal/extract_events.pyexecutablescript36.3 KB
eval/causal/generate_postmortem.pyexecutablescript17.0 KB
eval/causal/score_nodes.pyexecutablescript21.5 KB
eval/causal/templates/narrative_template.mdexecutablescript472 B
eval/causal/templates/viz_template.htmlexecutablescript9.5 KB
eval/causal/tests/__init__.pyexecutablescript151 B
eval/causal/tests/conftest.pyexecutablescript448 B
eval/causal/tests/fixtures/sample_session.jsonlexecutablescript10.4 KB
eval/causal/tests/fixtures/sample_session_data.jsonexecutablescript3.4 KB
eval/causal/tests/fixtures/sample_snapshot.jsonexecutablescript2.5 KB
eval/causal/tests/test_build_dag.pyexecutablescript2.7 KB
eval/causal/tests/test_diff_versions.pyexecutablescript13.5 KB
eval/causal/tests/test_extract_events.pyexecutablescript3.7 KB
eval/causal/tests/test_generate_postmortem.pyexecutablescript3.1 KB
eval/causal/tests/test_score_nodes.pyexecutablescript3.3 KB
eval/scripts/aggregate_versions.pyexecutablescript15.2 KB
eval/scripts/archive_run.pyexecutablescript9.1 KB
eval/scripts/codex_session.pyexecutablescript10.6 KB
eval/scripts/generate_dashboard.pyexecutablescript5.3 KB
eval/scripts/parse_artifacts.pyexecutablescript48.1 KB
eval/scripts/parse_session_logs.pyexecutablescript51.3 KB
eval/scripts/rescore_archived.pyexecutablescript5.5 KB
eval/scripts/score_campaign.pyexecutablescript43.8 KB
eval/scripts/snapshot_changes.pyexecutablescript11.1 KB
eval/scripts/verify_citations.pyexecutablescript8.8 KB
eval/tests/test_dashboard_bugs.pyexecutablescript8.8 KB
eval/tests/test_parse_session_logs.pyexecutablescript3.9 KB
eval/tests/test_parse_session_logs_round_inference.pyexecutablescript11.0 KB
eval/tests/test_score_campaign_diluted.pyexecutablescript9.4 KB
eval/viewer/dashboard_template.htmlexecutablescript15.1 KB
instrumentation/sitecustomize.pyexecutablescript3.6 KB
orchestration/audit-protocol.mdmarkdown9.3 KB
orchestration/debate-protocol.mdmarkdown11.2 KB
orchestration/integration-logic.mdmarkdown10.3 KB
orchestration/parallel-tracks.mdmarkdown8.9 KB
references/artifact-layout.mdexecutablescript22.4 KB
references/audit-invariants.mdmarkdown10.6 KB
references/champion-common-patterns.mdmarkdown3.4 KB
references/crossover-probing.mdexecutablescript4.7 KB
references/cudagraph-safety.mdmarkdown2.7 KB
references/debate-rules.mdmarkdown4.7 KB
references/debate-scoring-rubric.mdexecutablescript16.7 KB
references/e2e-delta-math.mdexecutablescript17.9 KB
references/e2e-latency-guide.mdexecutablescript9.6 KB
references/fusion-feasibility-heuristics.mdmarkdown5.6 KB
references/gpu-pool.mdexecutablescript5.4 KB
references/impl-track-rules.mdexecutablescript13.8 KB
references/nsys-profiling-guide.mdmarkdown9.8 KB
references/optimization-categories.mdexecutablescript11.0 KB
references/shutdown-protocol.mdexecutablescript3.1 KB
references/technology-selection.mdmarkdown5.0 KB
references/torch-compile-contract.mdmarkdown13.8 KB
references/validation-defaults.mdexecutablescript34.2 KB
references/workload-invocation.mdexecutablescript4.9 KB
references/writing-style.mdexecutablescript6.9 KB
scripts/ammo_state.pyexecutablescript142.0 KB
scripts/artifact_layout.jsonconfig16.3 KB
scripts/check_projection_accuracy.pyexecutablescript11.7 KB
scripts/create_evidence_template.pyexecutablescript9.7 KB
scripts/create_worktree_with_build.shexecutablescript10.2 KB
scripts/generate_validation_report.pyexecutablescript35.7 KB
scripts/gpu_reservation.pyexecutablescript27.1 KB
scripts/hook_cmd_classify.pyscript13.3 KB
scripts/mine_trace.pyscript29.4 KB
scripts/monitor_queue_ack.pyexecutablescript6.1 KB
scripts/ncu_sanity.shexecutablescript5.2 KB
scripts/ncu_sanity_driver.pyexecutablescript8.5 KB
scripts/new_target.pyexecutablescript22.0 KB
scripts/preflight_vllm_api.pyexecutablescript12.3 KB
scripts/reconcile_track_state.pyexecutablescript15.8 KB
scripts/remove_worktree_cleanup.shexecutablescript1.1 KB
scripts/resolve_codex_transcript.pyexecutablescript3.6 KB
scripts/run_vllm_bench_latency_sweep.pyexecutablescript249.6 KB
scripts/transcript_filter.pyexecutablescript38.4 KB
scripts/transitions.jsonexecutablescript1.5 KB
scripts/verify_validation_gates.pyexecutablescript88.8 KB
tests/agents/test-champion.mdexecutablescript20.4 KB
tests/agents/test-impl-champion.mdexecutablescript14.3 KB
tests/agents/test-implementer.mdexecutablescript15.8 KB
tests/agents/test-orchestrator.mdexecutablescript33.8 KB
tests/agents/test-researcher.mdexecutablescript21.0 KB
tests/agents/test-transcript-monitor.mdexecutablescript13.4 KB
tests/fixtures/diluted_pass/legacy_no_phase.golden.mdmarkdown1.1 KB
tests/fixtures/diluted_pass/legacy_no_phase.golden.summary.jsonconfig582 B
tests/fixtures/diluted_pass/legacy_no_phase.jsonconfig400 B
tests/fixtures/diluted_pass/legacy_scalar_phase.golden.mdmarkdown2.0 KB
tests/fixtures/diluted_pass/legacy_scalar_phase.golden.summary.jsonconfig1.0 KB
tests/fixtures/diluted_pass/legacy_scalar_phase.jsonconfig626 B
tests/fixtures/mining/real_campaign_bottleneck_analysis.mdmarkdown20.7 KB
tests/run_all.shexecutablescript1.6 KB
tests/scripts/test_transcript_filter.pyexecutablescript41.1 KB
tests/test_agent_runtime_contracts.pyexecutablescript1.8 KB
tests/test_ammo_state.pyexecutablescript71.7 KB
tests/test_artifact_layout_manifest.pyscript11.6 KB
tests/test_audit_started.pyscript18.2 KB
tests/test_correctness_comparator.pyscript12.6 KB
tests/test_diluted_pass.pyscript24.4 KB
tests/test_drift_compat.pyscript5.1 KB
tests/test_evidence_freshness.pyexecutablescript5.6 KB
tests/test_fail_closed.pyexecutablescript14.7 KB
tests/test_gpu_reservation.pyexecutablescript24.8 KB
tests/test_gpu_reservation_session_id.pyexecutablescript11.2 KB
tests/test_guidance_semantic_contract.pyscript24.9 KB
tests/test_hook_cmd_classify_parity.pyscript11.7 KB
tests/test_hook_semantics.pyexecutablescript95.3 KB
tests/test_mine_trace.pyscript24.2 KB
tests/test_mining_invalidated_schema.pyexecutablescript9.4 KB
tests/test_new_target_dp_ep.pyexecutablescript7.4 KB
tests/test_new_target_v2_scaffold.pyexecutablescript13.1 KB
tests/test_parse_artifacts.pyexecutablescript3.0 KB
tests/test_policy_convergence.pyscript797 B
tests/test_preflight_vllm_api.pyscript13.3 KB
tests/test_projection_accuracy_v2.pyexecutablescript4.1 KB
tests/test_reconcile_track_state.pyexecutablescript18.2 KB
tests/test_resolve_codex_transcript.pyexecutablescript3.1 KB
tests/test_state_schema_semantics.pyexecutablescript7.6 KB
tests/test_status_set_sync.pyexecutablescript9.1 KB
tests/test_sweep_baseline_from_arm.pyscript11.0 KB
tests/test_sweep_decode_capture.pyexecutablescript31.8 KB
tests/test_sweep_dp.pyexecutablescript45.4 KB
tests/test_sweep_fresh_cache.pyscript5.5 KB
tests/test_sweep_profiler_guard.pyscript22.6 KB
tests/test_sweep_real_prompts.pyscript20.1 KB
tests/test_sweep_refactor.pyexecutablescript37.6 KB
tests/test_sweep_round_slot.pyexecutablescript7.4 KB
tests/test_validation_report_phase_triage.pyexecutablescript10.0 KB
tests/test_validation_report_v2.pyexecutablescript6.2 KB
tests/test_verify_validation_gates.pyexecutablescript52.9 KB
tests/test_workload_matrix.pyexecutablescript19.3 KB

eval/causal/tests/test_diff_versions.py

View on GitHub
# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
# SPDX-License-Identifier: CC-BY-NC-4.0
# test_diff_versions.py
"""Tests for diff_versions.py — cross-version causal DAG comparison."""
import json
import copy
from pathlib import Path
import pytest

FIXTURES = Path(__file__).parent / "fixtures"


def _build_dag():
    from extract_events import extract_events
    from build_dag import build_dag
    from score_nodes import score_nodes
    session_data = json.loads((FIXTURES / "sample_session_data.json").read_text())
    events = extract_events(session_jsonl_path=FIXTURES / "sample_session.jsonl", session_data=session_data)
    dag = build_dag(events=events, artifact_dir=str(FIXTURES))
    snapshot = json.loads((FIXTURES / "sample_snapshot.json").read_text())
    scored_dag, _ = score_nodes(dag=dag, events=events, snapshot=snapshot)
    return scored_dag


def _make_v2(dag):
    v2 = copy.deepcopy(dag)
    for node in v2["nodes"]:
        if node["id"] == "debate":
            node["metrics"]["data_grounding"] = 0.3
            node["anomaly"] = {"type": "DATA_CORRUPTION", "triggered_by": {"data_grounding": 0.3}}
        if node["id"] == "bottleneck_mining":
            node["metrics"]["retry_rate"] = 0.05
            node["anomaly"] = None
    return v2


def test_metric_deltas_computed():
    from diff_versions import diff_versions
    v1 = _build_dag()
    v2 = _make_v2(v1)
    diff = diff_versions(current_dag=v2, previous_dag=v1)
    assert "metric_deltas" in diff
    assert "debate" in diff["metric_deltas"]


def test_new_anomalies_detected():
    from diff_versions import diff_versions
    v1 = _build_dag()
    v2 = _make_v2(v1)
    diff = diff_versions(current_dag=v2, previous_dag=v1)
    new = diff.get("new_anomalies", [])
    assert any(a["node"] == "debate" for a in new)


def test_resolved_anomalies_detected():
    from diff_versions import diff_versions
    v1 = _build_dag()
    for n in v1["nodes"]:
        if n["id"] == "bottleneck_mining":
            n["anomaly"] = {"type": "THRASHING", "triggered_by": {"retry_rate": 0.4}}
    v2 = _make_v2(v1)
    diff = diff_versions(current_dag=v2, previous_dag=v1)
    resolved = diff.get("resolved_anomalies", [])
    assert any(a["node"] == "bottleneck_mining" for a in resolved)


def test_edge_count_changes():
    from diff_versions import diff_versions
    v1 = _build_dag()
    v2 = copy.deepcopy(v1)
    v2["edges"] = [e for e in v2["edges"] if e["type"] != "data_citation"]
    diff = diff_versions(current_dag=v2, previous_dag=v1)
    assert "edge_changes" in diff
    if "data_citation" in diff["edge_changes"]:
        assert diff["edge_changes"]["data_citation"]["delta"] < 0


def test_diff_json_schema():
    from diff_versions import diff_versions
    v1 = _build_dag()
    v2 = _make_v2(v1)
    diff = diff_versions(current_dag=v2, previous_dag=v1)
    assert "version" in diff
    assert "compared" in diff
    assert "metric_deltas" in diff
    assert "new_anomalies" in diff
    assert "resolved_anomalies" in diff
    assert "edge_changes" in diff
    assert "anomaly_distribution_shift" in diff


def test_cli_with_two_dags(tmp_path):
    import subprocess
    v1 = _build_dag()
    v2 = _make_v2(v1)
    f1 = tmp_path / "v1.json"
    f2 = tmp_path / "v2.json"
    out = tmp_path / "diff.json"
    f1.write_text(json.dumps(v1))
    f2.write_text(json.dumps(v2))
    result = subprocess.run(
        ["python", str(Path(__file__).parent.parent / "diff_versions.py"),
         "--current-dag", str(f2), "--previous-dag", str(f1),
         "--output", str(out)],
        capture_output=True, text=True, cwd=str(Path(__file__).parent.parent),
    )
    assert result.returncode == 0, result.stderr
    diff = json.loads(out.read_text())
    assert "metric_deltas" in diff


def test_regression_report_with_deep_flag(tmp_path):
    import subprocess
    v1 = _build_dag()
    v2 = _make_v2(v1)
    f1 = tmp_path / "v1.json"
    f2 = tmp_path / "v2.json"
    out = tmp_path / "diff.json"
    report = tmp_path / "regression_report.md"
    f1.write_text(json.dumps(v1))
    f2.write_text(json.dumps(v2))
    result = subprocess.run(
        ["python", str(Path(__file__).parent.parent / "diff_versions.py"),
         "--current-dag", str(f2), "--previous-dag", str(f1),
         "--output", str(out), "--deep",
         "--regression-report", str(report)],
        capture_output=True, text=True, cwd=str(Path(__file__).parent.parent),
    )
    assert result.returncode == 0, result.stderr
    assert report.exists()
    assert len(report.read_text()) > 0


# ---------------------------------------------------------------------------
# New tests: skill-diff correlation
# ---------------------------------------------------------------------------

def test_skill_diff_parsing():
    """Parse a unified diff into structured hunks."""
    from diff_versions import _parse_skill_diff
    patch = """diff --git a/.codex/skills/ammo/SKILL.md b/.codex/skills/ammo/SKILL.md
--- a/.codex/skills/ammo/SKILL.md
+++ b/.codex/skills/ammo/SKILL.md
@@ -50,6 +50,8 @@
 ## Stage 3: Candidate Proposal + Adversarial Debate

 - Spawn 2-4 ammo-champion agents
+- Champions MUST cite exact line numbers from bottleneck_analysis.md
+- Reject proposals that don't ground f-values in profiling data
 - Phase 0: Each champion independently proposes
"""
    changes = _parse_skill_diff(patch)
    assert len(changes) >= 1
    assert changes[0]["file"] == ".codex/skills/ammo/SKILL.md"
    assert len(changes[0]["added_lines"]) == 2


def test_skill_diff_parsing_researcher_file():
    """Unified diff for a researcher-guide file infers researcher_guidance section."""
    from diff_versions import _parse_skill_diff
    patch = """diff --git a/references/researcher-guide.md b/references/researcher-guide.md
--- a/references/researcher-guide.md
+++ b/references/researcher-guide.md
@@ -10,4 +10,5 @@
 Some context line
+- New rule for researchers
 - Old rule
"""
    changes = _parse_skill_diff(patch)
    assert len(changes) >= 1
    assert changes[0]["section"] == "researcher_guidance"


def test_skill_diff_parsing_impl_file():
    """Unified diff for an impl file infers implementation_guidance section."""
    from diff_versions import _parse_skill_diff
    patch = """diff --git a/impl_runner.py b/impl_runner.py
--- a/impl_runner.py
+++ b/impl_runner.py
@@ -1,3 +1,4 @@
 def run():
+    pass
     return
"""
    changes = _parse_skill_diff(patch)
    assert len(changes) >= 1
    assert changes[0]["section"] == "implementation_guidance"


def test_skill_change_to_node_mapping():
    """Skill changes map to correct DAG nodes."""
    from diff_versions import _map_skill_changes_to_nodes
    changes = [
        {"file": "SKILL.md", "section": "debate_guidance", "added_lines": ["test"], "removed_lines": []},
        {"file": "references/researcher-guide.md", "section": "researcher_guidance", "added_lines": ["test"], "removed_lines": []},
    ]
    mapping = _map_skill_changes_to_nodes(changes)
    assert "debate" in mapping
    assert "bottleneck_mining" in mapping


def test_skill_change_impl_guidance_with_node_list():
    """implementation_guidance changes map to impl_* nodes when node list is provided."""
    from diff_versions import _map_skill_changes_to_nodes
    changes = [
        {"file": "impl_runner.py", "section": "implementation_guidance", "added_lines": ["x"], "removed_lines": []},
    ]
    mapping = _map_skill_changes_to_nodes(changes, all_node_ids=["impl_op001", "impl_op002", "debate"])
    assert "impl_op001" in mapping
    assert "impl_op002" in mapping
    assert "debate" not in mapping


def test_skill_change_general_maps_to_all_nodes():
    """general section changes map to all provided node IDs."""
    from diff_versions import _map_skill_changes_to_nodes
    changes = [
        {"file": "README.md", "section": "general", "added_lines": ["x"], "removed_lines": []},
    ]
    mapping = _map_skill_changes_to_nodes(changes, all_node_ids=["debate", "baseline_capture", "bottleneck_mining"])
    for nid in ["debate", "baseline_capture", "bottleneck_mining"]:
        assert nid in mapping


def test_correlation_produces_hypotheses():
    """Correlated skill + behavioral changes produce hypotheses."""
    from diff_versions import _correlate_changes
    skill_map = {
        "debate": [{"file": "SKILL.md", "section": "debate_guidance", "added_lines": ["new rule"], "removed_lines": []}]
    }
    metric_deltas = {"debate": {"data_grounding": -0.25}}
    hypotheses = _correlate_changes(
        skill_map,
        metric_deltas,
        new_anomalies=[{"node": "debate", "type": "DATA_CORRUPTION"}],
        resolved_anomalies=[],
    )
    assert len(hypotheses) >= 1
    assert hypotheses[0]["node_id"] == "debate"
    assert "hypothesis" in hypotheses[0]


def test_correlation_high_confidence_single_change():
    """Single skill change + single behavioral regression → high confidence."""
    from diff_versions import _correlate_changes
    skill_map = {
        "debate": [{"file": "SKILL.md", "section": "debate_guidance", "added_lines": ["change"], "removed_lines": []}]
    }
    metric_deltas = {"debate": {"data_grounding": -0.5}}
    hypotheses = _correlate_changes(skill_map, metric_deltas, new_anomalies=[], resolved_anomalies=[])
    assert len(hypotheses) == 1
    assert hypotheses[0]["confidence"] == "high"


def test_correlation_no_match_when_below_threshold():
    """Metric delta below 0.1 does not produce a hypothesis."""
    from diff_versions import _correlate_changes
    skill_map = {
        "debate": [{"file": "SKILL.md", "section": "debate_guidance", "added_lines": ["x"], "removed_lines": []}]
    }
    metric_deltas = {"debate": {"data_grounding": -0.05}}
    hypotheses = _correlate_changes(skill_map, metric_deltas, new_anomalies=[], resolved_anomalies=[])
    assert len(hypotheses) == 0


def test_deep_with_skill_diff_produces_rich_report(tmp_path):
    """--deep with --skill-diff produces report with hypotheses."""
    import subprocess
    v1 = _build_dag()
    v2 = _make_v2(v1)
    f1 = tmp_path / "v1.json"
    f2 = tmp_path / "v2.json"
    out = tmp_path / "diff.json"
    report = tmp_path / "regression_report.md"
    skill_diff = tmp_path / "skill.patch"
    skill_diff.write_text('''diff --git a/.codex/skills/ammo/SKILL.md b/.codex/skills/ammo/SKILL.md
--- a/.codex/skills/ammo/SKILL.md
+++ b/.codex/skills/ammo/SKILL.md
@@ -50,6 +50,7 @@
 ## Stage 3: Debate

 - Spawn champions
+- Reduced grounding requirements
''')
    f1.write_text(json.dumps(v1))
    f2.write_text(json.dumps(v2))
    result = subprocess.run(
        ["python", str(Path(__file__).parent.parent / "diff_versions.py"),
         "--current-dag", str(f2), "--previous-dag", str(f1),
         "--output", str(out), "--deep",
         "--skill-diff", str(skill_diff),
         "--regression-report", str(report)],
        capture_output=True, text=True, cwd=str(Path(__file__).parent.parent),
    )
    assert result.returncode == 0, result.stderr
    diff_data = json.loads(out.read_text())
    assert diff_data.get("deep_investigation") is not None
    assert diff_data["deep_investigation"].get("hypotheses") is not None
    report_text = report.read_text()
    assert "Causal Hypotheses" in report_text


def test_deep_without_skill_diff_still_works(tmp_path):
    """--deep WITHOUT --skill-diff still produces structural report (backward compat)."""
    import subprocess
    v1 = _build_dag()
    v2 = _make_v2(v1)
    f1 = tmp_path / "v1.json"
    f2 = tmp_path / "v2.json"
    out = tmp_path / "diff.json"
    report = tmp_path / "regression_report.md"
    f1.write_text(json.dumps(v1))
    f2.write_text(json.dumps(v2))
    result = subprocess.run(
        ["python", str(Path(__file__).parent.parent / "diff_versions.py"),
         "--current-dag", str(f2), "--previous-dag", str(f1),
         "--output", str(out), "--deep",
         "--regression-report", str(report)],
        capture_output=True, text=True, cwd=str(Path(__file__).parent.parent),
    )
    assert result.returncode == 0, result.stderr
    diff_data = json.loads(out.read_text())
    assert diff_data["deep_investigation"]["mode"] == "structural_diff"
    # Should NOT have hypotheses key (or it should be absent / None)
    assert "hypotheses" not in diff_data["deep_investigation"]
    report_text = report.read_text()
    assert len(report_text) > 0
    # Rich sections should NOT appear
    assert "Causal Hypotheses" not in report_text


def test_deep_investigation_json_schema_with_skill_diff(tmp_path):
    """version_diff.json deep_investigation block has the required schema keys."""
    import subprocess
    v1 = _build_dag()
    v2 = _make_v2(v1)
    f1 = tmp_path / "v1.json"
    f2 = tmp_path / "v2.json"
    out = tmp_path / "diff.json"
    skill_diff = tmp_path / "skill.patch"
    skill_diff.write_text('''diff --git a/.codex/skills/ammo/SKILL.md b/.codex/skills/ammo/SKILL.md
--- a/.codex/skills/ammo/SKILL.md
+++ b/.codex/skills/ammo/SKILL.md
@@ -50,6 +50,7 @@
 ## Stage 3: Debate

 - Spawn champions
+- Changed rule
''')
    f1.write_text(json.dumps(v1))
    f2.write_text(json.dumps(v2))
    result = subprocess.run(
        ["python", str(Path(__file__).parent.parent / "diff_versions.py"),
         "--current-dag", str(f2), "--previous-dag", str(f1),
         "--output", str(out), "--deep",
         "--skill-diff", str(skill_diff)],
        capture_output=True, text=True, cwd=str(Path(__file__).parent.parent),
    )
    assert result.returncode == 0, result.stderr
    diff_data = json.loads(out.read_text())
    di = diff_data["deep_investigation"]
    assert "skill_changes_parsed" in di
    assert "correlations_found" in di
    assert "hypotheses" in di
    assert "uncorrelated_skill_changes" in di
    assert "uncorrelated_behavioral_changes" in di
slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."Stars: 198kUpdated Claude CodeCodexVerifiedInstall
ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read.Stars: 194kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report.Stars: 194kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt.Stars: 194kUpdated Claude CodeCodexVerifiedInstall