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

scripts/create_evidence_template.py

View on GitHub
#!/usr/bin/env python3
# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
# SPDX-License-Identifier: CC-BY-NC-4.0
"""Create the current AMMO evidence.json skeleton for one track."""

from __future__ import annotations

import argparse
import json
import os
import re
from pathlib import Path
from typing import Any


TRACK_ID_PATTERN = re.compile(r"^[A-Za-z0-9][A-Za-z0-9_-]*$")
LEGACY_STATE_MARKERS = {
    "baseline",
    "parallel_tracks",
    "route_decision",
    "selected_candidates",
    "stage",
}


def template(track_id: str) -> dict[str, Any]:
    """Return a fail-closed structured-evidence skeleton."""
    _validate_track_id(track_id)
    return {
        "schema_version": 3,
        "track_id": track_id,
        "diluted": False,
        "baseline_source": {
            "kind": "stage1",
            "citation": "Baseline source: Stage 1 (not re-run).",
            "sweep_result": None,
        },
        "correctness": {
            "status": "FAIL",
            "method": "torch.allclose",
            "atol": None,
            "rtol": None,
            "max_abs_diff": None,
            "nan_inf_check": False,
            "graph_replay_check": False,
        },
        "kernel_bench": {
            "status": "FAIL",
            "weighted_speedup": None,
            "measured_under_cuda_graphs": False,
            "buckets": [],
            "boundary_ab": None,
        },
        "e2e": {
            "status": "FAIL",
            "run_purpose": "official",
            "baseline_avg_s": None,
            "optimized_avg_s": None,
            "speedup": None,
            "improvement_pct": None,
            "admissibility": {"status": "FAIL", "issues": []},
            "fastpath_proof": {"status": "FAIL", "hits": 0},
        },
        "kill_criteria": {},
        "amdahl": {
            "component_share_f": None,
            "kernel_speedup": None,
            "expected_e2e_pct": None,
            "actual_e2e_pct": None,
        },
        "cross_track_contamination": {
            "status": "N/A",
            "note": "single-track validation or fill multi-track audit",
        },
    }


def _validate_track_id(track_id: str) -> None:
    if not isinstance(track_id, str) or not TRACK_ID_PATTERN.fullmatch(track_id):
        raise ValueError(f"Invalid track id: {track_id!r}")


def _load_state(artifact_dir: Path) -> dict[str, Any] | None:
    state_path = artifact_dir / "state.json"
    if not state_path.exists():
        return None
    try:
        state = json.loads(state_path.read_text(encoding="utf-8"))
    except json.JSONDecodeError as exc:
        raise ValueError(f"Failed to parse JSON {state_path}: {exc}") from exc
    if not isinstance(state, dict):
        raise ValueError(f"{state_path} must contain a JSON object")
    return state


def _v2_current_round(state: dict[str, Any]) -> int | None:
    if "campaign" not in state:
        return None
    campaign = state.get("campaign")
    if not isinstance(campaign, dict):
        raise ValueError("Round-centric state.json campaign must be an object")
    value = campaign.get("current_round")
    if isinstance(value, bool) or not isinstance(value, int) or value < 1:
        raise ValueError(
            "Round-centric state.json requires a positive integer current_round"
        )
    return value


def _is_explicit_legacy_state(state: dict[str, Any] | None) -> bool:
    return bool(
        state
        and "campaign" not in state
        and LEGACY_STATE_MARKERS.intersection(state)
    )


def _current_round(artifact_dir: Path) -> int:
    """Return current V2 round, preserving round 1 for unscaffolded output."""
    state = _load_state(artifact_dir)
    if state is None or "campaign" not in state:
        return 1
    current_round = _v2_current_round(state)
    assert current_round is not None
    return current_round


def _discover_artifact_dir(output: Path) -> Path | None:
    """Find the nearest state.json ancestor for output-only invocations."""
    for parent in output.absolute().parents:
        if (parent / "state.json").is_file():
            return parent.resolve()
    return None


def _same_lexical_path(left: Path, right: Path) -> bool:
    """Compare normalized paths without allowing a symlink alias."""
    return Path(os.path.abspath(left)) == Path(os.path.abspath(right))


def _resolve_output(
    *,
    artifact_dir: Path | None,
    output: Path | None,
    track_id: str,
    round_arg: int | None,
    legacy: bool,
) -> Path:
    discovered = _discover_artifact_dir(output) if output is not None else None
    if artifact_dir is None:
        artifact_dir = discovered
    elif discovered is not None and discovered != artifact_dir:
        raise ValueError(
            "--output belongs to a different artifact directory than --artifact-dir"
        )

    state = _load_state(artifact_dir) if artifact_dir is not None else None
    current_round = _v2_current_round(state) if state is not None else None

    if legacy and round_arg is not None:
        raise ValueError("--legacy and --round cannot be used together")

    if current_round is not None:
        if legacy:
            raise ValueError(
                "V2 round-centric campaigns cannot write legacy root evidence"
            )
        if round_arg is not None and round_arg != current_round:
            raise ValueError(
                f"Cannot write round {round_arg}; state.json current_round is "
                f"{current_round}"
            )
        assert artifact_dir is not None
        expected = (
            artifact_dir
            / "rounds"
            / str(current_round)
            / "tracks"
            / track_id
            / "evidence.json"
        )
        if output is not None and (
            not _same_lexical_path(output, expected)
            or output.resolve() != expected.resolve()
        ):
            raise ValueError(
                "V2 evidence output must be in the current-round track directory: "
                f"{expected}"
            )
        return expected

    if state is not None and "campaign" in state:
        # `_v2_current_round` fails before this branch. Keep this explicit for
        # type checkers and to document that V2 never falls back to flat paths.
        raise ValueError("Round-centric state.json has no usable current round")

    if legacy:
        if not _is_explicit_legacy_state(state):
            raise ValueError(
                "Legacy output requires explicit legacy state.json metadata"
            )
        assert artifact_dir is not None
        expected = artifact_dir / "tracks" / track_id / "evidence.json"
        if output is not None and (
            not _same_lexical_path(output, expected)
            or output.resolve() != expected.resolve()
        ):
            raise ValueError(f"Legacy evidence output must be {expected}")
        return expected

    if output is not None:
        return output
    assert artifact_dir is not None
    round_id = round_arg if round_arg is not None else 1
    if isinstance(round_id, bool) or round_id < 1:
        raise ValueError("--round must be a positive integer")
    return (
        artifact_dir
        / "rounds"
        / str(round_id)
        / "tracks"
        / track_id
        / "evidence.json"
    )


def main() -> int:
    parser = argparse.ArgumentParser(description=__doc__)
    parser.add_argument("artifact_dir_pos", nargs="?", help="Artifact directory")
    parser.add_argument(
        "--artifact-dir", dest="artifact_dir_opt", help="Artifact directory alias"
    )
    parser.add_argument(
        "--track-id",
        "--track",
        dest="track_id",
        required=True,
        help="Track id, e.g. op001",
    )
    parser.add_argument(
        "--round",
        dest="round_id",
        type=int,
        default=None,
        help="Campaign round for round-centric layout",
    )
    parser.add_argument(
        "--legacy",
        action="store_true",
        help="Write artifact_dir/tracks/{track_id}/evidence.json for legacy state",
    )
    parser.add_argument(
        "--output",
        "--output-json",
        dest="output",
        default=None,
        help="Optional explicit output path",
    )
    parser.add_argument("--force", action="store_true")
    args = parser.parse_args()

    try:
        _validate_track_id(args.track_id)
        artifact_value = args.artifact_dir_opt or args.artifact_dir_pos
        if args.artifact_dir_opt and args.artifact_dir_pos:
            positional = Path(args.artifact_dir_pos).expanduser().resolve()
            option = Path(args.artifact_dir_opt).expanduser().resolve()
            if positional != option:
                raise ValueError(
                    "positional artifact directory and --artifact-dir disagree"
                )
        if not artifact_value and not args.output:
            parser.error(
                "artifact_dir positional/--artifact-dir or --output is required"
            )

        artifact_dir = (
            Path(artifact_value).expanduser().resolve() if artifact_value else None
        )
        output = Path(args.output).expanduser().absolute() if args.output else None
        out = _resolve_output(
            artifact_dir=artifact_dir,
            output=output,
            track_id=args.track_id,
            round_arg=args.round_id,
            legacy=args.legacy,
        )
        if out.exists() and not args.force:
            raise ValueError(f"Refusing to overwrite {out}; use --force")

        out.parent.mkdir(parents=True, exist_ok=True)
        out.write_text(
            json.dumps(template(args.track_id), indent=2, sort_keys=True) + "\n",
            encoding="utf-8",
        )
        print(out)
        return 0
    except (OSError, ValueError) as exc:
        parser.exit(2, f"ERROR: {exc}\n")


if __name__ == "__main__":
    raise SystemExit(main())
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