RedHeartSecretMan/dag-skill / skill/dag
dag
VerifiedCoordinate an Approved DAG in a Git-backed Target Project by selecting runnable Tickets, dispatching one end-to-end Execution Agent per Ticket, and accepting verified results. Use when the user asks to execute, advance, continue, or resume an Approved DAG.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 38.9 KB |
| agents/openai.yaml | config | 218 B |
| references/definition-binding.md | markdown | 9.4 KB |
| references/execution-artifacts.md | markdown | 8.1 KB |
| references/integration-transitions.md | markdown | 16.4 KB |
| references/outcome-closure.md | markdown | 9.9 KB |
| references/runnable-scheduling.md | markdown | 6.8 KB |
| references/ticket-execution.md | markdown | 12.6 KB |
| scripts/commit.pyexecutable | script | 7.5 KB |
| scripts/lib/__init__.py | script | 92 B |
| scripts/lib/artifacts.py | script | 57.9 KB |
| scripts/lib/common.py | script | 12.1 KB |
| scripts/lib/git_ops.py | script | 10.3 KB |
| scripts/lib/receipt.py | script | 8.0 KB |
| scripts/lib/scheduling.py | script | 33.2 KB |
| scripts/lib/tracker.py | script | 48.4 KB |
| scripts/lib/transitions.py | script | 61.8 KB |
| scripts/promote.pyexecutable | script | 2.0 KB |
| scripts/publish.pyexecutable | script | 9.3 KB |
| scripts/runtime.pyexecutable | script | 16.4 KB |
| scripts/verify.pyexecutable | script | 4.4 KB |
scripts/verify.py
View on GitHub#!/usr/bin/env python3
"""Read-only deterministic verification helpers for DAG definitions, artifacts, reviews, and checkpoints."""
from __future__ import annotations
import argparse
import sys
from pathlib import Path
from lib.artifacts import (
HANDLE_KIND,
verify_candidate_review,
verify_handle_file,
)
from lib.common import (
RecordError,
print_json,
require_oid,
require_supported_python,
require_text,
)
from lib.git_ops import ValidationError, validate_definition_index
from lib.tracker import verify_tracker_checkpoint
def build_parser() -> argparse.ArgumentParser:
parser = argparse.ArgumentParser(
description="Read-only deterministic verification for DAG definitions, artifacts, reviews, and tracker checkpoints."
)
subparsers = parser.add_subparsers(dest="subcommand", required=True)
definition = subparsers.add_parser(
"definition-index",
help="validate .dag/definition-index.json at one exact Git commit",
)
definition.add_argument("--repository", required=True, type=Path)
definition.add_argument("--commit", required=True)
artifact = subparsers.add_parser(
"artifact",
help="verify a content-addressed Artifact Handle and its referenced file",
)
artifact.add_argument("--handle", required=True, type=Path)
artifact.add_argument("--artifact-root", type=Path)
review = subparsers.add_parser(
"candidate-review",
help="verify a Candidate Review Record against its Review Context Capsule and review artifact",
)
review.add_argument("--record", required=True, type=Path)
review.add_argument("--context-capsule", required=True, type=Path)
review.add_argument("--artifact-root", required=True, type=Path)
review.add_argument("--expected-base-commit", required=True)
review.add_argument("--expected-base-tree", required=True)
review.add_argument("--expected-candidate-commit", required=True)
review.add_argument("--expected-candidate-tree", required=True)
review.add_argument("--expected-candidate-range", required=True)
tracker = subparsers.add_parser(
"tracker-checkpoint",
help="read-only preflight verification of a Tracker Checkpoint candidate before review and promotion",
)
tracker.add_argument("--repository", required=True, type=Path)
tracker.add_argument("--receipt", required=True, type=Path)
tracker.add_argument("--checkpoint", required=True, type=Path)
return parser
def main() -> int:
parser = build_parser()
arguments = parser.parse_args()
try:
require_supported_python()
if arguments.subcommand == "definition-index":
result = validate_definition_index(arguments.repository, arguments.commit)
elif arguments.subcommand == "artifact":
handle = verify_handle_file(arguments.handle, arguments.artifact_root)
result = {
"status": "verified",
"kind": HANDLE_KIND,
"artifact_sha256": handle["artifact_sha256"],
"byte_count": handle["byte_count"],
}
elif arguments.subcommand == "candidate-review":
result, _handle = verify_candidate_review(
arguments.record,
arguments.context_capsule,
arguments.artifact_root,
require_oid(arguments.expected_base_commit, "expected_base_commit"),
require_oid(arguments.expected_base_tree, "expected_base_tree"),
require_oid(
arguments.expected_candidate_commit, "expected_candidate_commit"
),
require_oid(
arguments.expected_candidate_tree, "expected_candidate_tree"
),
require_text(
arguments.expected_candidate_range, "expected_candidate_range"
),
)
else:
result = verify_tracker_checkpoint(
repository=arguments.repository,
receipt_path=arguments.receipt,
checkpoint_path=arguments.checkpoint,
)
except (
OSError,
RecordError,
ValidationError,
UnicodeDecodeError,
KeyError,
TypeError,
RuntimeError,
) as error:
print(f"error: {error}", file=sys.stderr)
return 1
print_json(result) # type: ignore[arg-type]
return 0
if __name__ == "__main__":
raise SystemExit(main())
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |