Skip to content

Hello-QM/catgo-LRG / server/catgo/workflow/skills/campaign

campaign-md-orchestration

Verified

Drive a file-first, agent-in-the-loop computational campaign via a folder + markdown tree (no DB). Use when the user opts out of the visual workflow engine.

scripts/campaign_report.py

View on GitHub
"""Draft a group-meeting / seminar report from the campaign's current state.

Pulls the funnel + ranking from analysis/, the narrative from README/plan, and
the sources from literature/INDEX into a progressive-md report under
report/<date>-<occasion>/. A draft the user edits — not a final artifact.
"""
from __future__ import annotations

from pathlib import Path

import campaign_lib as cl


def _read(p: Path, fallback: str) -> str:
    return p.read_text(encoding="utf-8") if p.is_file() else fallback


def make_report(project, occasion: str, date: str) -> Path:
    proj = Path(project).expanduser()
    name = proj.name
    funnel = _read(proj / "analysis" / "funnel.md", "(run aggregate.py first)")
    ranking = _read(proj / "analysis" / "formation_energy_ranking.md", "")
    lit = _read(proj / "literature" / "INDEX.md", "(no literature/INDEX.md)")

    slug = cl.slugify(f"{date}-{occasion}")
    rdir = proj / "report" / slug
    (rdir / "figures").mkdir(parents=True, exist_ok=True)

    body = [
        cl.tldr_header(f"{name} — {occasion} ({date})", "campaign report draft"),
        "",
        "## Background\n\n<from literature; see References below>\n",
        "## Methods\n\n<from cluster.md + per-calc plan.md>\n",
        "## Results\n",
        funnel,
        "",
        ranking,
        "",
        "## Conclusion\n\n<fill in>\n",
        "## References\n",
        lit,
    ]
    dest = rdir / "report.md"
    dest.write_text("\n".join(body) + "\n", encoding="utf-8")

    volcano = proj / "analysis" / "volcano.png"
    if volcano.is_file():
        (rdir / "figures" / "volcano.png").write_bytes(volcano.read_bytes())
    return dest
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: 472kUpdated Claude CodeCodexVerifiedInstall
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: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
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 availableStars: 322kUpdated Claude CodeCodexVerifiedInstall