Skip to content

getaero-io/gtm-eng-skills / skills/deepline-scoring

deepline-scoring

Verified

Use when discovering niche signals, auditing ICP or won/lost evidence, rescoring accounts, or building account and lead scoring Plays. Triggers on fit scoring, engagement scoring, backtesting, holdout evaluation, predictive lift, external proxies, and scoring leakage. Skip pure outreach copy or contributor skill installation tasks.

FileKindSize
.gitignoreother26 B
SKILL.mdskill md12.4 KB
package.jsonmanifest114 B
references/account-website-features.mdmarkdown10.3 KB
references/backtesting-task.mdmarkdown10.0 KB
references/buyer-language-research.mdmarkdown8.6 KB
references/capacity-evidence.mdmarkdown4.4 KB
references/dedupe.mdmarkdown1.5 KB
references/jev-feature-extraction.mdmarkdown8.2 KB
references/keyword-catalog.mdmarkdown4.9 KB
references/pitfalls.mdmarkdown1.6 KB
references/proven-signals.mdmarkdown1.1 KB
references/quality-gate.mdmarkdown2.8 KB
references/report-template.mdmarkdown6.2 KB
references/scorecard-creation.mdmarkdown3.3 KB
references/scorecard-training.mdmarkdown6.5 KB
references/scoring-delivery.mdmarkdown8.3 KB
references/scoring-diagnostics.mdmarkdown8.9 KB
references/scoring-pitfalls.mdmarkdown2.8 KB
references/signal-interpretation.mdmarkdown2.3 KB
references/step-7-prospects.mdmarkdown1.6 KB
references/technology-evidence.mdmarkdown9.4 KB
references/testing-and-evaluation.mdmarkdown6.8 KB
scripts/analyze_signals.pyscript16.9 KB
scripts/analyze_signals_v2.pyscript28.3 KB
scripts/build_feature_matrix.pyscript4.7 KB
scripts/collect_sources.pyscript16.1 KB
scripts/dedupe_utils.pyscript15.6 KB
scripts/dedupe_utils_v2.pyscript15.7 KB
scripts/find_contacts_v2.pyscript1.9 KB
scripts/hubspot_accounts.pyscript7.1 KB
scripts/jev_features.pyscript7.1 KB
scripts/replay-score.play.tsscript2.3 KB
scripts/requirements-scorecard.txtmarkdown263 B
scripts/scorecard/__init__.pyscript514 B
scripts/scorecard/config.pyscript5.0 KB
scripts/scorecard/explainer_artifacts.pyscript8.4 KB
scripts/scorecard/pipeline.pyscript38.9 KB
scripts/scorecard/report.pyscript30.4 KB
scripts/scorecard/scorer.pyscript17.3 KB
scripts/scorecard/specs.pyscript1.3 KB
scripts/scoring_contract.tsscript7.5 KB
scripts/technology_evidence.pyscript3.8 KB
scripts/tests/contract_check.tsscript1.9 KB
scripts/tests/test_jev_features.pyscript3.4 KB
scripts/tests/test_scorecard.pyscript9.5 KB
scripts/train_scorecard.pyscript20.0 KB
skill-metadata.jsonconfig3.8 KB

scripts/build_feature_matrix.py

View on GitHub
#!/usr/bin/env python3
"""Turn an accounts CSV plus frozen concept configs into a per-account feature matrix.

Reuses the analyzer's loader, concept parser and matcher so the booleans here are exactly the
matches the signal report counted. One column per `<family>__<concept>__<source>` (True when
an affirmative mention exists in that source), plus `coverage__website` / `coverage__jobs`
(success|partial|empty|error|missing) and any `--carry` columns copied from the input
(firmographics such as industry or employee count).

Accounts whose source coverage is not `success` get NaN for that source's concept flags, not
False: missing collection is unknown, not observed absence.

    python3 build_feature_matrix.py --input accounts.csv --keywords keywords.json \
      --tools tools.json --job-roles roles.json --carry industry,numberofemployees \
      --output features.csv
"""
from __future__ import annotations

import argparse
import csv
import sys as _sys
csv.field_size_limit(min(_sys.maxsize, 2**31 - 1))
import json
import sys
from pathlib import Path

HERE = Path(__file__).resolve().parent
if str(HERE) not in sys.path:
    sys.path.insert(0, str(HERE))

import analyze_signals_v2 as az  # noqa: E402


def load_config(path: str | None) -> dict:
    if not path:
        return {}
    return json.loads(Path(path).read_text())


def main() -> None:
    p = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)
    p.add_argument("--input", required=True)
    p.add_argument("--keywords")
    p.add_argument("--tools")
    p.add_argument("--job-roles")
    p.add_argument("--output", required=True)
    p.add_argument("--carry", default="", help="Comma-separated input columns to copy through unchanged")
    p.add_argument("--website-col", type=int)
    p.add_argument("--jobs-col", type=int)
    p.add_argument("--status-col", default="status")
    args = p.parse_args()

    accounts, stats = az.load_accounts(args.input, args.website_col, args.jobs_col, args.status_col, "all")
    carry = [c for c in (x.strip() for x in args.carry.split(",")) if c]
    raw_rows = {}
    with open(args.input, encoding="utf-8-sig", newline="") as f:
        for row in csv.DictReader(f):
            key = (row.get("account_id") or "").strip() or az.urlparse(
                row["domain"].strip().lower() if "://" in row["domain"] else "//" + row["domain"].strip().lower()
            ).hostname.removeprefix("www.").rstrip(".")
            raw_rows.setdefault(key, row)

    families = (("keywords", load_config(args.keywords)), ("tools", load_config(args.tools)), ("job_roles", load_config(args.job_roles)))
    columns = []
    specs = []
    for family, config in families:
        if not config:
            continue
        for category, name, aliases in az.concepts(config):
            for kind in (("jobs",) if family == "job_roles" else ("website", "jobs")):
                col = f"{family}__{az.normalize(name).replace(' ', '_')}__{kind}"
                columns.append(col)
                specs.append((col, family, aliases, kind))
    if not specs:
        sys.exit("no concepts configured; pass at least one of --keywords/--tools/--job-roles")

    out_rows = []
    for a in accounts:
        row = {"account_id": a["account_id"], "domain": a["domain"], "status": a["status"], "split": a["split"],
               "coverage__website": a["coverage"]["website"], "coverage__jobs": a["coverage"]["jobs"]}
        src = raw_rows.get(a["account_id"], {})
        for c in carry:
            row[c] = src.get(c, "")
        for col, family, aliases, kind in specs:
            if a["coverage"][kind] != "success":
                row[col] = ""  # unknown, not False
                continue
            positive = False
            for doc in a["documents"][kind]:
                text = doc["title"] if family == "job_roles" else doc["text"]
                if any(hit["polarity"] == "affirmative" for hit in az.occurrences(text, aliases)):
                    positive = True
                    break
            row[col] = positive
        out_rows.append(row)

    fieldnames = ["account_id", "domain", "status", "split", "coverage__website", "coverage__jobs"] + carry + columns
    with open(args.output, "w", newline="") as f:
        w = csv.DictWriter(f, fieldnames=fieldnames)
        w.writeheader()
        w.writerows(out_rows)
    summary = {"accounts": len(out_rows), "feature_columns": len(columns), "loader_stats": stats,
               "coverage": {k: {} for k in ("website", "jobs")}}
    for kind in ("website", "jobs"):
        for a in accounts:
            summary["coverage"][kind][a["coverage"][kind]] = summary["coverage"][kind].get(a["coverage"][kind], 0) + 1
    print(json.dumps(summary, indent=2))


if __name__ == "__main__":
    main()
rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.Stars: 194kUpdated Claude CodeCodexVerifiedInstall