Skip to content

gooseworks-ai/goose-skills / skills/video/video-production-harness

video-production-harness

Verified

Full video production sequence with script review, actual ingredient choices, controlled generation, editing, evidence-based quality review, polish, captions and delivery. A host binding supplies project storage, authentic approvals, provider access and billing.

FileKindSize
SKILL.mdskill md6.0 KB
auto-fix-from-review-notes.mdmarkdown6.5 KB
auto-refine.mdmarkdown5.3 KB
brainstorm.mdmarkdown3.2 KB
capabilities.mdmarkdown13.6 KB
create-clips.mdmarkdown15.0 KB
create-design-brief.mdmarkdown13.4 KB
create-storyboard.mdmarkdown8.8 KB
edit-clip.mdmarkdown6.4 KB
edit-video.mdmarkdown12.8 KB
lock-character.mdmarkdown12.2 KB
lock-script.mdmarkdown8.7 KB
orchestrator.mdmarkdown10.9 KB
polish.mdmarkdown9.2 KB
preflight-audit.mdmarkdown6.2 KB
promote.mdmarkdown3.2 KB
references/check-severity.mdmarkdown9.7 KB
references/creative-contract-and-review.mdmarkdown11.4 KB
references/creator-grammar.mdmarkdown6.7 KB
references/editorial-review.mdmarkdown6.4 KB
references/genres/ai-creator-ugc.mdmarkdown2.7 KB
references/genres/chat-ui.mdmarkdown2.2 KB
references/genres/hypermotion.mdmarkdown1.4 KB
references/genres/motion-graphics.mdmarkdown1.5 KB
references/genres/narrator-montage.mdmarkdown3.1 KB
references/genres/product-demo.mdmarkdown2.0 KB
references/hook-compatibility.mdmarkdown2.8 KB
references/libraries-look-and-rubric.mdmarkdown6.0 KB
references/product-scale-and-world.mdmarkdown4.2 KB
references/quality-tier.mdmarkdown9.4 KB
references/recipe-format.mdmarkdown7.1 KB
references/review-script-shortform.mdmarkdown11.7 KB
references/shot-routing.mdmarkdown14.9 KB
references/specialist-handoff.mdmarkdown4.7 KB
references/speech-and-route-qualification.mdmarkdown10.1 KB
references/talking-actor.mdmarkdown6.6 KB
release.jsonconfig22.1 KB
review-video.mdmarkdown15.0 KB
scripts/assemble.pyscript11.1 KB
scripts/assemble_sources.pyscript5.7 KB
scripts/assembly_timeline.pyscript11.4 KB
scripts/check_recipe.pyscript9.6 KB
scripts/final_grade.pyscript2.9 KB
scripts/final_measure.pyscript14.1 KB
scripts/final_measure_parts.pyscript14.6 KB
scripts/pack_recipe.pyscript11.3 KB
scripts/qc_evidence.pyscript15.0 KB
scripts/reference_rate.pyscript4.3 KB
scripts/reference_shots.pyscript13.1 KB
scripts/timeline_rules.pyscript10.8 KB
skill.meta.jsonconfig820 B
states/edit-to-delivery.mdmarkdown8.2 KB
states/setup-and-script.mdmarkdown10.8 KB
states/storyboard-and-clips.mdmarkdown8.1 KB
wrap-session.mdmarkdown5.9 KB

scripts/final_grade.py

View on GitHub
"""What a gooseworks-final-measure/1 result means for delivery (references/check-severity.md).

A failed check is a finding graded must_fix, ask or fine (SEVERITY in final_measure_parts.py).
Only a broken file is a hard failure: the length is wrong, or there is no sound when sound is
planned. (A file that can't be played at all never reaches here; qc_evidence.py reports it.)
"""
import math
from pathlib import Path
import sys

_SCRIPTS = str(Path(__file__).resolve().parent)
if _SCRIPTS not in sys.path:
    sys.path.insert(0, _SCRIPTS)
from final_measure import silent_by_choice  # noqa: E402
from final_measure_parts import SEVERITY, THRESHOLDS  # noqa: E402

# A final more than this far from the timeline's planned length is broken (a cut-off render or
# a doubled tail), not a taste call. The host warns from 0.5 s.
LENGTH_TOLERANCE_S = 1.0


def broken_reasons(duration, has_audio, pcm, raw_timeline, receipt=None, final_sha=None):
    """[{id, detail}] for a wrong length or no sound when sound is planned; [] when the file is whole.
    A receipt bound to other bytes is broken data, and its plan (length, silence) is not trusted."""
    broken = []
    raw_timeline = raw_timeline if isinstance(raw_timeline, dict) else None
    if isinstance(receipt, dict) and receipt.get("output_sha256") not in (None, final_sha):
        broken.append({"id": "timeline_mismatch", "detail": "The timeline receipt names other final bytes; pass this final's receipt"})
        raw_timeline = None
    planned_ms = (raw_timeline or {}).get("duration_ms")
    if isinstance(planned_ms, int) and not isinstance(planned_ms, bool) and planned_ms > 0 \
            and abs(duration - planned_ms / 1000) > LENGTH_TOLERANCE_S:
        broken.append({"id": "length", "detail": f"The file is {round(duration, 2)} s; the timeline plans {planned_ms / 1000} s (over {LENGTH_TOLERANCE_S} s off)"})
    if not silent_by_choice(raw_timeline):
        if not has_audio:
            broken.append({"id": "no_sound", "detail": "Sound is planned but the file has no audio track"})
        else:
            peak = max((abs(v) for v in pcm[1]), default=0) / 32768
            floor = THRESHOLDS["digital_silence_peak_dbfs"]
            if not peak or 20 * math.log10(peak) < floor:
                broken.append({"id": "no_sound", "detail": f"Sound is planned but the whole track peaks below {floor} dBFS"})
    return broken


def graded_findings(measure):
    """Every failed check with its severity; an unknown check id is ask."""
    return [{"id": c["id"], "severity": SEVERITY.get(c["id"], "ask"), "detail": c["detail"], "intervals_ms": c["intervals_ms"]}
            for c in measure["checks"] if c["result"] == "fail"]


def quality_status(broken, findings):
    severities = {f["severity"] for f in findings}
    return ("broken" if broken else "must_fix" if "must_fix" in severities
            else "ask" if "ask" in severities else "fine" if severities else "no_measured_findings")
receiving-code-reviewobra/superpowersUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementationStars: 322kUpdated Claude CodeCodexVerifiedInstall
requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirementsStars: 322kUpdated Claude CodeCodexVerifiedInstall
using-git-worktreesobra/superpowersUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallbackStars: 322kUpdated Claude CodeCodexVerifiedInstall
verification-before-completionobra/superpowersUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions alwaysStars: 322kUpdated Claude CodeCodexVerifiedInstall