Skip to content

siril9/presentation-skill / plugins/presentation-skill/skills/presentation-skill

presentation-skill

Flagged

Build, edit, redesign, render, and verify content-led, structurally diverse, clean, editable, reproducible PowerPoint `.pptx` decks. Use for scientific, lab, clinical, consulting, board, investor, editorial, policy, and operational presentations where alignment, readability, contrast, and balanced density matter.

FileKindSize
DESIGN.mdmarkdown13.7 KB
DISCOVERY.mdmarkdown6.6 KB
LICENSEother1.0 KB
SKILL.mdskill md14.7 KB
agents/discovery.jsonconfig8.2 KB
agents/openai.yamlconfig309 B
examples/outline.jsonconfig3.4 KB
package-lock.jsonmanifest22.0 KB
package.jsonmanifest1.8 KB
references/agent_picker.mdmarkdown1.9 KB
references/alignment_and_coherence.mdmarkdown2.1 KB
references/assets/visual_references/editorial_chart.jpgbinary53.2 KB
references/assets/visual_references/editorial_decision.jpgbinary100.4 KB
references/assets/visual_references/editorial_focal_metric.jpgbinary45.4 KB
references/assets/visual_references/editorial_pilot.jpgbinary62.0 KB
references/assets/visual_references/lab-native-method.jpgbinary53.9 KB
references/assets/visual_references/lab-residual-panels.jpgbinary64.8 KB
references/assets/visual_references/lab_cover.jpgbinary39.8 KB
references/assets/visual_references/lab_endpoints.jpgbinary70.8 KB
references/assets/visual_references/lab_evidence_gate.jpgbinary67.3 KB
references/assets/visual_references/lab_trend.jpgbinary60.5 KB
references/assets/visual_references/operations_handoffs.jpgbinary87.2 KB
references/assets/visual_references/operations_owner_register.jpgbinary87.2 KB
references/assets/visual_references/operations_queue.jpgbinary81.8 KB
references/assets/visual_references/operations_tradeoff.jpgbinary99.9 KB
references/benchmark_protocol.mdmarkdown12.1 KB
references/codex_guardrails.mdmarkdown10.3 KB
references/composition_grammar_catalog.mdmarkdown4.0 KB
references/deck_creation.mdmarkdown1.4 KB
references/deck_workspace_mode.mdmarkdown34.4 KB
references/design_philosophy.mdmarkdown5.5 KB
references/dynamic_design_and_subagents.mdmarkdown12.3 KB
references/editing.mdmarkdown12.4 KB
references/external_best_practices.mdmarkdown1.7 KB
references/large_style_corpus_sources.jsonconfig22.7 KB
references/model_adaptive_workflow.mdmarkdown6.6 KB
references/outline_schema.mdmarkdown44.8 KB
references/planning_schema.mdmarkdown54.8 KB
references/pptxgenjs.mdmarkdown7.6 KB
references/preview_extension.mdmarkdown1.7 KB
references/reference_script_patterns.mdmarkdown13.5 KB
references/renderer_role_contracts_v2.jsonconfig38.2 KB
references/reproducible_workflow.mdmarkdown5.1 KB
references/speed_and_rendering.mdmarkdown4.6 KB
references/style_grammar_index.jsonconfig364.2 KB
references/style_inspiration_corpus.jsonconfig32.9 KB
references/style_reference_catalog.mdmarkdown23.9 KB
references/style_reference_sources.jsonconfig35.8 KB
references/style_token_atlas.jsonconfig174.7 KB
references/subagent_patterns.mdmarkdown10.2 KB
references/visual_qa_prompt.mdmarkdown4.9 KB
references/visual_reference_catalog.jsonconfig26.6 KB
references/visual_reference_catalog.mdmarkdown6.0 KB
schemas/deck_ir.schema.jsonconfig9.5 KB
schemas/renderer_capabilities_v2.jsonconfig701 B
scripts/accessibility_qa.pyscript24.8 KB
scripts/action_registry.pyscript12.5 KB
scripts/add_slide.pyscript8.6 KB
scripts/advance_delivery.pyscript88.2 KB
scripts/advance_workspace.pyscript150.3 KB
scripts/apply_artifact_manifest_bindings.pyscript54.1 KB
scripts/apply_atom_composition.pyscript8.2 KB
scripts/apply_data_analysis_handoff.pyscript67.0 KB
scripts/apply_deck_intake_answers.pyscript35.6 KB
scripts/apply_design_contract.pyscript71.7 KB
scripts/apply_outline_authoring_handoff.pyscript23.7 KB
scripts/apply_pptx_style_fragment.pyscript19.7 KB
scripts/asset_stage.pyscript24.6 KB
scripts/audition_styles.pyscript8.7 KB
scripts/benchmark_decks.pyexecutablescript45.4 KB
scripts/build_deck.pyexecutablescript173.6 KB
scripts/build_deck_pptxgenjs.jsexecutablescript72.7 KB
scripts/build_large_style_corpus_contact_sheets.pyscript18.1 KB
scripts/build_workspace.pyscript126.2 KB
scripts/clean_unpacked.pyscript12.9 KB
scripts/compact_source_footers.pyscript17.8 KB
scripts/composition_grammar_catalog.pyscript30.3 KB
scripts/deck_benchmark.pyscript71.1 KB
scripts/deck_intake.pyscript6.9 KB
scripts/deck_ir.pyscript47.5 KB
scripts/design_catalog_selector.pyscript17.4 KB
scripts/design_rules_qa.pyscript24.8 KB
scripts/design_tokens.pyscript20.3 KB
scripts/edit_deck.pyscript8.4 KB
scripts/emit_content_research.pyscript4.6 KB
scripts/emit_data_analysis_prompt.pyscript30.1 KB
scripts/emit_deck_intake_prompt.pyexecutablescript19.9 KB
scripts/emit_deck_start_packet.pyscript97.1 KB
scripts/emit_design_contract_prompt.pyscript66.2 KB
scripts/emit_outline_authoring_prompt.pyscript35.4 KB
scripts/emit_outline_critique.pyscript11.6 KB
scripts/emit_style_content_router.pyscript49.6 KB
scripts/extract_outline.pyexecutablescript4.1 KB
scripts/extract_pptx_style.pyscript33.2 KB
scripts/fetch_wikimedia_cc.pyscript8.6 KB
scripts/finalize_quick_deck.pyscript17.6 KB
scripts/generate_openai_image.pyscript5.6 KB
scripts/init_deck_workspace.pyscript74.4 KB
scripts/inspect_artifact_manifest.pyscript29.8 KB
scripts/inventory.pyscript10.6 KB
scripts/iterate_deck.pyexecutablescript10.2 KB
scripts/layout_lint.pyscript40.4 KB
scripts/log_skill_telemetry.pyscript6.9 KB
scripts/model_adaptive_workflow.pyscript28.0 KB
scripts/office_package_hash.pyscript1.6 KB
scripts/pack_pptx.pyscript5.7 KB
scripts/palette_from_topic.pyscript4.1 KB
scripts/plan_research_assets.pyscript13.1 KB
scripts/preflight.pyscript136.9 KB
scripts/present.pyscript9.6 KB
scripts/python_runtime.pyscript787 B
scripts/qa_gate.pyexecutablescript27.4 KB
scripts/qa_visual_gate.pyexecutablescript8.5 KB
scripts/reference_deck.pyscript12.7 KB
scripts/render_cache.pyscript3.9 KB
scripts/render_mermaid.pyscript8.9 KB
scripts/render_slides.pyexecutablescript19.4 KB
scripts/repair_packet.pyscript14.7 KB
scripts/report_delivery_readiness.pyscript107.6 KB
scripts/report_workspace_readiness.pyscript244.6 KB
scripts/requirements-runtime.txtmarkdown472 B
scripts/role_layout_contracts.pyscript10.6 KB
scripts/runtime_doctor.pyscript6.3 KB
scripts/scaffold_figure_artifacts.pyscript92.3 KB
scripts/source_fidelity.pyscript30.5 KB
scripts/structural_diversity_v2.pyscript32.5 KB
scripts/style_atom_router.pyscript14.5 KB
scripts/style_inspiration_corpus.pyscript15.1 KB
scripts/style_reference_catalog.pyscript142.8 KB
scripts/style_reference_sources.pyscript12.7 KB
scripts/style_treatment_profiles.pyscript26.0 KB
scripts/summarize_skill_log.pyscript7.0 KB
scripts/taste_grammar_catalog.pyscript27.0 KB
scripts/test_structural_diversity_v2.pyscript4.9 KB
scripts/text_fit.pyscript23.6 KB
scripts/thumbnail.pyscript9.2 KB
scripts/trim_image_whitespace.pyexecutablescript5.4 KB
scripts/unpack_pptx.pyscript8.3 KB
scripts/upgrade_renderer_role_contracts_v2.pyscript7.3 KB
scripts/validate_planning.pyscript169.2 KB
scripts/verify_narration.pyscript10.6 KB
scripts/visual_qa.pyscript7.7 KB
scripts/visual_review.pyscript41.1 KB
scripts/visual_review_receipt.pyscript8.3 KB
scripts/workflow_atom_context.pyscript17.3 KB
templates/pptxgenjs/README.mdmarkdown8.4 KB
templates/pptxgenjs/presets.jsscript5.6 KB
templates/pptxgenjs/readable_role_layouts.jsscript17.5 KB
templates/pptxgenjs/render_plan.jsscript12.6 KB
templates/pptxgenjs/role_layout_contracts.jsscript4.7 KB
templates/pptxgenjs/slides.jsscript451.0 KB
templates/pptxgenjs/space_allocation.jsscript1.6 KB

scripts/repair_packet.py

View on GitHub
"""Build a bounded, source-first repair context from existing QA reports.

Counts describe diagnostic records, not unique defects across independent audits.
Layout records duplicated in qa_report.json are read only once. This helper does
not run QA, modify source, or certify that an artifact is ready for delivery.
"""

from __future__ import annotations

import argparse
from collections import Counter
import json
from pathlib import Path
import re
from typing import Any


DEFAULT_MAX_BYTES = 12_000
SCHEMA_VERSION = "repair_packet_v1"


def _json(value: Any) -> str:
    return json.dumps(value, ensure_ascii=True, sort_keys=True, separators=(",", ":"), allow_nan=False)


def _read(path: Path) -> Any:
    def reject_constant(value: str) -> None:
        raise ValueError(f"Non-finite JSON number {value} in {path}")

    return json.loads(path.read_text(encoding="utf-8"), parse_constant=reject_constant)


def _pointer_key(value: str) -> str:
    return value.replace("~", "~0").replace("/", "~1")


def _source_field(source: dict, issue: dict, index: int | None) -> tuple[str | None, str]:
    pointer = issue.get("source_pointer")
    if index is None or not isinstance(pointer, str) or not pointer.startswith(f"/slides/{index}/"):
        return None, ""
    value: Any = source
    try:
        for token in pointer[1:].split("/"):
            key = token.replace("~1", "/").replace("~0", "~")
            value = value[int(key)] if isinstance(value, list) and key.isdecimal() else value[key]
    except (KeyError, IndexError, TypeError, ValueError):
        return None, ""
    return pointer, _json(value)


def _counts(payload: Any) -> dict[str, int]:
    if not isinstance(payload, dict):
        return {}
    return {
        key: value for key, value in payload.items()
        if key.endswith("_count") and type(value) is int
    }


def _bounded(value: Any, depth: int = 0) -> tuple[Any, bool]:
    """Keep small measurements structured; flag every elision explicitly."""
    if isinstance(value, str):
        return value[:240], len(value) > 240
    if isinstance(value, (dict, list)):
        if depth >= 4:
            return None, True
        entries = sorted(value.items()) if isinstance(value, dict) else list(enumerate(value))
        limit = 18 if isinstance(value, dict) else 6
        truncated = len(entries) > limit
        result: Any = {} if isinstance(value, dict) else []
        for key, item in entries[:limit]:
            compact, clipped = _bounded(item, depth + 1)
            truncated |= clipped
            if isinstance(result, dict):
                result[key] = compact
            else:
                result.append(compact)
        return result, truncated
    return value, False


def _instruction(issue: dict[str, Any]) -> str:
    for key in ("suggested_fix", "suggestion"):
        if isinstance(issue.get(key), str) and issue[key].strip():
            return issue[key]
    rule = str(issue.get("type") or issue.get("code") or "").lower()
    if "alt_text" in rule:
        return "Add meaningful alt text to the matching source asset; verify the emitted object."
    if "reading_order" in rule:
        return "Correct source reading order so the headline precedes its evidence; rebuild and inspect."
    if "title" in rule and "missing" in rule:
        return "Supply a meaningful slide title in source and verify the rendered title."
    if any(word in rule for word in ("minimum", "font", "readability")):
        return "Meet the reported type threshold; shorten or split content before shrinking text."
    if any(word in rule for word in ("overlap", "overflow", "intrusion", "margin", "gap", "frame")):
        return "Repair source content or its supported layout to resolve measured fit and spacing; rebuild."
    if any(word in rule for word in ("placeholder", "branding")):
        return "Replace residual placeholder or unrelated branding in source with verified content."
    if rule == "audit_failed":
        return "Resolve the reported audit failure and rerun the audit before making a delivery claim."
    return "Inspect the diagnostic and source slide; correct the reported rule, rebuild, and rerun QA."


def build_repair_packet(
    outline: str | Path, qa_dir: str | Path, *, max_bytes: int = DEFAULT_MAX_BYTES
) -> dict[str, Any]:
    """Return JSON-serializable repairs; never infer source fields from shape IDs.

    ``max_bytes`` targets compact ASCII JSON including its trailing newline.
    Full counts, affected-slide identities, and detail paths are never dropped;
    exceptionally large metadata can exceed the budget, explicitly flagged.
    """
    if type(max_bytes) is not int or max_bytes < 1:
        raise ValueError("max_bytes must be a positive integer")
    outline_path = Path(outline).expanduser().resolve()
    directory = Path(qa_dir).expanduser().resolve()
    source = _read(outline_path)
    if not isinstance(source, dict) or not isinstance(source.get("slides"), list):
        raise ValueError("outline must be an object with a slides array")
    slides = source["slides"]
    qa_path = directory / "qa_report.json"
    qa = _read(qa_path) if qa_path.exists() else {}
    if not isinstance(qa, dict):
        raise ValueError(f"Expected a report object: {qa_path}")

    paths: dict[str, Path] = {"qa_report": qa_path}
    payloads: dict[str, Any] = {"qa_report": qa}
    statuses = {"qa_report": "present" if qa_path.exists() else "missing"}
    specs = (
        ("layout", "layout_lint.json", None),
        ("design", "design_rules.json", "design_report"),
        ("accessibility", "accessibility.json", "accessibility_report"),
        ("inventory", "issues.json", None),
        ("visual", "visual_qa.json", "visual_report"),
        ("visual_review", "visual_review/visual_review.json", "visual_review_report"),
    )
    for name, filename, field in specs:
        raw_path = qa.get(field) if field else None
        path = Path(raw_path).expanduser() if raw_path else directory / filename
        if raw_path and not path.is_absolute():
            path = directory / path
        paths[name] = path.resolve()
        disabled = (
            name == "accessibility" and qa.get("accessibility_enabled") is False
        ) or (name == "visual_review" and field in qa and not raw_path)
        statuses[name] = "disabled" if disabled else "present" if path.exists() else "missing"
        if statuses[name] == "present":
            payload = _read(path)
            expected = list if name == "visual" else dict
            if not isinstance(payload, expected):
                raise ValueError(f"Expected {expected.__name__} report: {path}")
            payloads[name] = payload

    # Only source-specific index fields are authoritative. No integer guessing.
    records: list[tuple[str, str, int | None, dict[str, Any]]] = []

    def add(name: str, pointer: str, issue: Any, index: Any) -> None:
        if not isinstance(issue, dict):
            raise ValueError(f"Expected diagnostic object: {paths[name]}#{pointer}")
        index = index if type(index) is int and 0 <= index < len(slides) else None
        records.append((name, pointer, index, issue))

    layout = payloads.get("layout")
    if layout is not None:
        for position, slide in enumerate(layout.get("slides", [])):
            for offset, issue in enumerate(slide.get("violations", [])):
                add("layout", f"/slides/{position}/violations/{offset}", issue, slide.get("slide_index"))
    else:
        for position, issue in enumerate(qa.get("geometry_violations", [])):
            add("qa_report", f"/geometry_violations/{position}", issue, issue.get("slide_index"))

    for name, key, index_key, base in (
        ("design", "issues", "slide_index", 0),
        ("accessibility", "findings", "slide_number", 1),
        ("visual", None, "slide", 1),
        ("visual_review", "issues", "slide", 1),
    ):
        payload = payloads.get(name, [] if key is None else {})
        for position, issue in enumerate(payload if key is None else payload.get(key, [])):
            value = issue.get(index_key)
            index = value - base if type(value) is int else None
            add(name, f"/{key}/{position}" if key else f"/{position}", issue, index)

    for slide_key, shapes in sorted(payloads.get("inventory", {}).items()):
        match = re.fullmatch(r"slide-(\d+)", slide_key)
        index = int(match[1]) - 1 if match else None
        for shape_key, detail in sorted(shapes.items()):
            for rule in ("overflow", "overlap"):
                if rule in detail:
                    add("inventory", f"/{_pointer_key(slide_key)}/{_pointer_key(shape_key)}", {
                        "type": rule, "shape_id": shape_key,
                        "text": detail.get("text", ""), rule: detail[rule],
                    }, index)
    for position, hit in enumerate(qa.get("placeholder_hits", [])):
        add("qa_report", f"/placeholder_hits/{position}", {"type": "placeholder", "text": hit}, None)

    records.sort(key=lambda row: (
        {"error": 0, "warning": 1, "info": 2}.get(row[3].get("severity"), 3),
        row[2] if row[2] is not None else len(slides), row[0], row[1],
    ))
    by_slide = Counter(index for _, _, index, _ in records)
    affected = []
    for index in sorted(i for i in by_slide if i is not None):
        slide = slides[index]
        slide_id = slide.get("slide_id", slide.get("id")) if isinstance(slide, dict) else None
        affected.append({
            "slide_index": index,
            "slide_id": slide_id if slide_id is not None else f"slide-{index + 1:02d}",
            "source_pointer": f"/slides/{index}", "finding_count": by_slide[index],
        })

    images: dict[int, str] = {}
    render_dirs = [directory / "renders"]
    review = payloads.get("visual_review", {})
    if review.get("renders_dir"):
        render_path = Path(review["renders_dir"]).expanduser()
        render_dirs.append(render_path if render_path.is_absolute() else paths["visual_review"].parent / render_path)
    for render_dir in render_dirs:
        for path in sorted(render_dir.glob("slide-*")):
            match = re.fullmatch(r"slide-(\d+)\.(?:jpg|jpeg|png)", path.name)
            if match and path.is_file():
                images.setdefault(int(match[1]) - 1, str(path.resolve()))

    groups: dict[int | None, dict[str, Any]] = {}
    identities = {item["slide_index"]: item for item in affected}
    for name, pointer, index, issue in records:
        if index not in groups:
            excerpt = _json(slides[index]) if index is not None else ""
            groups[index] = {
                **identities.get(index, {"slide_index": None, "slide_id": None, "source_pointer": None}),
                "finding_count": by_slide[index], "image_path": images.get(index),
                "source_excerpt": excerpt[:600], "excerpt_truncated": len(excerpt) > 600,
                "issues": [],
            }
        group = groups[index]
        if len(group["issues"]) >= 6:
            continue
        diagnostic, truncated = _bounded(issue)
        instruction = _instruction(issue)
        source_pointer, field_excerpt = _source_field(source, issue, index)
        group["issues"].append({
            "source": name, "detail_pointer": pointer, "diagnostic": diagnostic,
            "source_pointer": source_pointer, "source_field_excerpt": field_excerpt[:240],
            "instruction": instruction[:300],
            "details_truncated": truncated or len(instruction) > 300 or len(field_excerpt) > 240,
        })

    reported = {name: _counts(payload) for name, payload in payloads.items()}
    if layout is not None:
        reported["layout"].update(_counts(layout.get("summary", {})))
    packet = {
        "schema_version": SCHEMA_VERSION,
        "outline_path": str(outline_path), "qa_dir": str(directory),
        "mapping_note": "Group pointers identify slides. Issue field pointers are used only when reported and verified in that slide's source. Shape IDs are diagnostic references, not source fields. Null pointers require locating the source. This packet is not a QA verdict.",
        "counts": {
            "findings": len(records), "affected_slides": len(affected),
            "unmapped_findings": by_slide.get(None, 0),
            "by_source": dict(sorted(Counter(row[0] for row in records).items())),
            "by_severity": dict(sorted(Counter(str(row[3].get("severity") or "unspecified") for row in records).items())),
        },
        "reported_counts": reported,
        "detail_paths": {name: str(path) for name, path in paths.items()},
        "source_status": statuses, "affected_slides": affected,
        "repairs": list(groups.values()),
        "truncation": {"max_bytes": max_bytes, "budget_exceeded": False},
    }

    def update_truncation() -> None:
        repairs = packet["repairs"]
        emitted = sum(len(item["issues"]) for item in repairs)
        packet["truncation"].update({
            "omitted_findings": len(records) - emitted,
            "omitted_repairs": len(groups) - len(repairs),
            "truncated_excerpts": sum(item["excerpt_truncated"] for item in repairs),
            "truncated_diagnostics": sum(issue["details_truncated"] for item in repairs for issue in item["issues"]),
        })

    update_truncation()
    for repair in reversed(packet["repairs"]):
        if len(_json(packet).encode("utf-8")) + 1 <= max_bytes:
            break
        if repair["source_excerpt"]:
            repair["source_excerpt"] = ""
            repair["excerpt_truncated"] = True
            update_truncation()
    while packet["repairs"] and len(_json(packet).encode("utf-8")) + 1 > max_bytes:
        repair = packet["repairs"][-1]
        repair["issues"].pop()
        if not repair["issues"]:
            packet["repairs"].pop()
        update_truncation()
    packet["truncation"]["budget_exceeded"] = len(_json(packet).encode("utf-8")) + 1 > max_bytes
    return packet


def main(argv: list[str] | None = None) -> int:
    parser = argparse.ArgumentParser(description=__doc__)
    parser.add_argument("--outline", required=True, type=Path)
    parser.add_argument("--qa-dir", required=True, type=Path)
    parser.add_argument("--output", required=True, type=Path)
    args = parser.parse_args(argv)
    try:
        packet = build_repair_packet(args.outline, args.qa_dir)
        output = args.output.expanduser().resolve()
        protected = {packet["outline_path"], *packet["detail_paths"].values()}
        is_image = re.fullmatch(r"slide-\d+\.(?:jpg|jpeg|png)", output.name)
        if str(output) in protected or is_image:
            raise ValueError("output must not overwrite source, QA reports, or slide images")
        output.parent.mkdir(parents=True, exist_ok=True)
        output.write_text(_json(packet) + "\n", encoding="utf-8")
    except (OSError, ValueError, TypeError) as exc:
        parser.exit(2, f"repair_packet: {exc}\n")
    return 0


if __name__ == "__main__":
    raise SystemExit(main())
canvas-designanthropics/skillsCreate beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
docxanthropics/skillsUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
pdfanthropics/skillsUse this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
pptxanthropics/skillsUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill.Stars: 198kUpdated Claude CodeCodexVerifiedInstall