{"id":103875,"plugin_id":"plugin_asdk_app_6af4843aed908191af6dcaf48b127b34","kind":"skill","collection_source":"plugin_package","comparison_source":null,"observed_at":"2026-11-18T12:20:10.251Z","digest":"9bc3b6e9a011ed966485ee9d6b5121fe16285fffb868a912a20c4463efe3553d","against":null,"payload":{"description":"Compares a company's actual or forecast revenue growth by segment and country with the growth of the corresponding external market, computes the gap in percentage points and the implied market-share change, flags forecasts that outrun their market, and drafts commentary for forecast reviews and monthly reports. Use whenever a user asks \"are we growing faster than the market\", needs market context for variance commentary, wants to sanity-check a budget or forecast against market growth, or provides revenue by segment and asks how it compares externally.","included_files":[{"relative_path":"agents/openai.yaml","size_in_bytes":225},{"relative_path":"scripts/growth_gap.py","size_in_bytes":5129}],"name":"growth-vs-market-check","skill_md_contents":"---\nname: growth-vs-market-check\ndescription: Compares a company's actual or forecast revenue growth by segment and country with the growth of the corresponding external market, computes the gap in percentage points and the implied market-share change, flags forecasts that outrun their market, and drafts commentary for forecast reviews and monthly reports. Use whenever a user asks \"are we growing faster than the market\", needs market context for variance commentary, wants to sanity-check a budget or forecast against market growth, or provides revenue by segment and asks how it compares externally.\n---\n\n# Growth-vs-Market Check\n\n## Purpose\n\nAdd an external driver to forecast review and monthly reporting. A forecast that outgrows its market for several years is the most common sign of over-optimism. The check turns it into a question for the unit owner, not a verdict.\n\n## Inputs\n\n| Input | Required | Default |\n| --- | --- | --- |\n| Internal revenue CSV: `segment,country,year,revenue,type` with type `actual` or `forecast` | Yes | — |\n| Mapping of internal segments to market segments | No | Proposed by the skill, confirmed by the user |\n| Flag thresholds | No | Gap above +5 points in a forecast year; gap above +3 points in three consecutive years ending in a forecast year |\n| Currency basis (reported or constant) | No | Reported |\n\n## Workflow\n\n1. Validate the internal file: list the segment-country pairs and years, and confirm each pair has at least two consecutive years.\n2. Propose a mapping from each internal segment to a market segment available in the data connector, with a confidence of exact, close or loose. Show the mapping table and wait for confirmation; taxonomy mismatch is the main cause of a wrong conclusion.\n3. For each confirmed pair, fetch the market revenue series for the same years. Save all pairs in one CSV with columns `segment,country,year,market_revenue`, using the internal segment names.\n4. Run `scripts/growth_gap.py --internal <internal.csv> --market <market.csv>`; pass `--gap-threshold`, `--run-gap` or `--run-years` when the user changed the defaults.\n5. Write the commentary: one line per unflagged pair. For each flagged pair, write a short paragraph with the gap, the implied share change and the question for the owner, such as which initiatives or pricing actions support growth above the market.\n\n## Output format\n\n```\n# Growth versus market: <scope>, <period>\n\n## Mapping used\n| Internal segment | Market segment | Confidence |\n\n## Results\nTable from growth_gap.py.\n\n## Commentary\n\n## Caveats\nMapping confidence, currency basis, source and release date of each market series.\n```\n\n## Data rules\n\n- A share computed against a market estimate is itself an estimate; say so where it is quoted.\n- Compare like with like: growth in reported currency includes exchange-rate effects the market series may not.\n- A flag on a loosely mapped row means fix the mapping first.\n- The internal file stays with the user; the skill reads it for the run and reproduces it only in the results table.\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}