{"id":86298,"plugin_id":"plugin_asdk_app_6a8399a0bccc819185d57048383c915c","kind":"skill","collection_source":"plugin_package","comparison_source":null,"observed_at":"2026-11-09T00:17:03.111Z","digest":"127488f1757f01a9b5cc74488fb9071d23d09043a319601f931fc7c8d192b8d9","against":null,"payload":{"description":"Map the themes a research field is made of and the neighbouring fields around it — which neighbours are growing, which the field is moving toward, and which are fading. Use when the user asks which fields are adjacent to a topic, where a field is heading, which nearby areas are growing, or wants to explore around a theme from an earlier map.","included_files":[{"relative_path":"agents/openai.yaml","size_in_bytes":517},{"relative_path":"assets/pendar-logo.png","size_in_bytes":31724}],"name":"map-a-field","skill_md_contents":"---\nname: map-a-field\ndescription: Map the themes a research field is made of and the neighbouring fields around it — which neighbours are growing, which the field is moving toward, and which are fading. Use when the user asks which fields are adjacent to a topic, where a field is heading, which nearby areas are growing, or wants to explore around a theme from an earlier map.\nmetadata:\n  short-description: Map a field's themes and its growing neighbours\n---\n\n# Map a field\n\nShow what a research field is made of and what lies around it. `field_map` finds\nthe core themes of a topic, then the neighbouring themes that share papers with\nthem, and says for each whether it is growing, fading, or one the field is moving\ntoward. Every theme comes with a position to plot it at.\n\nAfter the first step the field is its core themes, not the phrase the user typed,\nso the map holds up even when the wording is loose.\n\n## Quick start\n\n1. Give exactly one of:\n   - `topic` — a **short noun phrase of two to six words**, as for a survey:\n     \"Which fields are next to solid-state battery electrolytes?\" becomes\n     `solid state battery electrolytes`;\n   - `theme_id` — a theme from an earlier `my_position` or `field_map` result, to\n     explore around it.\n2. Call `field_map` once.\n3. Read `field.core_coverage_pct` before describing the field (see below).\n4. Draw the map when you can (see Drawing), then report.\n\n## Reading the result\n\n- `field` — what was searched (`searched_for`, `matched_on`), how many papers\n  matched (`corpus_papers`), and `core_coverage_pct`: the share of those papers\n  the core themes cover. Low coverage means the phrase spans several fields; say\n  so, and offer to map a narrower phrase or one of the core themes.\n- `themes[].role` — `core` (the field itself) or `neighbour`.\n- `themes[].status`:\n  - `core` — a core theme. A `slowing` tag means it is declining.\n  - `converging` — a close neighbour that is growing and taking a larger share of\n    the field's papers: the field is moving toward it.\n  - `growing_neighbour` — a neighbour with `accelerating` momentum.\n  - `fading_neighbour` — a neighbour with `declining` momentum.\n  - `neighbour` — everything else.\n- `share_of_field_pct` — for a core theme, its share of the field's papers; for a\n  neighbour, the share of core papers also tagged with it.\n  `prior_share_of_field_pct` is the same for the earlier window.\n- `drift` — `gaining`, `losing`, `steady` or `new`: whether the field's papers are\n  moving toward a neighbour, between the two windows of `segment_window`.\n- `similar`, `momentum`, `momentum_vs_area` and `why` read as in\n  `map-my-research`: `similar` means \"tagged on the same papers\", `unknown`\n  momentum means too few papers to say, and `why` is the rule and its numbers in\n  words.\n- `areas` — the surrounding areas, how many themes each holds, and how many of\n  those are growing.\n- `links` — from each neighbour's closest core theme; `strength` repeats\n  `similar`.\n- `notes` — caveats; repeat the ones that bear on what you say.\n\n## Drawing\n\nDraw the map by default when you can: an artifact or code in Claude, the Python\ntool in ChatGPT. When you cannot draw, give a table instead.\n\n- **Position:** the given `x` and `y`. Never recompute or move a theme.\n- **Bubble size:** `papers_recent`, on a log scale.\n- **Fill:** `momentum` in three steps (accelerating, steady, declining); grey for\n  `unknown` and `too_new`.\n- **Outline:** thick for `core`, dashed for `converging`.\n- **Sticks:** `links`, thicker for a higher `strength`.\n- **Labels:** core and converging themes only; list the rest in a legend or table.\n\nNever draw a value that is not in the response.\n\n## Reporting\n\n1. **What the field is made of** — the core themes, their shares and momentum,\n   and the coverage.\n2. **Where it is heading** — the `converging` neighbours, each with its `why`.\n3. **Other growing neighbours.**\n4. **Fading neighbours.**\n5. **The areas around it** — from `areas`.\n6. **Caveats** — from `notes`.\n\n## Never\n\n- Present a growing or converging neighbour as advice on what to work on.\n- Read `drift` as cause and effect. It says where the papers moved, not why.\n- Compare two fields' maps without saying how well each phrase was covered.\n- Add themes, counts, or papers from memory.\n\n## Related workflows\n\n- To see where the user's own work sits on this map, offer `map-my-research`.\n- To size one of the themes, use `survey-a-research-field`.\n- To find journals for the field, use `choose-a-venue`.\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}