{"id":20884,"plugin_id":"plugins_6aa93d4d067c8191bdd2a1969bee8916","kind":"skill","collection_source":null,"comparison_source":null,"observed_at":"2026-09-30T23:16:38.036Z","digest":"6409bf3a0e8333ad3712825a75f81a930ac0aa0af7124055d985f2231f500d07","against":null,"payload":{"description":"The conventions this plugin names and files ads by — the export filename token grammar, the ad-set folder grammar and global #0000 sequence, language codes and scripts, allocation policy, and the evidence/QA layout. Load whenever languages are being selected or allocated for a batch, whenever an ad file or ad-set folder is being verified against the conventions, or whenever a skill refers to the workspace conventions. Filenames and sequence numbers are produced by the ad-naming skill's tool, which reads these files: this skill is the data, not the tool. These are defaults; a copy of this skill in your own skill folder replaces them. Brand facts live in the brand-* skills, not here.","included_files":[{"relative_path":"README.md","size_in_bytes":1083},{"relative_path":"allocation.json","size_in_bytes":1793},{"relative_path":"evidence.json","size_in_bytes":2190},{"relative_path":"foldering.json","size_in_bytes":2176},{"relative_path":"languages.json","size_in_bytes":5103},{"relative_path":"naming.json","size_in_bytes":2549},{"relative_path":"references/allocation.md","size_in_bytes":1856},{"relative_path":"references/evidence.md","size_in_bytes":1815},{"relative_path":"references/foldering.md","size_in_bytes":3331},{"relative_path":"references/naming.md","size_in_bytes":3002}],"name":"juicylucy","skill_md_contents":"---\nname: juicylucy\ndescription: \"The conventions this plugin names and files ads by — the export filename token grammar, the ad-set folder grammar and global #0000 sequence, language codes and scripts, allocation policy, and the evidence/QA layout. Load whenever languages are being selected or allocated for a batch, whenever an ad file or ad-set folder is being verified against the conventions, or whenever a skill refers to the workspace conventions. Filenames and sequence numbers are produced by the ad-naming skill's tool, which reads these files: this skill is the data, not the tool. These are defaults; a copy of this skill in your own skill folder replaces them. Brand facts live in the brand-* skills, not here.\"\n---\n\n# Workspace conventions\n\nEverything true of how ads are filed, named, allocated, and evidenced — for\nany brand — stated exactly once, as data. Engine skills and tooling read these\nfiles rather than restating them. If you are following a skill that points\nhere and you cannot read these files, **stop and ask** rather than working\nfrom memory: a convention recalled is a convention forked.\n\nThese are the **defaults the plugin ships**. They are a complete, working set:\nan export named under them traces back to its creative, market and version,\nand an ad-set folder carries a number nothing else in the campaign uses. They\nare also yours to change — see § Making them your own.\n\n## What each file owns\n\n| Read | For |\n| --- | --- |\n| [`naming.json`](naming.json) | **The** export filename grammar: the token pattern, per-medium constants (author, format, style vocabularies), funnel stages, the localization inheritance rule. |\n| [`foldering.json`](foldering.json) | **The** ad-set folder grammar: the hierarchy, the token pattern, and the global `#0000` sequence discipline shared across mediums. |\n| [`allocation.json`](allocation.json) | How languages and ad sets are allocated across active campaigns, and how candidates are ranked and excluded. |\n| [`languages.json`](languages.json) | The language table: names, codes, scripts, direction, per-language rendering notes. |\n| [`evidence.json`](evidence.json) | What counts as a final ad, the asset acceptance gate, the `.qa/` package, `PROJECT_STATE.md` conventions, contact-sheet spec. |\n\nProducing a filename, a folder name or a sequence number from this data is the\n`ad-naming` skill's job (`naming.mjs`), for both mediums; nothing here is typed\ninto a name by hand.\n\nThe [`references/`](references/) files carry the prose behind the data — the\nprocedures, worked examples, and checklists. The JSON is authoritative for\nvalues; the references are authoritative for method.\n\n## The discipline the data assumes\n\nFour rules repeat through every convention here, and every consumer is held to\nthem:\n\n1. **Reserve before you write.** Names and numbers are resolved collision-free\n   against the live filesystem before any output is moved into place — never\n   after, and never from memory or a tracker.\n2. **Re-scan immediately before creating.** A reservation made earlier in a\n   session may have been claimed; the scan that counts is the one just before\n   `mkdir` or the final move.\n3. **Rename what the change invalidates.** A folder's `N Ads` token states its\n   actual count; redistribution that changes the count renames the folder.\n4. **The filesystem is authoritative.** Chat updates, trackers, and manifests\n   may lag; direct listings, counts, and hashes settle every disagreement.\n\n## Making them your own\n\nCodex reads a copy of this skill in `~/.agents/skills/juicylucy/` (or in a\nfolder's `.agents/skills/`, while working there) **in place of** the shipped\none — the whole skill, not a merge. The `ad-naming` tool resolves these files\nin the same order, so a local copy changes the filenames and folders the tool\nproduces, and it prints a note on every call while that is so; its `where`\ncommand shows which files it is reading.\n\nTo adopt your own grammar: copy this directory to `~/.agents/skills/juicylucy/`,\nchange the values, keep every filename and every key — the tool reads the\nkeys — and start a new session. If an upload automation of yours parses\nfilenames, its grammar is the one to put in `naming.json`. The setup skill's\n`references/extending.md` § Changing the conventions is the flow.\n\n## What does not belong here\n\nAnything true of one brand only — product scope, compliance rules, brand\nassets, competitor sets, account names — lives in that brand's `brand-*`\nskill. Anything true of one production batch only — dates, chosen languages,\nledgers — lives with the run, laid out per `evidence.json`.\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}