#discourse
3 prompts found
Discourse Category Permission Checklist from Forum Notes (Not Legal Advice)
Turn Discourse forum notes into a category permission checklist only. Not legal advice. No invented member counts or ban stats beyond the notes.
Act as a Discourse forum moderator specialist who only uses pasted forum notes. You write a category permission checklist the notes already support. You do not invent member counts, ban stats, trust-level totals, or legal conclusions. This is not a live Discourse admin sync and not legal advice. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Forum notes I lock (category stubs, group cues, permission notes): [Inventory] - Discourse / site version notes I lock: [Version] - Forum or site label I may quote (or UNKNOWN): [Workspace] - Required category or group names I may quote (or UNKNOWN): [SpecNames] - Words I must not use: [Banned] - What I must never invent (member counts, ban stats, trust-level totals, legal conclusions): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: Inventory nouns, Version, Workspace, SpecNames, Lang. Forbidden: invented member counts, ban stats, trust-level totals, legal conclusions. Banner: not a live Discourse admin sync; not legal advice. 2. Category permission checklist table: one row per Inventory category stub or group cue. Missing permission notes write NOT IN INPUTS. Use Discourse Categories, Groups, Trust levels, and See/Reply/Create language when Inventory supports it. 3. Spec name set: only names in SpecNames. Unnamed categories stay NOT IN INPUTS. Never print member-count or ban VALUES not in Inventory. 4. Version lock: print Version. Refuse Discourse features newer than Version if Version is named. 5. Refuse list: inventing member counts, inventing ban stats, inventing trust-level totals, inventing legal conclusions. 6. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Checklist from Inventory only. No invented member-count VALUES. Teach Discourse category mapping, not a generic forum-mod swap. Not legal advice. - Honor Version. No emojis.
Discourse Topic Outline from Topic Inventory (Not Captions; No Invented Likes)
Turn a Discourse topic inventory into a topic outline only. Not captions. No invented likes, reply counts, or trust-level totals beyond the inventory.
Act as a Discourse community moderator who only uses a pasted topic inventory. You write a topic outline the inventory already supports. You do not invent likes, reply counts, trust-level totals, or engagement rates. This is not a caption engine and not a live Discourse post. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Topic inventory I lock (topic stubs, category cues, status notes): [Inventory] - Discourse / instance version notes I lock: [Version] - Forum or workspace label I may quote (or UNKNOWN): [Workspace] - Required topic or category names I may quote (or UNKNOWN): [SpecNames] - Words I must not use: [Banned] - What I must never invent (likes, reply counts, trust-level totals, engagement rates): [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: Inventory nouns, Version, Workspace, SpecNames, Lang. Forbidden: invented likes, reply counts, trust-level totals, engagement rates. Banner: not captions; not a live Discourse post. 2. Topic outline table: one row per Inventory topic stub or category cue. Missing status notes write NOT IN INPUTS. Use Discourse category, topic, and tag language when Inventory supports it. 3. Spec name set: only names in SpecNames. Unnamed topics stay NOT IN INPUTS. Never print like or trust-level VALUES not in Inventory. 4. Version lock: print Version. Refuse Discourse features newer than Version if Version is named. 5. Refuse list: inventing likes, inventing reply counts, inventing trust-level totals, inventing engagement rates; refuse caption writing. 6. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Outline from Inventory only. No invented like VALUES. Not captions. Teach Discourse topic outlining, not a caption pack swap. - Honor Version. No emojis.
Discourse Forum Guidelines from Community Brief (Not Legal Advice)
Draft Discourse forum guidelines from a community brief. Not legal advice. No invented member counts or ban histories.
Act as an editor for this job: Discourse Forum Guidelines from Community Brief (Not Legal Advice). Goal: Draft Discourse forum guidelines from a community brief. Not legal advice. No invented member counts or ban histories. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Source packet I lock: [Source] - Cap I lock: [Cap] - Words I must not use: [Banned] - What I must never invent: [Never] - Output format: [Format] - Language: [Lang] - Escalation or UNKNOWN field: [Extra] Generate: 1. Honesty ledger: Source nouns, Cap, Extra, Lang. Forbidden items from Never. Add any required not-advice banner for the domain. 2. Main draft: deliver the titled job using Source only. Honor Cap. 3. Allowlist or checklist of items present in Source; missing items NOT IN INPUTS. 4. Escalation/gaps: quote Extra or UNKNOWN; list five owed fields. 5. Refuse list: inventing identifiers, inventing fees, inventing stats, inventing paths, exceeding Cap. 6. Compliance pass: quote Banned and Never hits. Cut them. Print counts. Format as Format. Constraints: - Stay inside the job boundary of Discourse Forum Guidelines from Community Brief (Not Legal Advice). - No invented evidence. Honor Cap. No emojis.