SuperAPI AI Directory

project-intel

General & other

View repository

Updated 10-30 16:20

About this skill

Project Intel

The operator's project history already proves a large number of approaches and disproves others. Re-searching settled questions burns tokens and re-introduces known-bad paths. This skill carries the settled results, one card per project class.

Use

  1. Identify the project class and load the one card that matches the router below. Never load all cards.
  2. Treat every card line as evidence with a date, not eternal truth. Cards state what was observed, when, and how strongly.
  3. Freshness rule. Judge evidence by its date, version, reproducibility and relevance, not the model that wrote it. Old tool output can still prove a stable invariant; a new model's assertion is not runtime proof. Model, price and tool facts rot fastest: verify live before advising on them.
  4. When new work proves or disproves something durable, append a dated line to the matching card. One line, with the date and the strength of evidence. Write a workflow-scoped lesson, never a bare verdict: workflow/build -> what was tried -> result -> cause -> what worked instead -> evidence (strength, scope) -> recheck when. "X does not work" is not a lesson; "in workflow W, X failed because C, and Y worked" is. A failure seen in one workflow must not be generalized to another, and a dead end is only dead until its recheck trigger.
  5. These cards ship in a public repository. Never write personal data, real names, machine-specific absolute paths, credentials, or private account details into them. Machine-private detail belongs in a local-only folder that is gitignored and never published.

Router

Starting / resuming… Load
Skyrim SE/AE authoring: frameworks, crashes, conflicts, FOMOD, assets references/skyrim-modding.md
Nexus pages, releases, permissions, archive downloads references/skyrim-release.md
BDO, Helldivers 2, Saints Row, GTA/FiveM, RimWorld, Sims 4, Minecraft, Warframe references/game-modding-other.md
Model choice, harness routing, MCP wiring, agent cost control references/ai-models-harness.md
Game mashups by passthrough, Melty mashups and cross-engine character/asset swaps - only when the task is a mashup or an explicit two-game fusion; an ordinary mod uses its game card - plus UE4SS, ReShade add-ons, pre-UI draw, skeleton retargeting (workflow: game-mashup-passthrough) references/game-mashup-melty.md
Native Windows apps, browser extensions, installers, packaging references/apps-native-windows.md
Reverse engineering, cracking, exploits, malware false positives references/security-re.md

Rules that apply to every card

  • A card is a starting point, not a substitute for the task's own verification: reproduce the load order / build / log before trusting any line here.
  • When a card conflicts with what the user says they just observed, the user's fresh observation wins; then update the card.
  • Prefer linking to the bundle's dedicated skills for syntax-level work (Skyrim frameworks, Papyrus, FOMOD, packaging) over duplicating them here.