Hello-QM/catgo-LRG / server/catgo/workflow/skills/catgo-campaign-conventions
catgo-campaign-conventions
VerifiedAuthoring conventions for CatGo md-orchestration campaigns — progressive markdown, README+INDEX pairs and keeping them current, logging interventions to LESSONS, human-readable (never-hash) names, and the progressive (top→stage→calc) plan. Use when creating/editing any campaign markdown (plan/README/INDEX/STATUS/LESSONS) so the file tree stays navigable and resumable. Pairs with catgo-campaign.
catgo-campaign-conventions — how to author campaign markdown
TL;DR: Progressive md (TL;DR-first, drill down), a README+INDEX pair at every level kept current, log every intervention to LESSONS, human-readable names (no hashes), and a top→stage→calc progressive plan. These keep the tree navigable + resumable from disk.
Progressive markdown
Every md opens with # title + a > **TL;DR:** line, details below in greppable sections.
Read INDEX.md first; drill into a branch only when you work it. Keep STATUS.md /
LESSONS.md curated, not append-only logs. Don't pile everything into one big md —
split by concern, stitch with INDEX.
README + INDEX pair (kept current)
Every level has a README (description) + INDEX (pointer/navigation).
- When you add a stage or calc folder, update the parent
INDEX.md(one line + role). INDEX is the navigation spine — an empty/stale INDEX breaks drill-down. - Fill the scaffold's stub files — top
README.md(what / goal / current stage),plan.md,cluster.md. Never leave the<...>placeholders the scaffolder writes. - README (human: what the project is) vs CLAUDE.md (agent bootstrap) vs INDEX (pointer) — distinct roles, don't duplicate.
Log every intervention
Any time you cancel / rebuild / retry a calc, change its inputs, or hit a gotcha, record
what changed and why in that calc's LESSONS.md (and the project LESSONS.md if it
generalizes). STATUS.md only holds the CURRENT job — it does not remember a prior
cancelled/failed attempt, so the history lives in LESSONS. (catgo campaign submit updates
STATUS.md automatically; LESSONS is on you.)
Human-readable names (never hashes)
Names are readable; uniqueness comes from the project/stage/calc path hierarchy. A clash
gets a readable -2 suffix, never a digest. The remote work_dir mirrors the local tree.
Progressive plan (top → stage → calc)
- Top
plan.md= only WHAT (goal + the stage list, each line LINKING to that stage's plan). calc/<stage>/plan.md= mid-level detail + links to its calcs.calc/<stage>/<calc>/plan.md= the FULL recipe (method, params + rationale, convergence, freq/restart strategy, result to extract, dependencies). Keep the top short; push specifics down. (Flat campaign with no stages → two levels suffice.)
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). | Stars: 198k | Updated | Claude CodeCodex | Unverified | Install |
| doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |