hashgraph-online/awesome-codex-plugins / plugins/alpoxdev/hypercore/skills/hyper-documentation
hyper-documentation
Flagged[Hyper] Use this skill when the user asks to create, refactor, or update a documentation artifact: a project or package README.md, a repository AGENTS.md with its AGENTS.ko.md mirror, an AI-readable instruction base, runbook, specification, or rule pack, a reusable prompt, prompt template, prompt pack, or prompt eval fixture, or an agent's persistent memory files (MEMORY.md index, memory bank, lessons file) with their write, pruning, and deletion rules. It picks one mode from the requested output and grounds every claim in the project and its sources. Do not use for reusable skill folders, CHANGELOG, CONTRIBUTING, LICENSE, release notes, answer-only research, or implementation work; it never writes CLAUDE.md.
rules/agents-md/nested-placement.md
View on GitHub# Nested Placement
**Purpose**: Decide, with recorded measurements, whether a directory earns its own `AGENTS.md`. This is a package heuristic: it orders the decision and never substitutes for reading the repository.
## 1. What the score is
The placement score is a gate that justifies a child file. It is labelled a package heuristic in every report so nobody reads it as a vendor standard. A directory earns a child `AGENTS.md` only when the score says the subtree differs enough to govern on its own. Otherwise the parent covers it.
Never let the score trigger a repository-wide sweep. A bulk hierarchy run still requires an explicit user request; the score only justifies the single child file under review.
## 2. Signals and weights
Measure each signal only when repository evidence supports it. A signal that cannot be measured is `unmeasured`, and `unmeasured` never counts as zero.
| Signal | What to count | Weight |
|---|---|---|
| File count | Source files in the subtree | 2 |
| Subdirectory count | Immediate child directories with shipped code | 2 |
| Code ratio | Share of the subtree that is code rather than docs or data | 2 |
| Unique patterns | Distinct build, test, or convention patterns inside the subtree | 5 |
| Module boundary | A package, workspace, or ownership boundary the subtree crosses | 3 |
| Symbol density | Exports and entry points per file | 1 |
| Exports | Public entry points owned by the subtree | 1 |
| Reference centrality | How much the parent rule and neighboring files point at this subtree | 2 |
Add the weights of the measured signals. Report every `unmeasured` item by name in the run snapshot instead of folding it into the total.
## 3. Thresholds
| Score | Decision |
|---|---|
| Above 15 | The subtree earns a child `AGENTS.md` |
| 8 to 15 | A child file requires a distinct domain difference on top of the score |
| Below 8 | The parent covers the subtree; do not create a child file |
The same score on the same repository MUST NOT produce a different hierarchy between runs. The run snapshot records what was measured so two runs can be compared.
## 4. Depth budget
The depth budget defaults to 3 and limits creation only. A run MUST NOT create a child file deeper than the budget. The budget never deletes deeper existing files; an existing file below the budget stays where it is. Deleting one requires an explicit user request.
## 5. Score evidence row
Each placement decision records the score, the per-signal values, the `unmeasured` items, the depth, and the budget. A placement without those rows is unjustified.
## Sources
> Links checked 2026-11-09. No text or code was copied from the source repository. The mechanism is re-authored in this package's own words.
| Claim | Source |
|---|---|
| The weighted signals, the thresholds above 15 and at 8 to 15, the package-heuristic label, the depth budget default of 3, and the never-delete-below-budget rule in this file | `dbc-hbin/omp-ulw` at commit `74df40f` (2026-11-09); the source repository has no license, so the mechanism was re-authored, not copied |
### Evidence grade
`HEURISTIC` - the score is this package's own decision aid, re-authored from the source above, and not validated against any vendor standard.
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: 467k | 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: 196k | 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: 196k | 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: 196k | Updated | Claude CodeCodex | Verified | Install |