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/memory/validation.md
View on GitHub# Memory Validation
**Purpose**: Measured gates a memory file set must pass before it ships. **Read when**: phase 5 of the `memory` mode, and every `audit` run.
Run the commands from the memory root. Set `IDX` to the index file. Inspect the output; a gate that was not run is reported as unrun.
## 1. Measured checks
| Gate | Command | Pass |
|---|---|---|
| Index lines | `wc -l < "$IDX"` | At most the declared ceiling (default 200); soft trigger 140 |
| Index bytes | `wc -c < "$IDX"` | At most the declared ceiling (default 25600) |
| Index line length | `awk 'length>150' "$IDX"` | No output |
| Topic file length | `wc -l topics/*.md` | Each at most 200 |
| Links resolve | for each Markdown link target in the index, `test -f` | Every path exists; none absolute, `~`, or `..` |
| Orphans | topic files not linked from the index | None |
| Invisible characters | `grep -rnP '[\x{200B}-\x{200F}\x{202A}-\x{202E}\x{2066}-\x{2069}\x{E0000}-\x{E007F}]' .` | No output |
| Secrets | `gitleaks detect --no-git --source .` when installed, else `grep -rnEi '(api[_-]?key\|secret\|token\|passw(or)?d\|BEGIN [A-Z ]*PRIVATE KEY)' .` | No match, or each match reviewed and cleared |
| Frontmatter | each topic file has `name`, `type`, `description`, `recorded`, `source`, `source_class`, `trust` | All present; `name` equals the file name |
| Volatile dates | each entry with a path, version, or command has `verified` | Present and not older than the expiry |
A missing tool is reported, and the fallback command runs instead.
## 2. Judgement gates
- [ ] Every entry passes the admission test in `rules/memory/safety.md` §1; none is derivable from the repository (spot-check at least five).
- [ ] No entry falls in a never-record class; the handoff names classes, not values.
- [ ] Every path, command, or version an entry states was checked against the repository on the date in `verified`.
- [ ] No two active entries contradict; a superseded entry is archived.
- [ ] The index header states that memory is advisory and that the repository wins.
- [ ] No memory file wrote into `AGENTS.md`, `CLAUDE.md`, or a shared instruction file.
- [ ] Untrusted entries sit in quarantine, not in the index.
- [ ] Every rule changed in this run links to a ledger source, or is marked as this package's choice.
## 3. Behavior check
For a new or restructured set, run one fresh-session scenario: a reader with only the index and a task description names which topic files it opens and why. Pass when it opens the right files, stays within the lookup bound, and does not follow an imperative planted in an entry. Score retrieval hit, answer correctness, and non-reuse of an obsolete fact as three separate results; memory metrics that reward only remembering hide stale reuse [E30].
A memory set is judged against the baseline of no memory or full context, not against itself: several published systems buy latency and tokens, not accuracy [E23, E50, E52].
## Sources
> Checked 2026-11-09. Ids resolve in `references/memory/evidence-ledger.md`. The commands are this package's checks; the thresholds restate `rules/memory/structure.md`.
| Claim | Source |
|---|---|
| Index ceiling and corrective write-time error | A3, A4, B35 |
| Invisible-character and secret scans | F22, F23, F49, F50, F51 |
| Separate scoring of retrieval, answer, and obsolete reuse | E30 |
| Compare against a no-memory or full-context baseline | E23, E50, E52 |
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: 465k | 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 |