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.
references/prompt/prompt-pack-schema.md
View on GitHub# Prompt Pack Schema
**Purpose**: Define the pack fields a parser consumes. **Read when**: a full pack or a parser-consumed schema is requested.
Use this schema for reusable prompt artifacts. Keep keys stable when an eval harness or downstream script reads them.
```yaml
identity:
name: ""
role: ""
responsibility: ""
intent:
user_goal: ""
success_criteria: []
failure_criteria: []
trigger:
use_when: []
do_not_use_when: []
scope:
in_scope: []
out_of_scope: []
side_effect_limits: []
authority:
priority_order: []
conflict_rule: ""
binding_rules: [] # developer-level: valid on every run
advisory_rules: [] # defaults a user may override
untrusted_data_shaping: "yaml | json | xml | labeled-block"
evidence:
required_sources: []
source_ledger: ""
tools:
allowed: []
gated: []
variables:
required: []
optional: []
context_packet:
documents: []
material_order: "documents first, question and output format last"
assumptions: []
missing_information: []
volatile_tail: [] # date, current task, per-turn values appended last
examples:
positive: []
negative: []
constraints:
style: []
safety: []
reasoning_visibility: "Do not request hidden chain-of-thought; ask for public rationale and verification evidence."
output_shape: "instructions | example | schema" # never a prefilled assistant turn
output_schema:
format: "markdown | json | yaml"
fields: []
forbidden: []
eval_cases:
fixture: ""
categories: [positive, negative, boundary, workflow, source, safety, regression, adversarial]
runs: 0
aggregation: ""
grader_version: ""
version_note:
version: ""
changed: []
rationale: ""
remaining_risk: ""
```
## Required Sections
Every prompt pack should include identity, variables, context packet, examples, constraints, output schema, eval cases, and version note even when some values are intentionally empty with a reason.
## Field Rules
- `authority.binding_rules` and `authority.advisory_rules` are separated so a lower layer cannot silently override a higher one. A rule listed as advisory must not read like a prohibition.
- `context_packet.material_order` and `context_packet.volatile_tail` keep the stable prefix stable. Anything that must outlive a compaction belongs in a file, not in this block.
- `constraints.output_shape` names how the shape is expressed. A prefilled assistant turn is not an option: current Claude models reject a prefilled last assistant message with a 400 error.
- `eval_cases.runs` and `eval_cases.aggregation` are per case. `eval_cases.grader_version` changes whenever the judge changes, and a grader change makes earlier scores incomparable.
When `format` is `json` or `yaml`, define exact key names and types, reject malformed required inputs, and include a schema eval that parses the output. Do not accept prose that merely mentions the required fields.
## Sources
> Checked 2026-11-03 against the repository instruction base.
| Claim | Source | Checked |
|---|---|---|
| Authority levels and untrusted-data framing | `instructions/context-engineering/references/prompt-authoring.md` | 2026-11-03 |
| Stable prefix and volatile tail | `instructions/cache/CACHE.md` | 2026-11-03 |
| Per-case runs, aggregation, and the grader version in the record | `instructions/harness-engineering/HARNESS_ENGINEERING.md` | 2026-11-03 |
| Prefilled responses rejected on current Claude models | <https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices> | 2026-11-03 |
No other external URL is cited; the schema rules restate the repository base above.
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 |