hashgraph-online/awesome-codex-plugins / plugins/boshu2/agentops/skills/doc
doc
VerifiedWrite source-checked docs, READMEs, change descriptions and handoffs. Use when: documenting a change, leaving or resuming a handoff, or drafting a questionnaire for someone else.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 8.0 KB |
| references/agentops-internal.md | markdown | 2.0 KB |
| references/bootstrap/context-routing.md | markdown | 9.0 KB |
| references/bootstrap/examples.md | markdown | 1.2 KB |
| references/change-driven-docs.md | markdown | 6.5 KB |
| references/developer-journey.md | markdown | 5.0 KB |
| references/handoff.md | markdown | 4.6 KB |
| references/oss-pack.md | markdown | 2.2 KB |
| references/prose-and-report-workmanship.md | markdown | 3.6 KB |
| references/questionnaire.md | markdown | 1.7 KB |
| references/readme-craft.md | markdown | 3.2 KB |
| references/validation-rules.md | markdown | 7.0 KB |
| scripts/audit-oss-docs.shexecutable | script | 11.0 KB |
references/prose-and-report-workmanship.md
View on GitHub# Prose And Report Workmanship
Use this reference when documentation needs to read like maintainable project material rather than agent-generated filler.
## Prose Cleanup
Remove writing artifacts that do not help the operator:
- Inflated claims without evidence.
- Repeated "not only/but also" constructions.
- Decorative punctuation or emphasis that hides the main point.
- Meta-commentary about how the document is written.
- Long setup before the command, decision, or finding.
- Labels coined during the work (lane nicknames, internal IDs, invented terms)
and bare identifiers a reader without the code open cannot place. Say what
each one is or does, unless the caller requires the term.
- Structure the content does not need: bullets around an argument (lists suit
parallel items; reasoning reads better as connected sentences), a heading over
a section of a sentence or two, a divider after every section of a short page,
a table for one or two items, or a callout for an aside that would not derail
the main line.
Keep the tone direct, concrete, and source-grounded.
A question about a draft ("does this read generated?") asks for a check: list
each problem with its quoted line and a short suggested fix, and leave the text
unchanged. Report patterns, never a guess about who or what wrote the text. A
request to fix or polish asks for a rewrite: change only the sentences that
show a problem and leave the rest as written. In the caller's own prose keep
their word choice and voice; in a repository document match the surrounding
idiom. A concrete particular (a name, number, path or command) comes from the
source, the repository or the caller; never invent one to make prose specific.
## Order Ideas for a Learner
For a tutorial or explanation, decide which concepts the reader already brings.
Explain every other idea, named or not, before a section relies on it, and pick
each next section by what the reader needs next rather than by the order of
source files, notes or commits. When a section needs an idea not yet explained,
explain it earlier or state it as a prerequisite: too many prerequisites shut
readers out, too many early definitions bury the opening. Track what has been
explained in working notes, not a file.
## Diagrams
Decide per section from what it turns on. A flow across steps or components, an
exchange between parties, a lifecycle, a before-and-after data layout or a
decision boundary often reads faster as a picture; a single point, a rename or a
one-field change needs none. Your own prose seeming clear is no reason to skip
one. Place each diagram beside the sentence it supports and keep only the nodes
that sentence needs. The text states every relationship the diagram shows,
because agents and screen readers read the text; when the two disagree, the
text governs and the diagram gets fixed.
## One Live Statement
Within the authorized scope, when a fact or decision changes, rewrite or remove
the old text rather than striking it through or stacking an "Update" note under
it; version control keeps the history. Records whose history is the content
(changelog entries, ADRs, a handoff's failed attempts) keep it. State a rule,
limit or contract in full in one owning document and link to it elsewhere,
adding only what is local; for an external standard, cite it and name only this
project's differences.
## Final Pass
Before publishing docs:
| Check | Pass condition |
|---|---|
| Evidence | Claims cite code, commands, or source docs. |
| Brevity | Each section earns its place. |
| Operator value | The next reader can act without rediscovery. |
| No filler | Generic AI prose is removed. |
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 |