ai-disclosure
Use when writing or modifying OCaml code to annotate AI involvement. Triggers on any code generation, editing, or autonomous agent output in .ml/.mli files. Also use when creating or updating .opam files for packages containing AI-involved code.
What this skill does
# OCaml AI Content Disclosure ## When to Use Annotate AI disclosure when you: - Generate new OCaml modules or functions - Edit existing OCaml code with AI assistance - Create or modify `.opam` files for packages with AI-involved code ## Disclosure Values Four values, identical to the W3C AI Content Disclosure vocabulary: | Value | When to use | |-------|-------------| | `none` | Positive assertion: no AI was involved | | `ai-assisted` | Human-authored, AI edited or refined | | `ai-generated` | AI-generated with human prompting/review | | `autonomous` | AI-generated without human oversight | **No annotation = unknown.** Only use `none` as an affirmative claim. ## Granularity Rules **Prefer per-module. Use per-item only when individual bindings differ.** 1. If the entire file has a single disclosure level, use a module-level floating attribute. 2. If most of the file shares one level but a few items differ, use module-level for the dominant level and item-level overrides for exceptions. 3. Never annotate every function individually when a single module-level attribute suffices. Declare the dominant level; tooling infers heterogeneity from overrides. ## Syntax ### Module-level (floating attribute, applies to entire file) ```ocaml [@@@ai_disclosure "ai-generated"] [@@@ai_model "claude-opus-4"] [@@@ai_provider "Anthropic"] ``` Raplce the ai_model and ai_provider with your own information. Place these after any copyright header and `open` statements, before the first definition. ### Item-level (declaration attribute, applies to one binding) ```ocaml let merge_sort xs = ... [@@ai_disclosure "ai-assisted"] ``` ### Interface files (.mli) Annotate `.mli` independently of `.ml`. The interface records AI involvement in API design; the implementation records AI involvement in code. ## opam Package Level For each package in the project, create or update a `<package>.opam.template` file with the `x-ai-*` extension fields. Dune merges `.opam.template` contents into the generated `.opam` file, so these fields survive `dune build @install` and opam file regeneration. ``` x-ai-disclosure: "ai-generated" x-ai-model: "claude-opus-4" x-ai-provider: "Anthropic" ``` If the `.opam.template` file does not yet exist, create it with just the disclosure fields. If it already exists, append the fields. Use the dominant disclosure level as the package default. Individual modules override where they differ. A future dune language version will support these as first-class fields in the `(package)` stanza, eliminating the need for `.opam.template`: ```lisp (package (name foo) (ai_disclosure (level ai-generated) (model "claude-opus-4") (provider "Anthropic"))) ``` ## Common Patterns **Entire file generated by AI:** ```ocaml [@@@ai_disclosure "ai-generated"] [@@@ai_model "claude-opus-4"] [@@@ai_provider "Anthropic"] let foo = ... let bar = ... ``` **Human file with one AI-generated function:** ```ocaml [@@@ai_disclosure "ai-assisted"] let human_written x = ... let ai_helper y = ... [@@ai_disclosure "ai-generated"] ``` **Agent-generated code without human review:** ```ocaml [@@@ai_disclosure "autonomous"] [@@@ai_model "claude-opus-4"] [@@@ai_provider "Anthropic"] ``` ## What NOT to Annotate - Do not annotate files you did not create or modify. - Do not change existing disclosure annotations unless the code itself changed. - Do not annotate non-OCaml files with OCaml attributes (use opam x-fields for package metadata).
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.