Progressive Disclosure
Use this repo-local meta skill to split large skills into a concise SKILL.md plus adjacent reference files. This guides content moves and reference creation; it is not a content rewrite pass.
Guardrails
- Do not rewrite, reinterpret, simplify, or change the meaning of skill content.
- Do not delete details because they seem verbose. Move details to reference files instead.
- Do not change SDK guidance, commands, workflows, safety notes, or examples except to preserve links after moving content.
- Do not edit plugin manifests, versions,
CODEOWNERS, or unrelated repo metadata unless the user explicitly asks.
- Do not create deeply nested references. Reference files should be directly linked from
SKILL.md.
- Do not move first-use trigger guidance, required safety constraints, or critical prerequisites out of
SKILL.md.
- If content needs substantive editing, stop and ask the user before making that change.
Target Shape
Keep SKILL.md focused on:
- Frontmatter with accurate
name and description
- When to use the skill
- Quick start or primary workflow
- Key decision points and safety constraints
- Direct links to reference files
Move long supporting content into files such as:
reference.md
examples.md
troubleshooting.md
platform-setup.md
sdk-operations.md
ci-cd-patterns.md
Choose names that match the moved section. Prefer a small number of meaningful files over many tiny fragments.
Use folders only when the supporting material has a clear type or grouping:
references/ for longer conceptual guides, examples, and workflow details
scripts/ for executable helpers that the skill may ask the agent to run
- Language folders such as
python/, typescript/, or r/ when a skill supports multiple programming languages
Keep these folders directly under the skill directory. SKILL.md should link directly to files inside them, such as references/workflow-details.md, without requiring the agent to follow a chain of references.
Workflow
Inspect the target skill:
- Read
skills/<skill-name>/SKILL.md.
- Check current line count and major headings.
- Check current token warning/error status from
task test:integration when available.
- Identify sections that are detailed reference material, long examples, command recipes, troubleshooting tables, platform-specific variants, or API details.
Propose the split before editing when the change is substantial:
- List which sections will stay in
SKILL.md.
- List which sections will move and the destination reference file for each.
- Keep a simple traceability map: original heading -> destination file -> replacement link text.
- Confirm any ambiguous sections with the user.
Move content with minimal transformation:
- Preserve headings and body text as much as possible.
- Adjust heading levels only when needed for valid Markdown structure.
- Preserve code blocks exactly unless a relative link/path must change.
- Keep warnings, prerequisites, and safety notes attached to the relevant content.
Replace moved content with concise pointers:
For detailed deployment configuration, see [deployment-reference.md](deployment-reference.md).
Each pointer should explain when to read the reference, not summarize the whole reference.
Keep links one level deep:
SKILL.md should link directly to every reference file the agent may need.
- Reference files may link back to
SKILL.md if useful.
- Avoid chains like
SKILL.md -> references/overview.md -> references/deep-reference.md.
Validate:
- Run
task test:integration for structural checks.
- Run
task lint when tooling is available.
- If the goal is reducing context-window warnings, rerun the relevant tests and compare warning output. This repo warns at an estimated 3300 tokens and errors at 6700 tokens.
Candidate Section Heuristics
Good move candidates:
- Long examples that are not needed for initial task routing
- Repeated setup variants by platform or provider
- Detailed SDK method inventories
- Troubleshooting catalogs
- Extended CI/CD snippets
- Long validation or debugging procedures
Usually keep in SKILL.md:
- The first-pass decision tree
- Required safety constraints
- Minimal happy-path workflow
- Short command checklist needed for most runs
- Links to all supporting references
Diff Review Checklist
Before finishing, verify:
- Every moved block still exists in a reference file.
SKILL.md links directly to each new reference file.
- The frontmatter
description still includes clear trigger scenarios.
- The final response includes the traceability map for reviewer confidence.
- No instruction, recommendation, or example changed.
- No unrelated formatting churn was introduced.
- Repo validation passes or any local tooling gap is clearly reported.
1---2name: progressive-disclosure3description: Refactor large DataRobot skill files by moving detailed content into directly linked reference files while preserving meaning. Use when a skill triggers context-window warnings, needs progressive disclosure, or should be chunked without changing guidance.4---56# Progressive Disclosure78Use this repo-local meta skill to split large skills into a concise `SKILL.md` plus adjacent reference files. This guides content moves and reference creation; it is not a content rewrite pass.910## Guardrails1112- Do not rewrite, reinterpret, simplify, or change the meaning of skill content.13- Do not delete details because they seem verbose. Move details to reference files instead.14- Do not change SDK guidance, commands, workflows, safety notes, or examples except to preserve links after moving content.15- Do not edit plugin manifests, versions, `CODEOWNERS`, or unrelated repo metadata unless the user explicitly asks.16- Do not create deeply nested references. Reference files should be directly linked from `SKILL.md`.17- Do not move first-use trigger guidance, required safety constraints, or critical prerequisites out of `SKILL.md`.18- If content needs substantive editing, stop and ask the user before making that change.1920## Target Shape2122Keep `SKILL.md` focused on:2324- Frontmatter with accurate `name` and `description`25- When to use the skill26- Quick start or primary workflow27- Key decision points and safety constraints28- Direct links to reference files2930Move long supporting content into files such as:3132- `reference.md`33- `examples.md`34- `troubleshooting.md`35- `platform-setup.md`36- `sdk-operations.md`37- `ci-cd-patterns.md`3839Choose names that match the moved section. Prefer a small number of meaningful files over many tiny fragments.4041Use folders only when the supporting material has a clear type or grouping:4243- `references/` for longer conceptual guides, examples, and workflow details44- `scripts/` for executable helpers that the skill may ask the agent to run45- Language folders such as `python/`, `typescript/`, or `r/` when a skill supports multiple programming languages4647Keep these folders directly under the skill directory. `SKILL.md` should link directly to files inside them, such as `references/workflow-details.md`, without requiring the agent to follow a chain of references.4849## Workflow50511. Inspect the target skill:52 - Read `skills/<skill-name>/SKILL.md`.53 - Check current line count and major headings.54 - Check current token warning/error status from `task test:integration` when available.55 - Identify sections that are detailed reference material, long examples, command recipes, troubleshooting tables, platform-specific variants, or API details.56572. Propose the split before editing when the change is substantial:58 - List which sections will stay in `SKILL.md`.59 - List which sections will move and the destination reference file for each.60 - Keep a simple traceability map: original heading -> destination file -> replacement link text.61 - Confirm any ambiguous sections with the user.62633. Move content with minimal transformation:64 - Preserve headings and body text as much as possible.65 - Adjust heading levels only when needed for valid Markdown structure.66 - Preserve code blocks exactly unless a relative link/path must change.67 - Keep warnings, prerequisites, and safety notes attached to the relevant content.68694. Replace moved content with concise pointers:7071 ```markdown72 For detailed deployment configuration, see [deployment-reference.md](deployment-reference.md).73 ```7475 Each pointer should explain when to read the reference, not summarize the whole reference.76775. Keep links one level deep:78 - `SKILL.md` should link directly to every reference file the agent may need.79 - Reference files may link back to `SKILL.md` if useful.80 - Avoid chains like `SKILL.md` -> `references/overview.md` -> `references/deep-reference.md`.81826. Validate:83 - Run `task test:integration` for structural checks.84 - Run `task lint` when tooling is available.85 - If the goal is reducing context-window warnings, rerun the relevant tests and compare warning output. This repo warns at an estimated 3300 tokens and errors at 6700 tokens.8687## Candidate Section Heuristics8889Good move candidates:9091- Long examples that are not needed for initial task routing92- Repeated setup variants by platform or provider93- Detailed SDK method inventories94- Troubleshooting catalogs95- Extended CI/CD snippets96- Long validation or debugging procedures9798Usually keep in `SKILL.md`:99100- The first-pass decision tree101- Required safety constraints102- Minimal happy-path workflow103- Short command checklist needed for most runs104- Links to all supporting references105106## Diff Review Checklist107108Before finishing, verify:109110- Every moved block still exists in a reference file.111- `SKILL.md` links directly to each new reference file.112- The frontmatter `description` still includes clear trigger scenarios.113- The final response includes the traceability map for reviewer confidence.114- No instruction, recommendation, or example changed.115- No unrelated formatting churn was introduced.116- Repo validation passes or any local tooling gap is clearly reported.