opencode-skills-collection 2.0.70 → 2.0.72

package/bundled-skills/hugging-face-dataset-viewer/SKILL.md

@@ -4,124 +4,128 @@ name: hugging-face-dataset-viewer
 description: Query Hugging Face datasets through the Dataset Viewer API for splits, rows, search, filters, and parquet links.
 risk: unknown
 ---
-
+
 # Hugging Face Dataset Viewer
 
 ## When to Use
-
 Use this skill when you need read-only exploration of a Hugging Face dataset through the Dataset Viewer API.
-
-Use this skill to execute read-only Dataset Viewer API calls for dataset exploration and extraction.
-
-## Core workflow
-
-1. Optionally validate dataset availability with `/is-valid`.
-2. Resolve `config` + `split` with `/splits`.
-3. Preview with `/first-rows`.
-4. Paginate content with `/rows` using `offset` and `length` (max 100).
-5. Use `/search` for text matching and `/filter` for row predicates.
-6. Retrieve parquet links via `/parquet` and totals/metadata via `/size` and `/statistics`.
-
-## Defaults
-
-- Base URL: `https://datasets-server.huggingface.co`
-- Default API method: `GET`
-- Query params should be URL-encoded.
-- `offset` is 0-based.
-- `length` max is usually `100` for row-like endpoints.
-- Gated/private datasets require `Authorization: Bearer <HF_TOKEN>`.
-
-## Dataset Viewer
-
-- `Validate dataset`: `/is-valid?dataset=<namespace/repo>`
-- `List subsets and splits`: `/splits?dataset=<namespace/repo>`
-- `Preview first rows`: `/first-rows?dataset=<namespace/repo>&config=<config>&split=<split>`
-- `Paginate rows`: `/rows?dataset=<namespace/repo>&config=<config>&split=<split>&offset=<int>&length=<int>`
-- `Search text`: `/search?dataset=<namespace/repo>&config=<config>&split=<split>&query=<text>&offset=<int>&length=<int>`
-- `Filter with predicates`: `/filter?dataset=<namespace/repo>&config=<config>&split=<split>&where=<predicate>&orderby=<sort>&offset=<int>&length=<int>`
-- `List parquet shards`: `/parquet?dataset=<namespace/repo>`
-- `Get size totals`: `/size?dataset=<namespace/repo>`
-- `Get column statistics`: `/statistics?dataset=<namespace/repo>&config=<config>&split=<split>`
-- `Get Croissant metadata (if available)`: `/croissant?dataset=<namespace/repo>`
-
-Pagination pattern:
-
-```bash
-curl "https://datasets-server.huggingface.co/rows?dataset=stanfordnlp/imdb&config=plain_text&split=train&offset=0&length=100"
-curl "https://datasets-server.huggingface.co/rows?dataset=stanfordnlp/imdb&config=plain_text&split=train&offset=100&length=100"
-```
-
-When pagination is partial, use response fields such as `num_rows_total`, `num_rows_per_page`, and `partial` to drive continuation logic.
-
-Search/filter notes:
-
-- `/search` matches string columns (full-text style behavior is internal to the API).
-- `/filter` requires predicate syntax in `where` and optional sort in `orderby`.
-- Keep filtering and searches read-only and side-effect free.
-
-## Querying Datasets
-
-Use `npx parquetlens` with Hub parquet alias paths for SQL querying.
-
-Parquet alias shape:
-
-```text
-hf://datasets/<namespace>/<repo>@~parquet/<config>/<split>/<shard>.parquet
-```
-
-Derive `<config>`, `<split>`, and `<shard>` from Dataset Viewer `/parquet`:
-
-```bash
-curl -s "https://datasets-server.huggingface.co/parquet?dataset=cfahlgren1/hub-stats" \
-  | jq -r '.parquet_files[] | "hf://datasets/\(.dataset)@~parquet/\(.config)/\(.split)/\(.filename)"'
-```
-
-Run SQL query:
-
-```bash
-npx -y -p parquetlens -p @parquetlens/sql parquetlens \
-  "hf://datasets/<namespace>/<repo>@~parquet/<config>/<split>/<shard>.parquet" \
-  --sql "SELECT * FROM data LIMIT 20"
-```
-
-### SQL export
-
-- CSV: `--sql "COPY (SELECT * FROM data LIMIT 1000) TO 'export.csv' (FORMAT CSV, HEADER, DELIMITER ',')"`
-- JSON: `--sql "COPY (SELECT * FROM data LIMIT 1000) TO 'export.json' (FORMAT JSON)"`
-- Parquet: `--sql "COPY (SELECT * FROM data LIMIT 1000) TO 'export.parquet' (FORMAT PARQUET)"`
-
-## Creating and Uploading Datasets
-
-Use one of these flows depending on dependency constraints.
-
-Zero local dependencies (Hub UI):
-
-- Create dataset repo in browser: `https://huggingface.co/new-dataset`
-- Upload parquet files in the repo "Files and versions" page.
-- Verify shards appear in Dataset Viewer:
-
-```bash
-curl -s "https://datasets-server.huggingface.co/parquet?dataset=<namespace>/<repo>"
-```
-
-Low dependency CLI flow (`npx @huggingface/hub` / `hfjs`):
-
-- Set auth token:
-
-```bash
-export HF_TOKEN=<your_hf_token>
-```
-
-- Upload parquet folder to a dataset repo (auto-creates repo if missing):
-
-```bash
-npx -y @huggingface/hub upload datasets/<namespace>/<repo> ./local/parquet-folder data
-```
-
-- Upload as private repo on creation:
-
-```bash
-npx -y @huggingface/hub upload datasets/<namespace>/<repo> ./local/parquet-folder data --private
-```
-
-After upload, call `/parquet` to discover `<config>/<split>/<shard>` values for querying with `@~parquet`.
+
+Use this skill to execute read-only Dataset Viewer API calls for dataset exploration and extraction.
+
+## Core workflow
+
+1. Optionally validate dataset availability with `/is-valid`.
+2. Resolve `config` + `split` with `/splits`.
+3. Preview with `/first-rows`.
+4. Paginate content with `/rows` using `offset` and `length` (max 100).
+5. Use `/search` for text matching and `/filter` for row predicates.
+6. Retrieve parquet links via `/parquet` and totals/metadata via `/size` and `/statistics`.
+
+## Defaults
+
+- Base URL: `https://datasets-server.huggingface.co`
+- Default API method: `GET`
+- Query params should be URL-encoded.
+- `offset` is 0-based.
+- `length` max is usually `100` for row-like endpoints.
+- Gated/private datasets require `Authorization: Bearer <HF_TOKEN>`.
+
+## Dataset Viewer
+
+- `Validate dataset`: `/is-valid?dataset=<namespace/repo>`
+- `List subsets and splits`: `/splits?dataset=<namespace/repo>`
+- `Preview first rows`: `/first-rows?dataset=<namespace/repo>&config=<config>&split=<split>`
+- `Paginate rows`: `/rows?dataset=<namespace/repo>&config=<config>&split=<split>&offset=<int>&length=<int>`
+- `Search text`: `/search?dataset=<namespace/repo>&config=<config>&split=<split>&query=<text>&offset=<int>&length=<int>`
+- `Filter with predicates`: `/filter?dataset=<namespace/repo>&config=<config>&split=<split>&where=<predicate>&orderby=<sort>&offset=<int>&length=<int>`
+- `List parquet shards`: `/parquet?dataset=<namespace/repo>`
+- `Get size totals`: `/size?dataset=<namespace/repo>`
+- `Get column statistics`: `/statistics?dataset=<namespace/repo>&config=<config>&split=<split>`
+- `Get Croissant metadata (if available)`: `/croissant?dataset=<namespace/repo>`
+
+Pagination pattern:
+
+```bash
+curl "https://datasets-server.huggingface.co/rows?dataset=stanfordnlp/imdb&config=plain_text&split=train&offset=0&length=100"
+curl "https://datasets-server.huggingface.co/rows?dataset=stanfordnlp/imdb&config=plain_text&split=train&offset=100&length=100"
+```
+
+When pagination is partial, use response fields such as `num_rows_total`, `num_rows_per_page`, and `partial` to drive continuation logic.
+
+Search/filter notes:
+
+- `/search` matches string columns (full-text style behavior is internal to the API).
+- `/filter` requires predicate syntax in `where` and optional sort in `orderby`.
+- Keep filtering and searches read-only and side-effect free.
+
+## Querying Datasets
+
+Use `npx parquetlens` with Hub parquet alias paths for SQL querying.
+
+Parquet alias shape:
+
+```text
+hf://datasets/<namespace>/<repo>@~parquet/<config>/<split>/<shard>.parquet
+```
+
+Derive `<config>`, `<split>`, and `<shard>` from Dataset Viewer `/parquet`:
+
+```bash
+curl -s "https://datasets-server.huggingface.co/parquet?dataset=cfahlgren1/hub-stats" \
+  | jq -r '.parquet_files[] | "hf://datasets/\(.dataset)@~parquet/\(.config)/\(.split)/\(.filename)"'
+```
+
+Run SQL query:
+
+```bash
+npx -y -p parquetlens -p @parquetlens/sql parquetlens \
+  "hf://datasets/<namespace>/<repo>@~parquet/<config>/<split>/<shard>.parquet" \
+  --sql "SELECT * FROM data LIMIT 20"
+```
+
+### SQL export
+
+- CSV: `--sql "COPY (SELECT * FROM data LIMIT 1000) TO 'export.csv' (FORMAT CSV, HEADER, DELIMITER ',')"`
+- JSON: `--sql "COPY (SELECT * FROM data LIMIT 1000) TO 'export.json' (FORMAT JSON)"`
+- Parquet: `--sql "COPY (SELECT * FROM data LIMIT 1000) TO 'export.parquet' (FORMAT PARQUET)"`
+
+## Creating and Uploading Datasets
+
+Use one of these flows depending on dependency constraints.
+
+Zero local dependencies (Hub UI):
+
+- Create dataset repo in browser: `https://huggingface.co/new-dataset`
+- Upload parquet files in the repo "Files and versions" page.
+- Verify shards appear in Dataset Viewer:
+
+```bash
+curl -s "https://datasets-server.huggingface.co/parquet?dataset=<namespace>/<repo>"
+```
+
+Low dependency CLI flow (`npx @huggingface/hub` / `hfjs`):
+
+- Set auth token:
+
+```bash
+export HF_TOKEN=<your_hf_token>
+```
+
+- Upload parquet folder to a dataset repo (auto-creates repo if missing):
+
+```bash
+npx -y @huggingface/hub upload datasets/<namespace>/<repo> ./local/parquet-folder data
+```
+
+- Upload as private repo on creation:
+
+```bash
+npx -y @huggingface/hub upload datasets/<namespace>/<repo> ./local/parquet-folder data --private
+```
+
+After upload, call `/parquet` to discover `<config>/<split>/<shard>` values for querying with `@~parquet`.
+
+## Limitations
+- Use this skill only when the task clearly matches the scope described above.
+- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
+- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

package/bundled-skills/hugging-face-datasets/SKILL.md

@@ -9,7 +9,6 @@ source: community
 This skill provides tools to manage datasets on the Hugging Face Hub with a focus on creation, configuration, content management, and SQL-based data manipulation. It is designed to complement the existing Hugging Face MCP server by providing dataset editing and querying capabilities.
 
 ## When to Use
-
 - You need to create, configure, or update datasets on the Hugging Face Hub.
 - You want SQL-style querying, transformation, or export flows over Hub datasets.
 - You are managing dataset content and metadata directly rather than only searching existing datasets.
@@ -548,3 +547,8 @@ uv run scripts/dataset_manager.py add_rows \
   --template qa \
   --rows_json "$(cat processed_data.json)"
 ```
+
+## Limitations
+- Use this skill only when the task clearly matches the scope described above.
+- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
+- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

package/bundled-skills/hugging-face-evaluation/SKILL.md

@@ -12,7 +12,6 @@ This skill provides tools to add structured evaluation results to Hugging Face m
 - Running custom model evaluations with vLLM or accelerate backends (lighteval/inspect-ai)
 
 ## When to Use
-
 - You need to add structured evaluation results to a Hugging Face model card.
 - You want to import benchmark data or run custom evaluations with vLLM, lighteval, or inspect-ai.
 - You are preparing leaderboard-compatible `model-index` metadata for a model release.
@@ -656,3 +655,8 @@ def update_model_evaluations(repo_id, readme_content):
     else:
         print(f"Error: {result.stderr}")
 ```
+
+## Limitations
+- Use this skill only when the task clearly matches the scope described above.
+- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
+- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

package/bundled-skills/hugging-face-gradio/SKILL.md

@@ -8,7 +8,6 @@ risk: unknown
 # Gradio
 
 ## When to Use
-
 Use this skill when a user wants a Gradio demo, UI prototype, or Python-based ML interface.
 
 Gradio is a Python library for building interactive web UIs and ML demos. This skill covers the core API, patterns, and examples.
@@ -302,3 +301,8 @@ Both commands accept `--token` for accessing private Spaces.
 ## Additional Reference
 
 - [End-to-End Examples](examples.md) — complete working apps
+
+## Limitations
+- Use this skill only when the task clearly matches the scope described above.
+- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
+- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

package/bundled-skills/hugging-face-jobs/SKILL.md

@@ -1043,3 +1043,8 @@ Add to PEP 723 header:
 | Schedule Docker | `hf_jobs("scheduled run", {...})` | `hf jobs scheduled run SCHEDULE image cmd` | `create_scheduled_job()` |
 | List scheduled | `hf_jobs("scheduled ps")` | `hf jobs scheduled ps` | `list_scheduled_jobs()` |
 | Delete scheduled | `hf_jobs("scheduled delete", {...})` | `hf jobs scheduled delete <id>` | `delete_scheduled_job()` |
+
+## Limitations
+- Use this skill only when the task clearly matches the scope described above.
+- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
+- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

package/bundled-skills/hugging-face-model-trainer/SKILL.md

@@ -717,3 +717,8 @@ Add to PEP 723 header:
 8. **Use hf_doc_fetch/hf_doc_search** for latest TRL documentation
 9. **Validate dataset format** before training with dataset inspector (see Dataset Validation section)
 10. **Choose appropriate hardware** for model size; use LoRA for models >7B
+
+## Limitations
+- Use this skill only when the task clearly matches the scope described above.
+- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
+- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

package/bundled-skills/hugging-face-paper-publisher/SKILL.md

@@ -8,7 +8,6 @@ risk: unknown
 # Overview
 
 ## When to Use
-
 Use this skill when a user wants to publish, link, index, or manage research papers on the Hugging Face Hub.
 This skill provides comprehensive tools for AI engineers and researchers to publish, manage, and link research papers on the Hugging Face Hub. It streamlines the workflow from paper creation to publication, including integration with arXiv, model/dataset linking, and authorship management.
 
@@ -628,3 +627,8 @@ Planned features for future versions:
 - Integration with LaTeX workflows
 - Automated figure and table extraction
 - Paper metrics and impact tracking
+
+## Limitations
+- Use this skill only when the task clearly matches the scope described above.
+- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
+- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

package/bundled-skills/hugging-face-papers/SKILL.md

@@ -18,7 +18,6 @@ Whenever someone mentions a HF paper or arXiv abstract/PDF URL in a model card,
 The Hugging Face team has built an easy-to-use API to interact with paper pages. Content of the papers can be fetched as markdown, or structured metadata can be returned such as author names, linked models/datasets/spaces, linked Github repo and project page.
 
 ## When to Use
-
 - User shares a Hugging Face paper page URL (e.g. `https://huggingface.co/papers/2602.08025`)
 - User shares a Hugging Face markdown paper page URL (e.g. `https://huggingface.co/papers/2602.08025.md`)
 - User shares an arXiv URL (e.g. `https://arxiv.org/abs/2602.08025` or  `https://arxiv.org/pdf/2602.08025`)
@@ -239,3 +238,8 @@ If the Hugging Face paper page does not contain enough detail for the user's que
 - Write endpoints such as claim authorship, index paper, and update paper links require `Authorization: Bearer $HF_TOKEN`.
 - Prefer the `.md` endpoint for reliable machine-readable output.
 - Prefer `/api/papers/{PAPER_ID}` when you need structured JSON fields instead of page markdown.
+
+## Limitations
+- Use this skill only when the task clearly matches the scope described above.
+- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
+- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

package/bundled-skills/hugging-face-tool-builder/SKILL.md

@@ -10,7 +10,6 @@ source: community
 Your purpose is now is to create reusable command line scripts and utilities for using the Hugging Face API, allowing chaining, piping and intermediate processing where helpful. You can access the API directly, as well as use the `hf` command line tool. Model and Dataset cards can be accessed from repositories directly.
 
 ## When to Use
-
 - You need reusable CLI scripts around the Hugging Face API or `hf` command line tool.
 - You want shell-friendly utilities that support chaining, piping, and intermediate processing.
 - You are automating repeated Hub tasks and need a composable interface instead of ad hoc API calls.
@@ -116,3 +115,8 @@ Commands:
 ```
 
 The `hf` CLI command has replaced the now deprecated `huggingface_hub` CLI command.
+
+## Limitations
+- Use this skill only when the task clearly matches the scope described above.
+- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
+- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

package/bundled-skills/hugging-face-trackio/SKILL.md

@@ -115,3 +115,8 @@ Then poll from a separate terminal/process:
 ```bash
 trackio list alerts --project my-project --json --since "2025-01-01T00:00:00"
 ```
+
+## Limitations
+- Use this skill only when the task clearly matches the scope described above.
+- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
+- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

package/bundled-skills/hugging-face-vision-trainer/SKILL.md

@@ -593,3 +593,8 @@ For comprehensive troubleshooting: see [references/reliability_principles.md](re
 - [SAM Model Documentation](https://huggingface.co/docs/transformers/model_doc/sam)
 - [Object Detection Datasets](https://huggingface.co/datasets?task_categories=task_categories:object-detection)
 - [Image Classification Datasets](https://huggingface.co/datasets?task_categories=task_categories:image-classification)
+
+## Limitations
+- Use this skill only when the task clearly matches the scope described above.
+- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
+- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

package/bundled-skills/humanize-chinese/SKILL.md

@@ -19,7 +19,6 @@ date_added: "2026-04-03"
 Use this skill when you need to detect AI-like Chinese writing, rewrite it to feel less synthetic, reduce AIGC signals in academic prose, or convert the text into a more specific Chinese writing style.
 
 ## When to Use
-
 - Use when the user says `去AI味`, `降AIGC`, `去除AI痕迹`, `让文字更自然`, `改成人话`, or `降低AI率`
 - Use when the user wants a Chinese text checked for AI-writing patterns or suspicious phrasing
 - Use when the user wants academic-paper-specific AIGC reduction for CNKI, VIP, or Wanfang-style checks
@@ -144,3 +143,8 @@ When switching style, keep the user's meaning stable and change only tone, struc
 ## Source
 
 Adapted from the `voidborne-d/humanize-chinese` project and its CLI/script workflow for Chinese AI-text detection and rewriting.
+
+## Limitations
+- Use this skill only when the task clearly matches the scope described above.
+- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
+- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

package/bundled-skills/hybrid-cloud-architect/SKILL.md

@@ -162,3 +162,8 @@ Expert hybrid cloud architect with deep expertise in designing, implementing, an
 - "Plan migration strategy from legacy on-premises to hybrid multi-cloud architecture"
 - "Implement unified monitoring and observability across hybrid infrastructure"
 - "Create FinOps strategy for multi-cloud cost optimization and governance"
+
+## Limitations
+- Use this skill only when the task clearly matches the scope described above.
+- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
+- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

package/bundled-skills/hybrid-cloud-networking/SKILL.md

@@ -239,3 +239,8 @@ az network vpn-connection show-device-config-script
 
 - `multi-cloud-architecture` - For architecture decisions
 - `terraform-module-library` - For IaC implementation
+
+## Limitations
+- Use this skill only when the task clearly matches the scope described above.
+- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
+- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

package/bundled-skills/hybrid-search-implementation/SKILL.md

@@ -33,3 +33,8 @@ Patterns for combining vector similarity and keyword-based search.
 ## Resources
 
 - `resources/implementation-playbook.md` for detailed patterns and examples.
+
+## Limitations
+- Use this skill only when the task clearly matches the scope described above.
+- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
+- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

package/bundled-skills/i18n-localization/SKILL.md

@@ -157,3 +157,8 @@ Before shipping:
 
 ## When to Use
 This skill is applicable to execute the workflow or actions described in the overview.
+
+## Limitations
+- Use this skill only when the task clearly matches the scope described above.
+- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
+- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

package/bundled-skills/iconsax-library/SKILL.md

@@ -36,3 +36,8 @@ Trigger this skill when:
 - **ABSOLUTE MANDATE**: Agents MUST utilize this skill to build modern, creative, and visually stunning UI/UX. DO NOT use common, generic, or default browser/framework icons. Every icon must feel intentional and premium.
 - **Strict Consistency**: Stick to ONE style (e.g., only "Two-tone") throughout a single project to maintain high-end polish.
 - **Sizing & Alignment**: Follow strict, standard grid sizes (24x24) to ensure absolute crispness on high-DPI displays.
+
+## Limitations
+- Use this skill only when the task clearly matches the scope described above.
+- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
+- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

package/bundled-skills/idea-darwin/SKILL.md

@@ -118,3 +118,8 @@ Append new ideas to `ideas.md`, add environmental variables to `stimuli.md`.
 - [GitHub Repository](https://github.com/warmskull/idea-darwin)
 - Available in 3 languages: English, Chinese, Japanese
 - ClawHub: `clawhub install idea-darwin`
+
+## Limitations
+- Use this skill only when the task clearly matches the scope described above.
+- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
+- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

package/bundled-skills/identity-mirror/SKILL.md

@@ -8,7 +8,6 @@ date_added: "2026-04-04"
 You are a **Identity Psychologist and Self-Concept Researcher**. Your task is to identify the aspirational identity the target customer wants to inhabit, then rewrite outputs so the brand or offer reflects that identity back.
 
 ## When to Use
-
 - Use when messaging needs to reflect the audience's self-image, aspirations, or in-group identity.
 - Use when you want copy to feel personally resonant rather than broadly persuasive.
 
@@ -113,3 +112,8 @@ Before finalizing output, the agent asks:
 - [ ] Did I mirror language and imagery accurately?
 - [ ] Did I avoid shallow identity theater?
 - [ ] Would the customer feel seen, not sold to?
+
+## Limitations
+- Use this skill only when the task clearly matches the scope described above.
+- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
+- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

package/bundled-skills/ilya-sutskever/SKILL.md

@@ -1163,3 +1163,8 @@ humana — e que tomou isso a sério de forma que pouquíssimas pessoas fazem.
 - `elon-musk` - Complementary skill for enhanced analysis
 - `geoffrey-hinton` - Complementary skill for enhanced analysis
 - `sam-altman` - Complementary skill for enhanced analysis
+
+## Limitations
+- Use this skill only when the task clearly matches the scope described above.
+- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
+- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

package/bundled-skills/image-studio/SKILL.md

@@ -325,3 +325,8 @@ stability-ai:
 - `ai-studio-image` - Complementary skill for enhanced analysis
 - `comfyui-gateway` - Complementary skill for enhanced analysis
 - `stability-ai` - Complementary skill for enhanced analysis
+
+## Limitations
+- Use this skill only when the task clearly matches the scope described above.
+- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
+- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

package/bundled-skills/imagen/SKILL.md

@@ -76,3 +76,8 @@ User: "Create a diagram showing microservices architecture"
 User: "Generate a placeholder avatar image for the user profile component"
 -> Creates image in appropriate size for component use
 ```
+
+## Limitations
+- Use this skill only when the task clearly matches the scope described above.
+- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
+- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

package/bundled-skills/incident-responder/SKILL.md

@@ -207,3 +207,8 @@ Expert incident responder with deep knowledge of SRE principles, modern observab
 - **Learn and improve**: Every incident is an opportunity to build better systems
 
 Remember: Excellence in incident response comes from preparation, practice, and continuous improvement of both technical systems and human processes.
+
+## Limitations
+- Use this skill only when the task clearly matches the scope described above.
+- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
+- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

package/bundled-skills/incident-response-incident-response/SKILL.md

@@ -169,3 +169,8 @@ Orchestrate multi-agent incident response with modern SRE practices for rapid re
 - Timestamp all significant events
 
 Production incident requiring immediate response: $ARGUMENTS
+
+## Limitations
+- Use this skill only when the task clearly matches the scope described above.
+- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
+- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

package/bundled-skills/incident-response-smart-fix/SKILL.md

@@ -30,3 +30,8 @@ date_added: "2026-02-27"
 ## Resources
 
 - `resources/implementation-playbook.md` for detailed patterns and examples.
+
+## Limitations
+- Use this skill only when the task clearly matches the scope described above.
+- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
+- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

package/bundled-skills/incident-runbook-templates/SKILL.md

@@ -396,3 +396,8 @@ psql -c "VACUUM FULL large_table;"
 - [Google SRE Book - Incident Management](https://sre.google/sre-book/managing-incidents/)
 - [PagerDuty Incident Response](https://response.pagerduty.com/)
 - [Atlassian Incident Management](https://www.atlassian.com/incident-management)
+
+## Limitations
+- Use this skill only when the task clearly matches the scope described above.
+- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
+- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.