documentation-guidelines
Create, reorganize, or update documentation for monorepos or single-project repos using root docs indexes, unique repo/module/feature identifiers, repo-owned detailed docs, cross-repo relationship maps, machine-readable frontmatter, API contracts, workflows, runbooks, testing, and debugging guidance.
What this skill does
# Documentation Guidelines
## Overview
Produce documentation that is easy to locate, owned by the correct repo/module/feature, and safe to use as a source of truth. Use this skill for monorepos and single-project repos when creating, reorganizing, or updating architecture docs, module docs, feature docs, API contracts, workflows, runbooks, testing notes, or debugging guidance.
Apply the workflow directly unless the repository has newer explicit agent instructions or a newer docs index that conflicts.
For detailed templates, read `references/documentation-guidelines.md`.
## Non-Negotiable Reading Rule
Before summarizing, moving, deleting, or editing documentation:
1. Read the complete target file, not just search hits.
2. If root `docs/README.md` exists, read it first. It is the project routing index.
3. Read the owning repo `README.md`, local agent guide, and repo `docs/README.md` when they exist.
4. Read repo-level `modules.md` and `features.md` when resolving a module or feature.
5. Read all relationship docs marked `Required`.
6. Do not infer business logic from filenames, folder names, translated labels, role display names, or stale references.
7. If two docs appear duplicated, read both completely and identify the source-of-truth owner before deleting or merging.
## Project Shape
### Monorepo
A repo is a monorepo when it has multiple independent apps/services/packages or deployable runtimes, such as `apps/*`, `services/*`, or `packages/*`.
Use this documentation shape:
```text
docs/
README.md
naming-and-structure.md
relationship-map.md
runbooks/
decisions/
apps/<repo>/
README.md
docs/
README.md
modules.md
features.md
architecture/
modules/
reference/
runbooks/
memories/
archives/
```
Root `docs/` is a routing and coordination area. Detailed monorepo docs always live inside the owning repository, such as `apps/api/docs/...`, not under root `docs/<repo-id>/...`.
Root `docs/README.md` must link to each repo docs index, repo-level `modules.md`, and repo-level `features.md`. It must not copy every feature into a full global feature list.
### Single Project
A single-project repo may keep all docs under root `docs/`, but still uses the same index model:
```text
docs/
README.md
naming-and-structure.md
modules.md
features.md
architecture/
modules/
reference/
runbooks/
memories/
archives/
```
Use one repo prompt name for routing, such as `Main Repo`, `API Repo`, or a domain-specific project name.
## Routing Index Requirements
Root `docs/README.md` is the first file an AI agent should use to resolve natural-language prompts. It must include:
- Project shape: `monorepo` or `single-project`.
- Repo prompt names and repo IDs.
- Links to each repo docs index, `modules.md`, and `features.md`.
- A root Module Locator for quick module resolution.
- Cross-repo Relationship Map.
- Independent/tooling areas.
- AI reading workflow and update rules.
Repo-level `modules.md` lists modules owned by that repo. Repo-level `features.md` lists features owned by that repo.
## Global Uniqueness Rules
These identifiers must be unique across the whole project:
| Identifier | Example | Purpose |
| :--- | :--- | :--- |
| Repo prompt name | `API Repo` | Natural-language routing |
| Repo ID | `api` | Stable machine-readable repo key |
| Canonical module name | `Order Module` | Natural-language module routing |
| Module ID | `order` | Stable machine-readable module key |
| Canonical feature name | `Approve Order API` | Natural-language feature routing |
| Feature ID | `approve-order-api` | Stable machine-readable feature key |
When the same business concept appears in multiple repos, include owner or surface in the canonical name, such as `Approve Order API` and `Approve Order Office UI`.
Aliases are allowed only when each alias maps to exactly one canonical repo, module, or feature. Remove or narrow ambiguous aliases.
## Relationship Levels
Use only these values in relationship maps:
| Level | Meaning | AI Behavior |
| :--- | :--- | :--- |
| `Required` | Change may break another repo, contract, workflow, or test surface | Read before proposing or editing |
| `Recommended` | Related context may affect UX, rollout, tests, or integration quality | Read for design, contract, workflow, or user-facing work |
| `Optional` | Useful background only; not blocking | Mention as context and read only if the task needs it |
| `None` | No expected coordination | Do not broaden scope unless the prompt explicitly asks |
Independent/tooling repos must be marked `None` when they have no product runtime or contract dependency.
## Ownership Rules
Place documentation by enforcement owner:
| Information Type | Source of Truth |
| :--- | :--- |
| API payloads, responses, errors, permissions, validation, database rules | Owning backend/API module feature docs |
| UI routes, client state, rendering behavior, form flow | Owning client module feature docs |
| Background jobs, queues, schedules, retries | Owning worker/service module docs |
| Shared package public APIs | Owning package docs |
| Cross-repo dependency | Root relationship map plus owner docs |
| Local scripts and developer tooling | Tooling repo docs |
Consumer docs may summarize how they consume a contract, but must link to the owner doc instead of copying the full business rule.
## Workflow
When creating or updating docs:
1. Read root `docs/README.md` when present.
2. Resolve the repo prompt name, module name, and feature name from the user prompt.
3. If only a feature is named, use repo-level feature indexes linked from root `docs/README.md` to find its owner.
4. Read the owning repo docs index, repo `modules.md`, repo `features.md`, owning module `README.md`, and existing feature docs.
5. Read relationship docs marked `Required`; read `Recommended` docs for design, contract, workflow, and user-facing changes.
6. Decide whether the work is an index update, module doc, feature doc, API contract, workflow, runbook, memory/convention, archive/move, or cross-repo relationship update.
7. Create or update docs in the owning docs folder. Remove obsolete content instead of appending contradictory sections.
8. Update root and repo indexes when adding, renaming, moving, or archiving repos/modules/features.
9. Search for stale paths, old names, old IDs, and removed terms.
10. Verify links resolve relative to the file location.
If routing remains ambiguous after reading indexes, ask one targeted question instead of guessing.
## Frontmatter
Every new or materially rewritten Markdown doc must start with YAML frontmatter:
```yaml
---
name: Human Readable Title
description: One sentence describing scope and owner.
version: 1.0.0
last_updated: YYYY-MM-DD
maintained_by: Team Or Owner
---
```
Module docs must also include routing fields:
```yaml
repo_prompt_name: API Repo
repo_id: api
module_name: Order Module
module_id: order
module_aliases:
- Orders
related_docs:
- ../../features.md
```
Feature docs must also include feature routing fields:
```yaml
repo_prompt_name: API Repo
repo_id: api
module_name: Order Module
module_id: order
feature_name: Approve Order API
feature_id: approve-order-api
feature_aliases:
- Order Approval API
related_docs:
- ../README.md
- ../../../features.md
```
Preserve existing version/history when migrating docs. Update `last_updated` and version when content changes materially.
## Required Content
For backend/API contract docs, include when applicable:
- Purpose, scope, consumers, and ownership boundary.
- Controllers/routes, requests, resources, models, services, jobs, providers, constants, and config.
- Endpoint table, headers, payload examples, response examples, and error dictionary.
- Permissions, token abilities, feature flags, rate limits, audit rules, and client consumption rules.
- Data model, state transitions, events, queues, cache behavior, side effects, and external dependencies.
- Local deveRelated in Backend & APIs
jfrog
IncludedInteract with the JFrog Platform via the JFrog CLI and REST/GraphQL APIs. Use this skill when the user wants to manage Artifactory repositories, upload or download artifacts, manage builds, configure permissions, manage users and groups, work with access tokens, configure JFrog CLI servers, search artifacts, manage properties, set up replication, manage JFrog Projects, run security audits or scans, look up CVE details, query exposures scan results from JFrog Advanced Security, manage release bundles and lifecycle operations, aggregate or export platform data, or perform any JFrog Platform administration task. Also use when the user mentions jf, jfrog, artifactory, xray, distribution, evidence, apptrust, onemodel, graphql, workers, mission control, curation, advanced security, exposures, or any JFrog product name.
cupynumeric-migration-readiness
IncludedPre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-friendly patterns from blockers such as unsupported APIs, scalar synchronization, host round-trips, Python/object-heavy control flow, shape/data-dependent branching, and in-place mutation hazards. Produce a verdict of READY, LIGHT REFACTOR, SIGNIFICANT REFACTOR, or NOT RECOMMENDED, with concrete refactor pointers.
alibabacloud-data-agent-skill
IncludedInvoke Alibaba Cloud Apsara Data Agent for Analytics via CLI to perform natural language-driven data analysis on enterprise databases. Data Agent for Analytics is an intelligent data analysis agent developed by Alibaba Cloud Database team for enterprise users. It automatically completes requirement analysis, data understanding, analysis insights, and report generation based on natural language descriptions. This tool supports: discovering data resources (instances/databases/tables) managed in DMS, initiating query or deep analysis sessions, real-time progress tracking, and retrieving analysis conclusions and generated reports. Use this Skill when users need to query databases, analyze data trends, generate data reports, ask questions in natural language, or mention "Data Agent", "data analysis", "database query", "SQL analysis", "data insights".
token-optimizer
IncludedReduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking, and native 2026.2.15 features (session pruning, bootstrap size limits, cache TTL alignment). Use when token costs are high, API rate limits are being hit, or hosting multiple agents at scale. The 4 executable scripts (context_optimizer, model_router, heartbeat_optimizer, token_tracker) are local-only — no network requests, no subprocess calls, no system modifications. Reference files (PROVIDERS.md, config-patches.json) document optional multi-provider strategies that require external API keys and network access if you choose to use them. See SECURITY.md for full breakdown.
resend-cli
IncludedUse this skill when the task is specifically about operating Resend from an AI agent, terminal session, or CI job via the official resend CLI: installing/authenticating the CLI, sending/listing/updating/cancelling emails, batch sends, domains and DNS, webhooks and local listeners, inbound receiving, contacts, topics, segments, broadcasts, templates, API keys, profiles, or debugging Resend CLI/API failures. Trigger on mentions of Resend CLI, `resend`, `resend doctor`, `resend emails send`, `resend domains`, `resend webhooks listen`, `resend emails receiving`, or agent-friendly terminal automation.
alibabacloud-odps-maxframe-coding
IncludedUse this skill for MaxFrame SDK development and documentation navigation on Alibaba Cloud MaxCompute (ODPS). Helps answer MaxFrame API, concept, official example, and supported pandas API questions; create data processing programs; read/write MaxCompute tables; debug jobs (remote or local); and build custom DPE runtime images. Trigger when users mention MaxFrame, MaxCompute with MaxFrame, ODPS table processing, DPE runtime, MaxFrame docs/examples, DataFrame/Tensor operations, or GPU runtime setup. Works for both English and Chinese queries about Alibaba Cloud data processing with MaxFrame.