Kubernetes Architect
Cybereason-Public/owLSM
Expert Kubernetes architect specializing in cloud-native infrastructure, advanced GitOps workflows (ArgoCD/Flux), and enterprise container orchestration.
Official agent skill
Doc Drift Detection
by aws-samples in aws-samples/sample-multi-agent-orchestration-chat-on-agentcore
Detect semantic drift between documentation and source code.
Install Doc Drift Detection
$ npx skills add aws-samples/sample-multi-agent-orchestration-chat-on-agentcore --skill doc-drift-detection -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install aws-samples/sample-multi-agent-orchestration-chat-on-agentcore doc-drift-detection --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/aws-samples/sample-multi-agent-orchestration-chat-on-agentcore.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/doc-drift-detection .claude/skills/doc-drift-detection && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "doc-drift-detection" agent skill from https://github.com/aws-samples/sample-multi-agent-orchestration-chat-on-agentcore/tree/main/.agents/skills/doc-drift-detection into .claude/skills/doc-drift-detection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "doc-drift-detection", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/aws-samples/sample-multi-agent-orchestration-chat-on-agentcore/tree/main/.agents/skills/doc-drift-detectionType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add aws-samples/sample-multi-agent-orchestration-chat-on-agentcore --skill doc-drift-detection -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install aws-samples/sample-multi-agent-orchestration-chat-on-agentcore doc-drift-detection --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/aws-samples/sample-multi-agent-orchestration-chat-on-agentcore.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/doc-drift-detection .agents/skills/doc-drift-detection && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "doc-drift-detection" agent skill from https://github.com/aws-samples/sample-multi-agent-orchestration-chat-on-agentcore/tree/main/.agents/skills/doc-drift-detection into .agents/skills/doc-drift-detection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "doc-drift-detection", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add aws-samples/sample-multi-agent-orchestration-chat-on-agentcore --skill doc-drift-detection -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install aws-samples/sample-multi-agent-orchestration-chat-on-agentcore doc-drift-detection --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/aws-samples/sample-multi-agent-orchestration-chat-on-agentcore.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/doc-drift-detection .cursor/skills/doc-drift-detection && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "doc-drift-detection" agent skill from https://github.com/aws-samples/sample-multi-agent-orchestration-chat-on-agentcore/tree/main/.agents/skills/doc-drift-detection into .cursor/skills/doc-drift-detection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "doc-drift-detection", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/aws-samples/sample-multi-agent-orchestration-chat-on-agentcore.git --path .agents/skills/doc-drift-detection--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add aws-samples/sample-multi-agent-orchestration-chat-on-agentcore --skill doc-drift-detection -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install aws-samples/sample-multi-agent-orchestration-chat-on-agentcore doc-drift-detection --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/aws-samples/sample-multi-agent-orchestration-chat-on-agentcore.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/doc-drift-detection .gemini/skills/doc-drift-detection && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "doc-drift-detection" agent skill from https://github.com/aws-samples/sample-multi-agent-orchestration-chat-on-agentcore/tree/main/.agents/skills/doc-drift-detection into .gemini/skills/doc-drift-detection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "doc-drift-detection", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install aws-samples/sample-multi-agent-orchestration-chat-on-agentcore doc-drift-detectionInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add aws-samples/sample-multi-agent-orchestration-chat-on-agentcore --skill doc-drift-detection -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/aws-samples/sample-multi-agent-orchestration-chat-on-agentcore.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/doc-drift-detection .github/skills/doc-drift-detection && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "doc-drift-detection" agent skill from https://github.com/aws-samples/sample-multi-agent-orchestration-chat-on-agentcore/tree/main/.agents/skills/doc-drift-detection into .github/skills/doc-drift-detection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "doc-drift-detection", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add aws-samples/sample-multi-agent-orchestration-chat-on-agentcore --skill doc-drift-detection -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install aws-samples/sample-multi-agent-orchestration-chat-on-agentcore doc-drift-detection --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/aws-samples/sample-multi-agent-orchestration-chat-on-agentcore.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/doc-drift-detection .opencode/skills/doc-drift-detection && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "doc-drift-detection" agent skill from https://github.com/aws-samples/sample-multi-agent-orchestration-chat-on-agentcore/tree/main/.agents/skills/doc-drift-detection into .opencode/skills/doc-drift-detection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "doc-drift-detection", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
doc-drift-detection- GitHub stars
- 130
- Token cost
- ~714 tokens
- SKILL.md length
- 255 words
- Files
- 2
- Skills in repo
- 5
- Repo updated
- First seen
- Licence
- MIT-0
At a glance
Detect semantic drift between documentation and source code.
- Tasks that involve GitOps
- SKILL.md covers Purpose, Scope, Severity Classification and Output Format, plus 1 more section
- Calls gh
What it does
Doc Drift Detection is an agent skill from aws-samples/sample-multi-agent-orchestration-chat-on-agentcore, published by the product's own GitHub organization. Detect semantic drift between documentation and source code. Goes beyond grep-based checks to find meaning-level discrepancies that mechanical tools miss.
Its SKILL.md is about 710 tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `changelog.md`).
It sits in DevOps & Cloud, covering GitOps. The repository describes itself as: Build & Share AI agents with your team. Full AgentCore, Full Serverless, Full TypeScript Sample. The licence is MIT-0.
When your agent uses it
- Tasks that involve GitOps
Example prompts
- “/doc-drift-detection”
What it can do on your machine
Read from SKILL.md and the folder at commit 297d9c9. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
gh
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use gh, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Doc Drift Detection loads about 714 tokens when it runs. Until then it costs about 44 tokens; SKILL.md has 255 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from aws-samples/sample-multi-agent-orchestration-chat-on-agentcore at commit 297d9c9, republished under its MIT-0 licence (© aws-samples). 255 words, ~714 tokens.
Download SKILL.mdSave it as
.claude/skills/doc-drift-detection/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- doc-drift-detection
- description
- Detect semantic drift between documentation and source code. Goes beyond grep-based checks to find meaning-level discrepancies that mechanical tools miss.
Doc-Drift Detection Skill
Purpose
Detect semantic drift between documentation and code — the kind that grep cannot catch:
- API endpoints added in code but missing from README
- Architecture diagrams that no longer match actual dependency graph
- Environment variable docs out of sync with config schemas
- Code examples in docs that use outdated APIs
Scope
Layer Model
| Layer | Method | Example | Owner |
|---|---|---|---|
| Layer 0 | Mechanical grep | "env var name exists in README" | scripts/bin/check-doc-drift.sh |
| Layer 1 | Structural read | "route list in code vs endpoint list in doc" | This skill |
| Layer 2 | Semantic understanding | "doc says X but code actually does Y" | This skill |
Active Document-Code Pairs
| Group | Document | Code Source |
|---|---|---|
| A | AGENTS.md | All package structures, dependency graph |
| B | packages/backend/README.md | backend/src/routes/*.ts, config |
| C | packages/agent/README.md | agent/src/ (tools, config, endpoints) |
Skip List
Documents excluded from analysis. Add entries here when a PR is closed without merging (i.e., the finding was a false positive or intentional).
packages/frontend/README.md— Vite boilerplate, not project documentationpackages/cdk/README.md— Minimal stub; deployment docs live indocs/guides/deployment-options.md
Severity Classification
| Severity | Criteria | Action |
|---|---|---|
| 🔴 HIGH | Clear factual error — wrong endpoint, wrong version, nonexistent file referenced | PR to fix |
| 🟡 MEDIUM | Missing information — new route undocumented, new env var missing | Chat report |
| 🟢 LOW | Stale wording, minor description inaccuracy | Chat report |
Output Format
Return findings as JSON:
{
"group": "B",
"document": "packages/backend/README.md",
"findings": [
{
"section": "API Endpoints",
"codeSource": "packages/backend/src/routes/memory.ts",
"type": "missing_info",
"severity": "MEDIUM",
"description": "DELETE /memory/records/:recordId is implemented but not documented",
"evidence": "router.delete('/records/:recordId', ...) at line 60",
"suggestedFix": "Add DELETE /api/memory/records/:recordId to the API Endpoints section"
}
]
}State Management
This skill does not maintain JSON state files. All state is derived from:
- Run history:
changelog.mdin this directory (max 30 entries) - PR status:
gh pr list --label doc-drift --state all(GitHub is source of truth) - Skip list: The Skip List section above in this file
© aws-samples, MIT-0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in .agents/skills/doc-drift-detection of aws-samples/sample-multi-agent-orchestration-chat-on-agentcore.
- SKILL.md
- changelog.md
Open the folder on GitHubat commit 297d9c9
Compare with similar skills
Doc Drift Detection next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Doc Drift Detection this skillaws-samples/sample-multi-agent-orchestration-chat-on-agentcore | 130 | — | ~714 | Automated safety check: Pass | MIT-0 | |
| Kubernetes ArchitectCybereason-Public/owLSM | 280 | 8 repos | ~2.6k | Automated safety check: Pass | GPL-2.0 | |
| Docs Corpus Auditmicrosoft/apm | 4k | — | ~2.6k | Automated safety check: Pass | MIT | |
| Kubernetes SpecialistJeffallan/claude-skills | 12k | 1 repos | ~2.1k | Automated safety check: Pass | MIT | |
| Devopsnicepkg/auto-company | 192 | 2 repos | ~814 | Automated safety check: Pass | MIT | |
| Gitops Repo Auditfluxcd/agent-skills | 230 | — | ~3.8k | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
Docs Corpus Audit
microsoft/apm
A skill your agent uses to run a holistic regrounding pass on the entire microsoft/apm documentation corpus against current source code, page-by-page, and emit surgical fixes for stale claims.
Kubernetes Specialist
Jeffallan/claude-skills
Creates and checks Kubernetes manifests, Helm charts, RBAC and network policies, and helps debug pod problems, with kubectl checks and rollback steps.
Devops
nicepkg/auto-company
Deploy to Cloudflare (Workers, R2, D1), Docker, GCP (Cloud Run, GKE), Kubernetes (kubectl, Helm).
Gitops Repo Audit
fluxcd/agent-skills
Audit and validate Flux CD GitOps repositories by scanning local repo files (not live clusters) — runs Kubernetes schema validation, detects deprecated Flux APIs, reviews RBAC/multi-tenancy/secrets…
Cluster Health
Diaoul/home-ops
Full cluster health check for the home-ops Kubernetes cluster.
More from aws-samples/sample-multi-agent-orchestration-chat-on-agentcore
- Official
Deep Modules
aws-samples/sample-multi-agent-orchestration-chat-on-agentcore
Apply Ousterhout's "deep modules" principle (narrow interface, deep implementation) when designing or refactoring classes and modules.
- Official
Moca Guide
aws-samples/sample-multi-agent-orchestration-chat-on-agentcore
How to use Moca itself — what this platform can do and how to ask for it.
- Official
UI Design
aws-samples/sample-multi-agent-orchestration-chat-on-agentcore
UI/UX design rules, Atomic Design placement, design tokens, component conventions, and responsive patterns for the Moca frontend.
- Official
Coding Style
aws-samples/sample-multi-agent-orchestration-chat-on-agentcore
Design decisions, implicit rules, and anti-patterns for the Moca project.
Related
Categories
Questions about Doc Drift Detection
What does Doc Drift Detection do?
Detect semantic drift between documentation and source code. Doc Drift Detection is an agent skill from aws-samples/sample-multi-agent-orchestration-chat-on-agentcore, published by the product's own GitHub organization. Detect semantic drift between documentation and source code.
When should I use Doc Drift Detection?
Doc Drift Detection fits situations like: tasks that involve GitOps.
How do I install Doc Drift Detection in Claude Code?
Run `npx skills add aws-samples/sample-multi-agent-orchestration-chat-on-agentcore --skill doc-drift-detection -a claude-code`. Or copy the skill folder (.agents/skills/doc-drift-detection in aws-samples/sample-multi-agent-orchestration-chat-on-agentcore) into .claude/skills/doc-drift-detection in your project. Claude Code loads it when a task matches its description.
How do I install Doc Drift Detection in Codex?
Run `npx skills add aws-samples/sample-multi-agent-orchestration-chat-on-agentcore --skill doc-drift-detection -a codex`. Or copy the skill folder (.agents/skills/doc-drift-detection in aws-samples/sample-multi-agent-orchestration-chat-on-agentcore) into .agents/skills/doc-drift-detection in your project. Codex loads it when a task matches its description.
Can I use Doc Drift Detection in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add aws-samples/sample-multi-agent-orchestration-chat-on-agentcore --skill doc-drift-detection -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/doc-drift-detection, .gemini/skills/doc-drift-detection, .github/skills/doc-drift-detection and .opencode/skills/doc-drift-detection in your project.
What does Doc Drift Detection need to run?
Going by SKILL.md and its folder, Doc Drift Detection needs the command-line tools its instructions call (gh).
Does Doc Drift Detection access the network?
SKILL.md contains no URLs. Its commands use gh, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Doc Drift Detection safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Doc Drift Detection use?
Doc Drift Detection is published under the MIT-0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Doc Drift Detection use?
About 714 tokens (SKILL.md is roughly 2.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Doc Drift Detection?
Skills that share tags, products or a category with Doc Drift Detection: Kubernetes Architect (Cybereason-Public/owLSM, 280 stars), Docs Corpus Audit (microsoft/apm, 4k stars), Kubernetes Specialist (Jeffallan/claude-skills, 12k stars) and Devops (nicepkg/auto-company, 192 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Doc Drift Detection?
aws-samples (a GitHub organization, an official publisher) maintains it in aws-samples/sample-multi-agent-orchestration-chat-on-agentcore, which has 130 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 6, 2026.
Source: aws-samples/sample-multi-agent-orchestration-chat-on-agentcore on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.