Manage artifact metadata, versioning, ownership, and review history across the SDLC lifecycle
$ npx skills add jmagly/aiwg --skill artifact-metadata -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install jmagly/aiwg artifact-metadata --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/jmagly/aiwg.git skills-src && mkdir -p .claude/skills && cp -r skills-src/agentic/code/plugins/utils/skills/artifact-metadata .claude/skills/artifact-metadata && 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 "artifact-metadata" agent skill from https://github.com/jmagly/aiwg/tree/main/agentic/code/plugins/utils/skills/artifact-metadata into .claude/skills/artifact-metadata/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "artifact-metadata", 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/jmagly/aiwg/tree/main/agentic/code/plugins/utils/skills/artifact-metadataType 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 jmagly/aiwg --skill artifact-metadata -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install jmagly/aiwg artifact-metadata --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jmagly/aiwg.git skills-src && mkdir -p .agents/skills && cp -r skills-src/agentic/code/plugins/utils/skills/artifact-metadata .agents/skills/artifact-metadata && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "artifact-metadata" agent skill from https://github.com/jmagly/aiwg/tree/main/agentic/code/plugins/utils/skills/artifact-metadata into .agents/skills/artifact-metadata/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "artifact-metadata", 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 jmagly/aiwg --skill artifact-metadata -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install jmagly/aiwg artifact-metadata --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jmagly/aiwg.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/agentic/code/plugins/utils/skills/artifact-metadata .cursor/skills/artifact-metadata && 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 "artifact-metadata" agent skill from https://github.com/jmagly/aiwg/tree/main/agentic/code/plugins/utils/skills/artifact-metadata into .cursor/skills/artifact-metadata/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "artifact-metadata", 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/jmagly/aiwg.git --path agentic/code/plugins/utils/skills/artifact-metadata--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 jmagly/aiwg --skill artifact-metadata -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install jmagly/aiwg artifact-metadata --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jmagly/aiwg.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/agentic/code/plugins/utils/skills/artifact-metadata .gemini/skills/artifact-metadata && 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 "artifact-metadata" agent skill from https://github.com/jmagly/aiwg/tree/main/agentic/code/plugins/utils/skills/artifact-metadata into .gemini/skills/artifact-metadata/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "artifact-metadata", 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 jmagly/aiwg artifact-metadataInstalls 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 jmagly/aiwg --skill artifact-metadata -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/jmagly/aiwg.git skills-src && mkdir -p .github/skills && cp -r skills-src/agentic/code/plugins/utils/skills/artifact-metadata .github/skills/artifact-metadata && 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 "artifact-metadata" agent skill from https://github.com/jmagly/aiwg/tree/main/agentic/code/plugins/utils/skills/artifact-metadata into .github/skills/artifact-metadata/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "artifact-metadata", 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 jmagly/aiwg --skill artifact-metadata -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install jmagly/aiwg artifact-metadata --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jmagly/aiwg.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/agentic/code/plugins/utils/skills/artifact-metadata .opencode/skills/artifact-metadata && 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 "artifact-metadata" agent skill from https://github.com/jmagly/aiwg/tree/main/agentic/code/plugins/utils/skills/artifact-metadata into .opencode/skills/artifact-metadata/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "artifact-metadata", 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.
artifact-metadataManage artifact metadata, versioning, ownership, and review history across the SDLC lifecycle
Artifact Metadata is an agent skill from jmagly/aiwg. Manage artifact metadata, versioning, ownership, and review history across the SDLC lifecycle
Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts (for example `scripts/artifact_metadata.py`).
The repository describes itself as: Cognitive architecture for AI-augmented software development. Specialized agents, structured workflows, and multi-platform deployment. Claude Code · Codex · Copilot · Cursor ·… The licence is MIT.
4 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit dda238f. It shows what the files ask for, not the result of running them.
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.
Ships 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
pythonFrom the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
json-schema.orgFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Artifact Metadata loads about 1.9k tokens when it runs. Until then it costs about 28 tokens; SKILL.md has 316 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.
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); the scripts in this folder are not scanned.
The full file from jmagly/aiwg at commit dda238f, republished under its MIT licence (© jmagly). 316 words, ~1,856 tokens.
.claude/skills/artifact-metadata/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.Manage artifact metadata, versioning, ownership, and history tracking.
Alternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):
This skill provides consistent metadata management for all SDLC and marketing artifacts. It tracks ownership, versioning, review history, and status across the artifact lifecycle.
When triggered, this skill:
Locates or creates metadata:
metadata.json alongside artifactUpdates metadata fields:
Tracks history:
Validates relationships:
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"required": ["artifact_id", "name", "type", "version", "status", "owner"],
"properties": {
"artifact_id": {
"type": "string",
"description": "Unique identifier (e.g., SAD-001, UC-003)"
},
"name": {
"type": "string",
"description": "Human-readable artifact name"
},
"type": {
"type": "string",
"enum": ["requirements", "architecture", "test", "security", "deployment", "marketing", "report"]
},
"version": {
"type": "string",
"pattern": "^\\d+\\.\\d+\\.\\d+$",
"description": "Semantic version"
},
"status": {
"type": "string",
"enum": ["draft", "review", "approved", "baselined", "deprecated"]
},
"owner": {
"type": "string",
"description": "Primary owner (agent name or user)"
},
"created": {
"type": "string",
"format": "date-time"
},
"modified": {
"type": "string",
"format": "date-time"
},
"baselined": {
"type": "string",
"format": "date-time"
},
"reviewers": {
"type": "array",
"items": {"type": "string"}
},
"history": {
"type": "array",
"items": {
"type": "object",
"properties": {
"version": {"type": "string"},
"date": {"type": "string", "format": "date-time"},
"author": {"type": "string"},
"summary": {"type": "string"}
}
}
},
"reviews": {
"type": "array",
"items": {
"type": "object",
"properties": {
"reviewer": {"type": "string"},
"date": {"type": "string", "format": "date-time"},
"outcome": {"type": "string", "enum": ["approved", "conditional", "rejected"]},
"comments": {"type": "string"}
}
}
},
"traceability": {
"type": "object",
"properties": {
"requirements": {"type": "array", "items": {"type": "string"}},
"parent": {"type": "string"},
"children": {"type": "array", "items": {"type": "string"}}
}
},
"tags": {
"type": "array",
"items": {"type": "string"}
}
}
}User: "Create metadata for the SAD"
Skill creates:
.aiwg/architecture/sad/metadata.json
{
"artifact_id": "SAD-001",
"name": "Software Architecture Document",
"type": "architecture",
"version": "0.1.0",
"status": "draft",
"owner": "architecture-designer",
"created": "2025-12-08T14:30:00Z",
"modified": "2025-12-08T14:30:00Z",
"reviewers": [],
"history": [],
"reviews": []
}User: "Version the SAD to 1.0.0 with summary 'Initial baseline'"
Skill updates:
- version: "1.0.0"
- status: "baselined"
- baselined: "2025-12-08T16:45:00Z"
- history: [adds entry with version, date, summary]User: "Record security-architect review as approved"
Skill updates:
- reviews: [adds review record]
- reviewers: [adds "security-architect" if not present]
- modified: [updates timestamp]User: "Who owns the test plan?"
Skill responds:
"Test Plan (TP-001) is owned by test-architect.
Status: review
Version: 0.3.0
Last modified: 2025-12-07
Reviewers: security-auditor, requirements-analyst"draft → review → approved → baselined
↑ ↓
└── rejected (returns to draft)
baselined → deprecated (end of life)| From | To | Triggered By |
|---|---|---|
| draft | review | Submit for review |
| review | approved | All reviewers approve |
| review | draft | Any reviewer rejects |
| approved | baselined | Formal baseline action |
| baselined | deprecated | Superseded or retired |
| Change Type | Version Bump |
|---|---|
| Typo fix | patch (0.0.x) |
| Section update | minor (0.x.0) |
| Structure change | major (x.0.0) |
| Initial baseline | 1.0.0 |
| Type | ID Prefix | Location |
|---|---|---|
| requirements | UC-, REQ-, NFR- | .aiwg/requirements/ |
| architecture | SAD-, ADR-, API- | .aiwg/architecture/ |
| test | TP-, TC-, TS- | .aiwg/testing/ |
| security | TM-, SEC- | .aiwg/security/ |
| deployment | DP-, RN- | .aiwg/deployment/ |
| marketing | CB-, CA- | .aiwg/marketing/ |
| report | RPT- | .aiwg/reports/ |
# Create metadata for artifact
python artifact_metadata.py --create --artifact ".aiwg/architecture/sad.md" --type architecture
# Update version
python artifact_metadata.py --version "1.0.0" --artifact ".aiwg/architecture/sad.md" --summary "Initial baseline"
# Record review
python artifact_metadata.py --review --artifact ".aiwg/architecture/sad.md" \
--reviewer "security-architect" --outcome "approved" --comments "LGTM"
# Query metadata
python artifact_metadata.py --query --artifact ".aiwg/architecture/sad.md"
# List all artifacts by status
python artifact_metadata.py --list --status "review"
# Validate all metadata
python artifact_metadata.py --validate-allThis skill integrates with:
artifact-orchestration: Sets initial metadata when creating artifactsgate-evaluation: Checks artifact status for gate criteriatraceability-check: Uses traceability links in metadatatemplate-engine: Copies metadata template on instantiation{artifact-dir}/metadata.json{artifact-dir}/{artifact-name}.metadata.json.aiwg/reports/artifact-index.jsonschemas/artifact-metadata.schema.json© jmagly, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 1 other file (scripts) in agentic/code/plugins/utils/skills/artifact-metadata of jmagly/aiwg.
Open the folder on GitHubat commit dda238f
Artifact Metadata 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 |
|---|---|---|---|---|---|---|
| Artifact Metadata this skilljmagly/aiwg | 220 | — | ~1.9k | Automated safety check: Pass | MIT | |
| Extracting Browser History Artifactsmukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~2.9k | Automated safety check: Warn | Apache-2.0 | |
| Artifacts Buildernexu-io/open-design | 100k | — | ~347 | Automated safety check: Pass | Apache-2.0 | |
| Web Artifacts Builderanthropics/skills | 180k | 41 repos | ~769 | Automated safety check: Pass | Apache-2.0 | |
| Web Artifacts Buildernexu-io/open-design | 100k | — | ~337 | Automated safety check: Pass | Apache-2.0 | |
| Managing Endpoint VersionsPostHog/posthog | 40k | — | ~2.3k | Automated safety check: Pass | Custom licence |
mukul975/Anthropic-Cybersecurity-Skills
Extracts and analyzes browser history, cookies, cache, downloads, and bookmarks from Chrome, Firefox, and Edge using sqlite3, DB Browser for SQLite, Hindsight, and NirSoft tools…
nexu-io/open-design
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui).
anthropics/skills
Builds multi-component claude.ai HTML artifacts as a small React, TypeScript and Tailwind project, then bundles it into one shareable HTML file.
nexu-io/open-design
Build complex claude.ai HTML artifacts with React and Tailwind.
PostHog/posthog
Work safely with endpoint versions — preview a draft in the playground, roll back to an older version, update settings on one version without bumping query history, deactivate a specific version.
sickn33/agentic-awesome-skills
To build powerful frontend claude.ai artifacts, follow these steps:
jmagly/aiwg
Review editorial phrase patterns and suggest contextual alternatives; legacy name does not imply authorship detection.
jmagly/aiwg
Apply a voice profile to transform content. An agent skill from jmagly/aiwg.
jmagly/aiwg
Run mutation testing to validate test quality beyond code coverage.
jmagly/aiwg
Configure TDD enforcement via pre-commit hooks and CI coverage gates.
jmagly/aiwg
Detect project type, AIWG framework state, team configuration, and active work to summarize status and recommend next actions
jmagly/aiwg
Scan source code for banned APIs/forbidden functions per project banlist; report violations with paths, line numbers, and recommended replacements
Manage artifact metadata, versioning, ownership, and review history across the SDLC lifecycle. Artifact Metadata is an agent skill from jmagly/aiwg.
Run `npx skills add jmagly/aiwg --skill artifact-metadata -a claude-code`. Or copy the skill folder (agentic/code/plugins/utils/skills/artifact-metadata in jmagly/aiwg) into .claude/skills/artifact-metadata in your project. Claude Code loads it when a task matches its description.
Run `npx skills add jmagly/aiwg --skill artifact-metadata -a codex`. Or copy the skill folder (agentic/code/plugins/utils/skills/artifact-metadata in jmagly/aiwg) into .agents/skills/artifact-metadata in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jmagly/aiwg --skill artifact-metadata -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/artifact-metadata, .gemini/skills/artifact-metadata, .github/skills/artifact-metadata and .opencode/skills/artifact-metadata in your project.
Going by SKILL.md and its folder, Artifact Metadata needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.
SKILL.md names 1 domain. In commands or code: json-schema.org; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Artifact Metadata is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.9k tokens (SKILL.md is roughly 7.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Artifact Metadata: Extracting Browser History Artifacts (mukul975/Anthropic-Cybersecurity-Skills, 34k stars), Artifacts Builder (nexu-io/open-design, 100k stars), Web Artifacts Builder (anthropics/skills, 180k stars) and Web Artifacts Builder (nexu-io/open-design, 100k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
jmagly (a GitHub user) maintains it in jmagly/aiwg, which has 220 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on October 8, 2026.
Source: jmagly/aiwg on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.
