currentai-org/os-ai-map/update-product
Claude Code and agent skill by currentai-org/os-ai-map
- community
Checking that the SKILL.md file is still in the repository.
Use when an editor wants to change an existing product in the AI Stack Map — its identity/artifacts, its description/comments prose, a score's evidence or value, its category/org membership, or to retire it. Routes the change to the right procedure. For a brand-new product use add-product.
Install
npx vskill@latest install currentai-org/os-ai-map/update-productSKILL.md
Update a product
The single door for changing an existing product. Thin wrapper over a router — describe what changed and the workflow doc sends you to the right procedure. This file does not restate the routes.
Trigger
Anything about an existing product needs to change. If it does not exist yet, use add-product.
Required reading
Read `docs/workflows/update-product.md` and follow its classifier. It routes by what changed: identity/artifacts (including a version bump like "add v1.5" — the slug never changes), prose only, a score's evidence or value, roster membership, or retirement (a slug retires as an alias, never a deletion).
Agent orchestration
- Prose-only change: rewrite
description/commentstodocs/reference/product-copy.md
against primary sources. comments is a footnote about the reading or nothing; it carries no Verified … via line. This never touches scores and never writes last_verified. A whole category's notes written in rubric vocabulary is clean-corpus-prose, not this.
- A score moved: this is evidence work and earns a date — re-read the cited sources, record
the evidence, and stamp last_verified per docs/reference/evidence-and-freshness.md. Do not just edit the number. If the whole category is stale, use refresh-category instead.
- Edit
sources/files surgically viabuild/components.py; never load-modify-dump.
Scripts to run
build.preflight runs what .github/workflows/validate.yml runs and accounts for every step it cannot run locally, so it does not drift the way a copied gate list does. Do not hand-assemble a subset — that is what shipped a check_components failure to CI once already.
The individual gates, for re-running one after a failure:
Stop and escalate
- The change is really axis-wide schema/vocabulary →
migrate-axis. - The category can't ladder the new evidence →
build-rubric. - Never commit
build/notebook_data.jsonornotebooks/.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/update-product/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/currentai-org/os-ai-map/update-product)