Menu
Fetch the latest Acumen skills from GitHub and update local copies (source, .agents, .claude symlinks).
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Scope a single product increment end-to-end — context, spec, implementation, wireframes, and engineering considerations. Use when a feature or bet needs a shippable document before building — typically the option chosen out of /workshop's divergence. Leads to /critique-product.
Print a quick-reference cheatsheet of all Acumen skills, organized by layer.
Pull latest code from main, summarize recent changes in product-friendly terms, and report .acumen/ context health (what exists, what's fresh, what's stale, what's missing). Preserves all .acumen/ context files.
Evaluate and validate a PM artifact — score for rigor, test riskiest assumptions, and decide if it's ready to ship. Use when reviewing a PRD, spec, increment, strategy, or roadmap.
Find what's broken and what's underexploited — problems AND opportunities — grounded in data, value delivery per persona, and current features. The entry point to ideation; hands sharp problems and opportunities to /workshop.
One-time setup that gathers product context for your project and saves it to .acumen.md. Run once to establish persistent product guidelines.
Basé sur la classification professionnelle SOC
| name | update-acumen |
| description | Fetch the latest Acumen skills from GitHub and update local copies (source, .agents, .claude symlinks). |
| user-invocable | true |
Pull the latest skills from the Acumen repo and sync them into this project.
Source repo: VGrss/Acumen on GitHub (branch: main)
Use gh to list the skill directories in the repo:
gh api repos/VGrss/Acumen/git/trees/main:source/skills --jq '.tree[] | select(.type == "tree") | .path'
This gives you the list of all skill names in the upstream repo.
Also list the local skills in source/skills/ to compare.
Report what's new, removed, or already present.
For every skill found upstream, fetch its files recursively. Each skill lives at source/skills/{name}/ and may contain SKILL.md plus optional subdirectories (e.g. reference/).
For each skill directory:
Get the file tree for that skill:
gh api repos/VGrss/Acumen/git/trees/main:source/skills/{name} --jq '.tree[]'
For each file, fetch its raw content and write it locally:
gh api repos/VGrss/Acumen/contents/source/skills/{name}/{file} --jq '.content' | base64 -d
Write the decoded content to source/skills/{name}/{file}.
For subdirectories (like reference/), recurse: list the subtree, then fetch each file inside it.
After syncing source/skills/, replicate the distribution structure:
Copy to .agents/skills/: For each skill, copy the entire source/skills/{name}/ directory to .agents/skills/{name}/.
cp -r source/skills/{name} .agents/skills/{name}
Create .claude/skills/ symlinks: For any new skill that doesn't already have a symlink:
ln -sf ../../.agents/skills/{name} .claude/skills/{name}
Clean up removed skills: If a skill exists locally but not upstream, report it to the user and ask whether to remove it.
Print a summary:
Include the total skill count and confirm the distribution is in sync.