Skip to content
Skills Library
AI & agents · Automation

update-skill-stack

/update-skill-stack

Review and apply upstream skill-stack updates without losing a personal profile or local skills. Use only when the user invokes $update-skill-stack or explicitly asks to update the adopted skill stack.

Licence
MIT
Last repository change
12.11.2026

Assessment and security

86/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content21 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
3
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 12.11.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Review and apply upstream skill-stack updates without losing a personal profile or local skills. Use only when the user invokes $update-skill-stack or explicitly asks to update the adopted skill stack.

Original author description

Review and apply upstream skill-stack updates without losing a personal profile or local skills. Use only when the user invokes $update-skill-stack or explicitly asks to update the adopted skill stack.

How it works

SKILL.md has no level-two headings · 17 lines, 278 words

SKILL.md preview
---
name: update-skill-stack
description: Review and apply upstream skill-stack updates without losing a personal profile or local skills. Use only when the user invokes $update-skill-stack or explicitly asks to update the adopted skill stack.
disable-model-invocation: true
metadata:
  opencode/autoinvoke: "false"
---

# Update the skill stack

1. Locate the adopted repository from the current checkout or `~/.config/astrobyte-agent-skills/install-manifest.json`. Read `config/repository.json`, the active operator profile, `docs/upstreams.md`, and the installation manifest. When the recorded checkout is gone, `python3 scripts/install.py --check` from any checkout prints the clone and checkout commands that restore it; ask where to clone before running them.
2. Check repository status. Stop for unresolved local changes that overlap the update.
3. Fetch `upstream` and identify the current base version and available release. Do not merge yet.
4. Create an isolated update branch or worktree.
5. Compare upstream changes with personal profiles, custom skills, catalog composition, adapters, installer behavior, licenses, and migrations.
6. Show behavioral changes, conflicts, renamed or removed skills, source-pin changes, and any new scripts or external actions.
7. Preserve personal profiles and custom skills. A fully renamed skill set needs a manual mapping for each upstream change.
8. Apply the reviewed update. Run `python3 scripts/validate.py` and `python3 -m unittest discover -s tests -v`.
9. Present the diff and installation plan. Ask before pushing, opening or merging a pull request, or reinstalling.
10. After approval, push the update branch, open the pull request, wait for CI, merge, and run `python3 scripts/install.py --operator <handle>` from the merged checkout. Relay any routing approval it previews. An installation made before 0.5.0 needs `--routing` once.
11. Run `python3 scripts/install.py --check` and resolve drift, checkout differences, and shadowed routing. Then verify actual skill discovery in the selected agent products. `docs/routing.md` describes each check result.

Follow the operator's update policy: manual only, notify, open a reviewed pull request, or merge and install automatically only when every configured gate passes. Agent and repository permissions remain authoritative.
Files in this package (3)
  • LICENSES.txt 1 KB
  • SKILL.md 2 KB
  • agents/openai.yaml 1 KB

Versions

The database has no other skills named update-skill-stack.

Database snapshot: 13.11.2026 · package version eefee790b391 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100find-skills
    Searches the open agent skills ecosystem (skills.sh, npx skills) and installs a matching skill for personal use. Use when the user asks to find a skill for X, is there a skill that can do Y, how to extend the agent with a capability, or to install or update skills. Not for…
  • 100set-up-stack-profile
    Use when starting in a repo with no .claude/stack-profile.md, when the stack changed, or when the user asks which plugins and skills to use. Detects the stack, asks only the gaps, writes the profile, and lists plugins and skill order.
  • 100clean-code-update
    Re-sync the clean-* skill family against its upstream source repository, reporting what changed upstream and merging it without losing the local adaptations. Use when asked to "update my clean code skill(s)", re-sync clean code rules, or check whether the upstream clean-code-skills repo has changed.
  • 100update-skill
    Thorough on-demand refresh of one skill in a skills repo - researches usage, upstream, and docs in parallel, gates twice for approval, bumps version, updates CHANGELOG, validates, commits, watches CI. Use to check a skill's freshness.
  • 100skf-create-stack-skill
    Consolidated project stack skill with integration patterns — code-mode (analyzes manifests) or compose-mode (synthesizes from existing skills + architecture doc). Use when the user requests to "create a stack skill", "forge a stack", or "stack this project".
  • 100skill-update
    Repeatable process for keeping skills up-to-date with upstream sources and versions. Use when checking for stale skills, updating a skill for a new upstream version, auditing source freshness, or bootstrapping version tracking for a plugin.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.