viktor/infra
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 2
infra/scripts/workstation/claude-skills/README.md

48 lines
2.5 KiB
Markdown
Raw Normal View History

t3-provision-users: vendor agent skills + per-user install_skills (emo) Make the admin's Claude Code agent skills available to the `emo` devvm user. Viktor asked to install Matt Pocock's skills for emo, starting with grill-me but covering the full set the admin already uses. The `npx skills` upstream has drifted off that set (diagnose -> diagnosing-bugs and write-a-skill -> writing-great-skills were renamed; caveman + zoom-out are no longer published), so reproducing it via npx is impossible and would also spray ~70 agent dirs into the user's home + add a GitHub-clone + unpinned-CLI dependency to the hourly root reconcile. Instead vendor a point-in-time snapshot of the 16 skills (scripts/workstation/claude-skills/) and copy them per-user, mirroring install_memory: install_skills() copies each skill into ~/.agents/skills/<name> (owned by the user) and symlinks ~/.claude/skills/<name> -> ../../.agents/skills/<name>. if-absent, additive, best-effort, scoped to the SKILL_USERS allowlist (emo). find-skills is from vercel-labs/skills (not Matt Pocock) but included since it is part of the admin's current set. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-23 09:23:37 +00:00
# claude-skills — vendored agent-skill snapshot
Point-in-time snapshot of the admin's (`wizard`) Claude Code agent skills, deployed
per-user by `install_skills()` in `../../t3-provision-users.sh` (scoped to the
`SKILL_USERS` allowlist). Each subdirectory is one skill (`SKILL.md` + any bundled
references). The provisioner copies a skill into `~/.agents/skills/<name>/` (owned by
the user) and symlinks `~/.claude/skills/<name> -> ../../.agents/skills/<name>` — the
layout the `skills` CLI's `-g` install produces; Claude Code reads `~/.claude/skills/`.
## Why vendored (not `npx skills add` at provision time)
Upstream drifted from this set: on `mattpocock/skills` master, `diagnose` →
`diagnosing-bugs` and `write-a-skill` → `writing-great-skills` were renamed, and
`caveman` + `zoom-out` are no longer published — so `npx skills` cannot reproduce this
exact set. Vendoring is also offline/deterministic and keeps GitHub-clone +
unpinned-CLI dependencies out of the hourly **root** reconcile.
## Sources
- `mattpocock/skills` (https://github.com/mattpocock/skills) — all except `find-skills`
- `vercel-labs/skills` (https://github.com/vercel-labs/skills) — `find-skills`
devvm: personalize emo's cluster-health skill for ha-sofia emo cares about ha-sofia + his Sofia smart-home devices (Tuya, the MPPT ATS, the Барзини → Статус dashboard), and only about the cluster when it's breaking those. Rewrite his vendored cluster-health into an ha-sofia-focused, read-only variant: - leads with ha-sofia's in-cluster dependency chain (tuya-bridge + the cloudflared/Traefik/DNS/TLS reachability path), all checkable read-only; - fixes the script path to emo's own clone (/home/emo/code) — he can't read wizard's tree — and runs it --no-fix (he's cluster read-only); - loads emo's own HA token (see below) so the ha-sofia checks (26-29, 45) actually run for him; documents the host-SSH/Vault checks that skip; - triages: cluster FAIL/WARN matters only if on his chain; everything else is a one-line "admin's area"; escalate via /file-issue since he can't fix. This snapshot copy is now an emo-specific variant, intentionally diverged from the canonical 47-check admin skill — README updated to say "do not re-sync from canonical". Token: a dedicated long-lived HA token (client_name emo-cluster-health) was minted on ha-sofia via the admin account and stored emo-readable at /home/emo/.config/cluster-health/haos_token (600). It carries admin HA scope (HA only mints tokens for the authenticating account); independently revocable. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-26 16:03:14 +00:00
- **homelab-local, emo-PERSONALIZED** — `cluster-health` here is an
**emo-specific variant**, not a copy of the canonical skill. It started as a
copy of this repo's `.claude/skills/cluster-health/` but was rewritten on
2026-06-26 to focus on ha-sofia + emo's Sofia devices (emo is the only entry
in `SKILL_USERS`, a read-only power-user). The canonical admin skill
(`.claude/skills/cluster-health/`) is the full 47-check version and is left
untouched. **Do NOT `cp -a` the canonical copy over this one** — that would
clobber the personalization. Maintain the two independently.
t3-provision-users: vendor agent skills + per-user install_skills (emo) Make the admin's Claude Code agent skills available to the `emo` devvm user. Viktor asked to install Matt Pocock's skills for emo, starting with grill-me but covering the full set the admin already uses. The `npx skills` upstream has drifted off that set (diagnose -> diagnosing-bugs and write-a-skill -> writing-great-skills were renamed; caveman + zoom-out are no longer published), so reproducing it via npx is impossible and would also spray ~70 agent dirs into the user's home + add a GitHub-clone + unpinned-CLI dependency to the hourly root reconcile. Instead vendor a point-in-time snapshot of the 16 skills (scripts/workstation/claude-skills/) and copy them per-user, mirroring install_memory: install_skills() copies each skill into ~/.agents/skills/<name> (owned by the user) and symlinks ~/.claude/skills/<name> -> ../../.agents/skills/<name>. if-absent, additive, best-effort, scoped to the SKILL_USERS allowlist (emo). find-skills is from vercel-labs/skills (not Matt Pocock) but included since it is part of the admin's current set. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-23 09:23:37 +00:00
## Refreshing
devvm: vendor cluster-health into per-user agent-skill snapshot Make cluster-health a user-global skill for emo (the lone entry in the provisioner's SKILL_USERS allowlist), so it's available from any directory — not only when working inside the infra clone where it already exists as a project skill (.claude/skills/cluster-health). install_skills() in t3-provision-users.sh copies the vendored snapshot into ~/.agents/skills/ and symlinks ~/.claude/skills/, so this is the durable, rebuild-surviving path. cluster-health is homelab-local (vendored from this repo's own .claude/skills/), unlike the other snapshot entries which mirror upstream mattpocock/skills + vercel-labs/skills; README documents its provenance and the explicit re-sync step so the vendored copy doesn't silently drift. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-26 15:20:19 +00:00
Re-snapshot the upstream skills from a current install and commit the diff:
t3-provision-users: vendor agent skills + per-user install_skills (emo) Make the admin's Claude Code agent skills available to the `emo` devvm user. Viktor asked to install Matt Pocock's skills for emo, starting with grill-me but covering the full set the admin already uses. The `npx skills` upstream has drifted off that set (diagnose -> diagnosing-bugs and write-a-skill -> writing-great-skills were renamed; caveman + zoom-out are no longer published), so reproducing it via npx is impossible and would also spray ~70 agent dirs into the user's home + add a GitHub-clone + unpinned-CLI dependency to the hourly root reconcile. Instead vendor a point-in-time snapshot of the 16 skills (scripts/workstation/claude-skills/) and copy them per-user, mirroring install_memory: install_skills() copies each skill into ~/.agents/skills/<name> (owned by the user) and symlinks ~/.claude/skills/<name> -> ../../.agents/skills/<name>. if-absent, additive, best-effort, scoped to the SKILL_USERS allowlist (emo). find-skills is from vercel-labs/skills (not Matt Pocock) but included since it is part of the admin's current set. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-23 09:23:37 +00:00
```sh
cp -a ~/.agents/skills/. scripts/workstation/claude-skills/
```
devvm: personalize emo's cluster-health skill for ha-sofia emo cares about ha-sofia + his Sofia smart-home devices (Tuya, the MPPT ATS, the Барзини → Статус dashboard), and only about the cluster when it's breaking those. Rewrite his vendored cluster-health into an ha-sofia-focused, read-only variant: - leads with ha-sofia's in-cluster dependency chain (tuya-bridge + the cloudflared/Traefik/DNS/TLS reachability path), all checkable read-only; - fixes the script path to emo's own clone (/home/emo/code) — he can't read wizard's tree — and runs it --no-fix (he's cluster read-only); - loads emo's own HA token (see below) so the ha-sofia checks (26-29, 45) actually run for him; documents the host-SSH/Vault checks that skip; - triages: cluster FAIL/WARN matters only if on his chain; everything else is a one-line "admin's area"; escalate via /file-issue since he can't fix. This snapshot copy is now an emo-specific variant, intentionally diverged from the canonical 47-check admin skill — README updated to say "do not re-sync from canonical". Token: a dedicated long-lived HA token (client_name emo-cluster-health) was minted on ha-sofia via the admin account and stored emo-readable at /home/emo/.config/cluster-health/haos_token (600). It carries admin HA scope (HA only mints tokens for the authenticating account); independently revocable. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-26 16:03:14 +00:00
`cluster-health` is hand-maintained (emo variant) — it is **not** covered by the
`cp -a` above and must **not** be overwritten from `.claude/skills/`. Edit it in
place here when emo's needs change, then refresh his live copy (the provisioner's
`install_skills()` is if-absent, so it won't update an existing `~/.agents/skills`
copy — `cp` the new `SKILL.md` to `/home/emo/.agents/skills/cluster-health/` and
`chown emo:emo`, or remove emo's copy and re-run the reconcile).
devvm: vendor cluster-health into per-user agent-skill snapshot Make cluster-health a user-global skill for emo (the lone entry in the provisioner's SKILL_USERS allowlist), so it's available from any directory — not only when working inside the infra clone where it already exists as a project skill (.claude/skills/cluster-health). install_skills() in t3-provision-users.sh copies the vendored snapshot into ~/.agents/skills/ and symlinks ~/.claude/skills/, so this is the durable, rebuild-surviving path. cluster-health is homelab-local (vendored from this repo's own .claude/skills/), unlike the other snapshot entries which mirror upstream mattpocock/skills + vercel-labs/skills; README documents its provenance and the explicit re-sync step so the vendored copy doesn't silently drift. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-26 15:20:19 +00:00
devvm: personalize emo's cluster-health skill for ha-sofia emo cares about ha-sofia + his Sofia smart-home devices (Tuya, the MPPT ATS, the Барзини → Статус dashboard), and only about the cluster when it's breaking those. Rewrite his vendored cluster-health into an ha-sofia-focused, read-only variant: - leads with ha-sofia's in-cluster dependency chain (tuya-bridge + the cloudflared/Traefik/DNS/TLS reachability path), all checkable read-only; - fixes the script path to emo's own clone (/home/emo/code) — he can't read wizard's tree — and runs it --no-fix (he's cluster read-only); - loads emo's own HA token (see below) so the ha-sofia checks (26-29, 45) actually run for him; documents the host-SSH/Vault checks that skip; - triages: cluster FAIL/WARN matters only if on his chain; everything else is a one-line "admin's area"; escalate via /file-issue since he can't fix. This snapshot copy is now an emo-specific variant, intentionally diverged from the canonical 47-check admin skill — README updated to say "do not re-sync from canonical". Token: a dedicated long-lived HA token (client_name emo-cluster-health) was minted on ha-sofia via the admin account and stored emo-readable at /home/emo/.config/cluster-health/haos_token (600). It carries admin HA scope (HA only mints tokens for the authenticating account); independently revocable. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-26 16:03:14 +00:00
Snapshot taken 2026-06-23 (upstream); `cluster-health` vendored 2026-06-26,
personalized for emo 2026-06-26.
Reference in a new issue Copy permalink