feat(update-claude-skills): add update skill + scripts [v0.1.0]

New skill and cross-platform scripts that automate the full uplift cycle:
git pull → conditionally rebuild MCP servers → install skills → version
diff → reload hints. Claude-Code-only (Hermes uses hermes-installer-skill).

- scripts/update.sh: bash version (Linux/macOS/git-bash)
- scripts/update.ps1: PowerShell version (Windows)
- skills/update-claude-skills/SKILL.md: thin wrapper, detects platform
- hermes/mapping.yaml: mode: skip (Claude-Code-only)
- dist/update-claude-skills.skill: built archive
- .tasks/STATUS.md: task marked done

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
2026-05-07 14:04:27 +03:00
parent efd73ec4e6
commit 627a183b3e
8 changed files with 472 additions and 4 deletions

View File

@@ -12,6 +12,7 @@ Do not edit by hand — edit the mapping and re-run the build.
- **caveman-review** — Caveman family — cheap-model context, no compression motive.
- **find-skills** — Hermes has built-in skills_list() / progressive disclosure.
- **setup-interns** — Hermes itself is a cheap-intern model — the delegation tier collapses.
- **update-claude-skills** — Claude-Code-only orchestrator — Hermes uses hermes-installer-skill instead.
- **using-interns** — Hermes itself is a cheap-intern model — the delegation tier collapses.
## Pending (deferred to follow-up tasks)

View File

@@ -1,6 +1,6 @@
---
name: project-bootstrap
version: 1.10.0
version: 1.10.1
description: >
Initializes or upgrades a project in the current folder: git, .gitignore, README.md,
.wiki/ using Karpathy's method, .tasks/ for task tracking, CLAUDE.md with skill triggers.
@@ -338,7 +338,9 @@ use task management system
check across all projects
pull remote before work
follow project discipline
follow tdd-criteria
delegate to interns when allowed
recommend, don't menu
we're on Windows
```
@@ -365,6 +367,14 @@ push only after explicit per-session approval. Install the skill on the host
if `project-discipline` is not in `~/.claude/skills/`; otherwise the trigger is
silently dead like any other absent skill.
The `follow tdd-criteria` line activates the `tdd-criteria` skill, which enforces
test-driven development by default with four bright-line carve-outs (visual CSS,
spike exploration, oneshot scripts, pure wrappers) and four anti-loophole rules
(including test-immutability: modifying assertions requires a `[test-modify: ...]`
marker in the commit subject). Full rationale at `.wiki/concepts/tdd-criteria-design.md`
in the `claude-skills` repo. Install the skill on the host if `tdd-criteria` is not
in `~/.claude/skills/`; otherwise the trigger is silently dead like any other absent skill.
The `delegate to interns when allowed` line activates the `using-interns` skill,
which lets Claude offload predictable bulk I/O and summarization tasks
(reading 3+ files, distilling long transcripts) to cheap intern LLMs via the
@@ -378,6 +388,14 @@ server is registered — install via `setup-interns` on a fresh machine if
`mcp__interns__*` tools are missing. Full design at
`.wiki/concepts/interns-design.md` in the `claude-skills` repo.
The `recommend, don't menu` line activates the `recommend-dont-menu` skill,
which overrides the default `superpowers:brainstorming` behavior: in design
discussions, architecture reviews, or "what should we do" questions, the agent
gives **one argued recommendation with explicit trade-offs**, not a multiple-
choice menu. User instructions always take precedence over skill defaults.
Install the skill on the host if `recommend-dont-menu` is not in `~/.claude/skills/`;
otherwise the trigger is silently dead like any other absent skill.
The `we're on Windows` line activates the `active-platform` skill and pins the
project's default platform to Windows / PowerShell — so generated commands and
README quick-starts use PS-native syntax. Bootstrapping on a Linux or macOS