Six bundled default skills with skills install target (1.40.0)

- BUNDLED_SKILLS embeds deep-research, seriousdevelopment, git, plan,
  requirements-clarification, taste (21 files), adapted for tai:
  load_skill, ask_user, fork/poll workers, web_fetch (never curl),
  single-line descriptions, no em dashes; seriousdevelopment verbatim
- new skills install target (12th): install writes missing only,
  upgrade refreshes pristine and loudly keeps user-modified files,
  reinstall rebuilds tracked files keeping extras, uninstall removes
  only unmodified content; sidecar records upstream provenance
- bare --install includes skills; run_install refreshes live skills
- README: Skills section bundled paragraph, twelve targets

README.md

@@ -80,7 +80,7 @@ Any other input is sent to the agent.
     /install status
     /install upgrade scheduler-service
 
-Eleven install targets exist side by side: `binary` (`~/.local/bin/tai.py`); a command-not-found hook per shell -- `bash-hook` (`~/.bashrc`), `zsh-hook` (`~/.zshrc`), `fish-hook` (`~/.config/fish/config.fish`, respecting `$XDG_CONFIG_HOME`) -- each a guarded block (backed up once to `<rc file>.bak-tai` before the first write) adding a `tai` alias/function so the bare `tai` command resolves to the REPL instead of falling through, plus the shell's own not-found mechanism (`command_not_found_handle` for bash, `command_not_found_handler` for zsh, a `fish_command_not_found` function for fish) so any other unknown shell command is answered by the agent instead; a plexer auto-wrap hook per shell -- `plexer-hook` (bash), `zsh-plexer-hook`, `fish-plexer-hook` -- that transparently re-execs a fresh interactive shell into a managed, scriptable plexer session (`tai.py --plexer-wrap`; skipped automatically inside tmux, inside another plexer-wrapped shell, or when `~/.tai-no-plexer` exists) using whatever that shell can actually express (`[`/`case "$-"` for bash and zsh -- byte-identical content, since both are POSIX enough for it; `status is-interactive`/`test`/`isatty` for fish, which has neither); `venv` (`~/.tai/venv`, created whenever the venv module exists); `scheduler-service` and `telegram-service` (systemd user units that prefer the venv python); and `container` (the sandbox, whose image carries its own `/box/venv`). Installing a zsh/fish-specific target on a machine without that shell skips loudly (`"zsh-hook: zsh not found, skipped"`) rather than writing a dangling hook into a config file nothing will ever source; `uninstall`/`reinstall` still act on the file regardless, so a hook installed before a shell was later removed still gets cleaned up. `/install status` (or the `install` tool) reports exactly which of these exist, with versions and service states. `install` adds missing pieces, `upgrade` refreshes in place, `reinstall` rebuilds artifacts from scratch, `uninstall` removes them; service changes restart or start units immediately. Data handling is explicit: no action ever touches the vault (`memory.db`, secrets, schedules, records, backups). `./tai.py --install` (the one-shot CLI bootstrap) always installs the bash hook and, in addition, detects `$SHELL` and installs that shell's matching hook too when it's zsh or fish.
+Twelve install targets exist side by side: `binary` (`~/.local/bin/tai.py`); a command-not-found hook per shell -- `bash-hook` (`~/.bashrc`), `zsh-hook` (`~/.zshrc`), `fish-hook` (`~/.config/fish/config.fish`, respecting `$XDG_CONFIG_HOME`) -- each a guarded block (backed up once to `<rc file>.bak-tai` before the first write) adding a `tai` alias/function so the bare `tai` command resolves to the REPL instead of falling through, plus the shell's own not-found mechanism (`command_not_found_handle` for bash, `command_not_found_handler` for zsh, a `fish_command_not_found` function for fish) so any other unknown shell command is answered by the agent instead; a plexer auto-wrap hook per shell -- `plexer-hook` (bash), `zsh-plexer-hook`, `fish-plexer-hook` -- that transparently re-execs a fresh interactive shell into a managed, scriptable plexer session (`tai.py --plexer-wrap`; skipped automatically inside tmux, inside another plexer-wrapped shell, or when `~/.tai-no-plexer` exists) using whatever that shell can actually express (`[`/`case "$-"` for bash and zsh -- byte-identical content, since both are POSIX enough for it; `status is-interactive`/`test`/`isatty` for fish, which has neither); `venv` (`~/.tai/venv`, created whenever the venv module exists); `scheduler-service` and `telegram-service` (systemd user units that prefer the venv python); `container` (the sandbox, whose image carries its own `/box/venv`); and `skills` (six default skills into `~/.tai/skills`, see "Skills" below). Installing a zsh/fish-specific target on a machine without that shell skips loudly (`"zsh-hook: zsh not found, skipped"`) rather than writing a dangling hook into a config file nothing will ever source; `uninstall`/`reinstall` still act on the file regardless, so a hook installed before a shell was later removed still gets cleaned up. `/install status` (or the `install` tool) reports exactly which of these exist, with versions and service states. `install` adds missing pieces, `upgrade` refreshes in place, `reinstall` rebuilds artifacts from scratch, `uninstall` removes them; service changes restart or start units immediately. Data handling is explicit: no action ever touches the vault (`memory.db`, secrets, schedules, records, backups). `./tai.py --install` (the one-shot CLI bootstrap) always installs the bash hook and, in addition, detects `$SHELL` and installs that shell's matching hook too when it's zsh or fish.
 
 ## Plexer
 
@@ -233,6 +233,8 @@ Its quieter cousin, `get_current_terminal_content`, grabs just the visible pane
 
 Standard agent skill files (`SKILL.md` with `name` plus `description` frontmatter, optional `scripts/`, `references/`, `assets/`, per the open Agent Skills format) are discovered from four places, in ascending priority so the most tai-specific location always wins a name collision: read-only interop with `~/.claude/skills` and `./.agents/skills` first (so a skill another tool already dropped next to your project is visible with *zero* install step), then tai's own `~/.tai/skills`, then `./.tai/skills`. Descriptions stay in the system prompt catalog at all times; full instructions load only through `load_skill`, on demand — the same lazy-loading philosophy as tools, applied to skills.
 
+Six skills ship inside `tai.py` itself and land in `~/.tai/skills` with `./tai.py --install` (or `/install skills`): `deep-research` (parallel evidence-gathering method with per-domain source routing, adapted to `fork`/`poll` and `web_fetch`), `seriousdevelopment` (spec-first delivery method with ADRs and build tracking, verbatim), `git` (history-write safety plus a recovery script, with a note reconciling it with tai's approval settings), `plan` (explicit planning requests with research-before-drafting, `go` to execute), `requirements-clarification` (narrow pre-commit questions via `ask_user`), and `taste` (frontend anti-slop filter). They are installed, never forced: `install` writes only missing skills, `upgrade` refreshes pristine files and loudly keeps user-modified ones, `reinstall` rebuilds tracked files while keeping user-added extras, and `uninstall` removes only unmodified content. Edit an installed skill freely; its `.installs/` sidecar records the upstream provenance.
+
 Two independent, complementary ways to get a skill:
 
 - **`create_skill`** authors a brand-new one from a brief: a dedicated deep-research subagent runs `sysinfo` first so the skill matches the actual machine, then researches with web search and shell until the material is independently verified, then writes `SKILL.md` plus supporting files — project-scoped by default. Six blueprints ship built in (`bot-creator`, `api-client`, `web-researcher`, `pdf-forms`, `data-wrangler`, `home-sysadmin`); `load_skill` builds a missing one through this exact same path the first time it's actually needed, so a skill finalizes lazily at the moment of use, not at install time.