upravy projektu a skillu

skills/project/SKILL.md

@@ -4,9 +4,9 @@ description: >
   Switch between named ongoing projects, each with its own persistent
   context, carried forward across turns until the user switches or ends it.
   Triggers on: "project X", "switch to project X", "we're working on X",
-  "end project" / "no project". For a long-lived, named work context — not a
-  single task to plan and execute, and not a short or global fact to
-  remember.
+  "list projects", "end project" / "no project". For a long-lived, named
+  work context — not a single task to plan and execute, and not a short or
+  global fact to remember.
 ---
 
 # Project
@@ -19,17 +19,28 @@ separate from every other project and from the agent's general memory.
 
 `workspace/projects/<slug>/`:
 
-- `prompt.md` — project-specific context/instructions, read in full whenever
-  the project becomes active
+- `prompt.md` — **what doesn't change**: purpose, goals, scope, constraints,
+  how the user wants to work on this. Read in full whenever the project
+  becomes active.
 - `memory.md` — append-only chronological log of decisions and history
-- `state.md` — living document: the current state/synthesis of the project,
-  edited in place, not appended to
+- `state.md` — **what changes**: the living synthesis of where the project is
+  now. Progress, current approach, open questions, "what's next". Edited in
+  place, never appended to.
 - `artifacts/` — generated files (documents, code, data exports, reports)
 
+If you're about to write anything time-varying into `prompt.md` (a "current
+status" or "next steps" section), put it in `state.md` instead.
+
 **Which project is active is tracked purely through conversation memory —
-nothing is persisted to disk for that.** Once a project is chosen, keep
-treating it as active for the rest of this conversation; don't re-read its
-files on every subsequent turn once they're already in context.
+nothing is persisted to disk for that.**
+
+## Script
+
+All project file operations go through one script, run from the workspace root:
+
+`uv run skills/project/scripts/project_cli.py <subcommand>`
+
+It owns the entry date and the append hygiene so they can't be guessed wrong.
 
 ## Activation
 
@@ -37,20 +48,19 @@ Triggered by "project X" / "switch to project X" / "we're working on X":
 
 1. Turn `X` into a kebab-case directory name (like picking a slug for a plan
    file — no need to spell out an algorithm, just pick something sensible).
-2. **`workspace/projects/<slug>/` already exists** → read `prompt.md`,
-   `memory.md`, and `state.md` in full, then briefly confirm what's active
-   and, if `prompt.md` or `state.md` has content, what context you loaded.
-3. **It doesn't exist, but the name is a close match to one or more existing
-   projects** (case-insensitive) → ask which one was meant. Don't guess, and
-   don't create a near-duplicate of an existing project.
-4. **It doesn't exist and there's no close match** → this skill only works
-   with projects that already exist without asking. Ask the user whether to
-   start a new project with that name. Only on explicit yes, create
-   `prompt.md`, `memory.md`, `state.md` (all empty) and `artifacts/`. Never
-   create a project just because a trigger phrase was said.
+2. Run `project_cli.py activate <slug>`. On success it prints `prompt.md`,
+   `memory.md` and `state.md` (creating any that are missing), so no separate
+   reads are needed. Then briefly confirm what's active and, if `prompt.md` or
+   `state.md` has content, what context you loaded.
+3. **Exit 1 means no such project.** The error lists the existing ones. If one
+   is a close match (case-insensitive), ask which was meant — don't guess, and
+   don't create a near-duplicate.
+4. **No close match** → ask the user whether to start a new project with that
+   name. Only on an explicit yes, run `project_cli.py new <slug>`. Never create
+   a project just because a trigger phrase was said.
 
 **Already active:** if the same project is already active in this
-conversation, don't re-create or re-read anything — just continue.
+conversation, don't re-run activation — just continue.
 
 ## Staying active
 
@@ -58,6 +68,11 @@ Once a project is active, keep applying its `prompt.md` instructions and
 `state.md` context for the rest of the conversation, until the user switches
 or ends it.
 
+**If the file contents are no longer in your context** (a long conversation
+gets compacted, and the loaded files can drop out of it while the memory that
+a project is active stays), run `activate` again. Never answer from a faded
+recollection of `prompt.md` or `state.md`.
+
 If a long gap or an ambiguous reference makes it unclear whether the project
 is still the right context (e.g. the conversation has clearly moved to an
 unrelated topic), ask rather than silently carrying it forward or silently
@@ -74,55 +89,84 @@ dropping it.
 
 ## Writing to memory.md
 
-Append only — never rewrite or reorder existing entries. One entry per
-decision, dead end, or noteworthy piece of history:
+**Only ever through the script** — never `edit_file` or `write_file`. Pass the
+text on stdin with a quoted heredoc so quotes and apostrophes survive verbatim:
 
 ```
-- YYYY-MM-DD: <terse entry, reformulated, not verbatim>
+uv run skills/project/scripts/project_cli.py log <slug> <<'NOTE'
+<entry text>
+NOTE
 ```
 
-Write an entry when a decision is made, a dead end is found, or a fact
-central to the project's ongoing context emerges — not for routine
-back-and-forth. When in doubt whether something is memory-worthy, prefer not
-writing it; `memory.md` is for what a future conversation needs to pick up
-the thread, not a transcript.
+The script prepends today's date and guarantees the entry starts on its own
+line. Write the entry in the user's language, reformulated, not verbatim.
+
+Write an entry when a decision is made, a dead end is found, or a fact central
+to the project's ongoing context emerges — not for routine back-and-forth. When
+in doubt, **write it**: losing something the user told you is worse than an
+entry that turns out to be unremarkable. Entry length is not limited — capture
+the reasoning behind a decision, not just its outcome.
+
+**Correcting an entry:** `memory.md` is append-only, so never rewrite history.
+Log a new entry starting with `correction:` that states what was wrong.
 
 ## Maintaining state.md
 
-Unlike `memory.md`, `state.md` is edited in place: surgically update the
-relevant section when the project's current state or understanding has
-moved on enough that the old text would mislead a reader. It answers "where
-is this now", not "what happened" — old content gets replaced, not appended
-to. If it's still empty and the project has accumulated enough context to
-synthesize, offer to draft it.
+Edited in place with `edit_file`: surgically update the relevant section when
+the project's current state or understanding has moved on enough that the old
+text would mislead a reader. It answers "where is this now", not "what
+happened" — old content gets replaced, not appended to.
+
+**If `state.md` is empty and `memory.md` has content, draft it** from that
+history and show the user the result. Don't just offer. Likewise, if
+`prompt.md` still holds a time-varying section, move it here.
+
+## Answering questions about a project
+
+Answers that live in project files come **from the files**, not from memory:
+read or `grep` them. If a project is active, its files are the first place to
+look; with no project active, `grep` across `workspace/projects/` to find where
+something was written.
+
+## What goes where
+
+While a project is active, a fact tied to that project goes into its
+`memory.md` via the script. A durable fact about the user in general — one that
+would still matter with no project active — goes to the normal memory path
+instead.
 
 ## Artifacts
 
 Files generated while working on the project (documents, code, data exports,
-reports) go in `workspace/projects/<slug>/artifacts/` instead of scattered
-elsewhere. Name them descriptively; no numbering or index file needed at
+reports) go in `workspace/projects/<slug>/artifacts/`, created the first time
+one is written. Name them descriptively; no numbering or index file needed at
 this scale.
 
+## Growth
+
+`memory.md` grows without limit and is **never compacted, archived or
+summarized**. When it gets long, `activate` simply stops printing all of it and
+says where the rest is — read or `grep` the file directly for older context.
+Never delete, shorten or rewrite stored content to save space.
+
 ## Listing
 
-**"list projects" / "which projects exist":** list the directory names under
-`workspace/projects/`. If none exist, say so.
+**"list projects" / "which projects exist":** run `project_cli.py list`. It
+prints each project with its file sizes; `(!)` marks an empty `state.md`.
 
 ## Edge cases
 
 - "project" with no name → ask which project.
-- The project directory exists but one or more of `prompt.md` / `memory.md`
-  / `state.md` is missing (e.g. created by hand) → create the missing
-  file(s) empty, don't error.
+- Missing `prompt.md` / `memory.md` / `state.md` (e.g. directory made by hand)
+  → `activate` creates them, don't error.
 - Deleting or renaming a project is out of scope for this skill — point the
   user at `workspace/projects/<slug>/` to do it by hand.
 
 ## Rules
 
-- This skill's body is English; reply to the user in their own language.
+- This skill's body is English; reply to the user in their own language, and
+  write project files in the user's language too.
 - Never fabricate project content — `prompt.md`, `memory.md`, and `state.md`
   only grow from what the user actually said or what actually happened.
 - Never create a new project without the user's explicit confirmation.
 - Don't force a project context onto an unrelated request.
-- The Dream memory processor must not touch `workspace/projects/` — it is
-  outside the memory and skills Dream curates.