marketplace/skills/issue/SKILL.md

name, description

name	description
issue	Work with this project's issues as units of work — create, read, grep, validate, and walk their dependency graph. Entirely offline; issues are local markdown files and need no tracker. Load when the user asks to file/create an issue, read or find issues, check an issue against the format, or see what depends on what. For pushing to or pulling from Gitea, load /tea:sync instead.

/tea:issue — issues as units of work

An issue is a markdown file in tmp/issues/. This skill covers everything you do with an issue: writing one, reading one, checking it against the canonical format, and walking the dependency graph.

Nothing here touches the network. No tea, no Gitea, no login. An issue that lives only on this machine is a first-class issue, not a draft waiting to be uploaded. Synchronizing with a tracker is a separate, optional layer — /tea:sync.

Read references/format.md before creating or editing an issue. It is the single source of truth for identity, metadata, types, labels, templates, and language rules.

Identity: the slug

The file name is the id and the id is a slug — tmp/issues/wire-sqlc-appclick.md. It never changes, not when the title changes and not when the issue is pushed somewhere. Tracker numbers live in a metadata field (gitea: owner/repo#42), never in a file name and never in depends:.

Consequence worth internalizing: #42 means nothing in this layer. Refer to issues by id.

Scripts

All offline, all in <skill-base-dir>/scripts/.

Script	What it does
issue_new.py --type T --title "…"	create tmp/issues/<slug>.md from the type's template
issue_check.py [id…]	validate against the canonical format; exit 1 on errors
issue_ac.py <id> [--check N|TEXT]	list the body's checkboxes; tick or untick one
issue_tree.py [id…]	draw the dependency graph from depends:
issue_evict.py [id…] [--dry-run]	remove closed issues from the store; never an origin: local one
issue_index.py	rebuild tmp/issues/INDEX.md
issue.py	the domain module the others import — not a command

tmp/issues/INDEX.md                 table of every issue — read this first
tmp/issues/wire-sqlc-appclick.md    metadata block + `# Title` + body
tmp/issues/wire-sqlc.comments.md    comment thread (written by /tea:sync only)
tmp/issues/tree-<id>.md             saved graph (issue_tree.py --write)

Where the store is

<repo root>/tmp/issues — not tmp/issues relative to wherever you are standing. The scripts resolve it by walking up from their own file to the nearest .git or AGENTS.md, so they all see one store no matter which directory you run them from, and a cd earlier in the session changes nothing.

--out overrides that and is taken literally: an absolute path is used as given, a relative one stays relative to the current directory. Nothing rewrites what you typed.

Two things follow, and both are deliberate:

• A store that is not there reports does not exist; a store with no issues in it reports is empty. They are different problems.
• No script conjures a store as a side effect of writing. Only issue_new.py creates one — the first issue in a fresh checkout — and it says so on stderr.

Reading: grep, don't parse

Metadata is one field per line with inline lists precisely so plain grep works. INDEX.md first, then the files:

grep -l  'labels:.*type/bug' tmp/issues/*.md      # all bugs
grep -l  'origin: local' tmp/issues/*.md          # never pushed anywhere
grep -ln 'depends:.*migrate-schema' tmp/issues/*.md   # who depends on it
grep -A3 '## Acceptance criteria' tmp/issues/wire-*.md
grep -c  '^- \[ \]' tmp/issues/wire-sqlc-appclick.md  # open checkboxes

Read whole files only for the issues the task actually needs.

Creating an issue

1. Read the format: references/format.md.
2. Pick the type — bug, task, refactor, test, feature (a container for several issues with one business value), or draft (an idea not ready for work). If it is not obvious from the request, ask the user (one question).
3. Scaffold it:

   python3 <skill-base-dir>/scripts/issue_new.py \
     --type task --title "Wire sqlc into the appclick repo layer" \
     --label tech/sql --label comp/appclick --depends migrate-schema
   

   English imperative title with no type prefix; --depends takes ids.
4. Fill the sections with Edit — every section of the template present and in order, headers English, prose Russian. ## Spec gets a repo path, a URL, or the literal none; ask the user if you cannot determine which.
5. Check it:

   python3 <skill-base-dir>/scripts/issue_check.py wire-sqlc-appclick
   

One file = one issue. Several related issues = several files, linked through depends:.

The issue is now real and complete. Publishing it to Gitea is a separate decision — /tea:sync — and does not change the file's status here.

Editing an issue

Edit the file. Change state: to close it, edit labels:, add ids to depends:. Re-run issue_check.py afterwards, and issue_index.py to refresh the table. Checkboxes are the exception — use issue_ac.py, below.

If the issue is synced (origin: gitea), the file is a working copy: your edit is local until you run push.py --update from /tea:sync, and that push deletes the file once Gitea has it. Nothing tracks drift, and with one copy at a time there is little to track — a file that is still here has not been pushed. Get it back with pull.py <n>; the slug does not change.

Ticking checkboxes

A checkbox is the one part of a body that is state and not prose, so it has a command of its own. Never rewrite a body just to tick a box: the rewrite re-flows lines and re-words sentences, and the issue's diff swells around a change that means one character.

python3 <skill-base-dir>/scripts/issue_ac.py wire-sqlc-appclick
python3 <skill-base-dir>/scripts/issue_ac.py wire-sqlc-appclick --check 3
python3 <skill-base-dir>/scripts/issue_ac.py wire-sqlc-appclick --check "регресс"
python3 <skill-base-dir>/scripts/issue_ac.py wire-sqlc-appclick --uncheck 3

With no flag it prints the numbered list with each item's state, grouped by the heading the item sits under. --check / --uncheck take that number or a substring of the item's text (case-insensitive).

• Every checkbox in the body counts, not just ## Acceptance criteria. A type/feature keeps its children as checkboxes under ## Issues, and they are numbered in the same list. The script is named after the section most boxes live in, nothing more.
• A substring must match exactly one item. Two matches is an error that lists them; pick by number instead. It never guesses.
• Exactly one character of the file changes. Metadata, wording, wrapping and trailing whitespace all come back byte for byte, so git diff and the tracker's diff show the tick and nothing else.
• Examples inside a ``` fence are markup, not state — they are skipped.
• INDEX.md gains a progress column (3/7, blank when the issue has no boxes), recomputed from the body on every build and stored in no field. issue_ac.py rebuilds the index after a successful tick.

Getting the tick to the tracker is a separate step — push.py --update in /tea:sync.

Writing a proper description

Issues get filed on the run — "comments aren't pulled", "the guard broke". That is a request, not a statement of work: no reproduction steps, no path/file:line, acceptance criteria nobody can check. Rewriting one into the canonical format is a procedure, not improvisation.

1. Read the issue whole, and everything it points at — the ids in depends:, the ## Spec target, the files it names.

2. Determine the type and its template. The type/* label selects one of the templates in references/format.md, and that template's section list is the shape you are aiming at. If the label is missing or wrong, decide it now and fix labels:; promoting a type/draft to a concrete type is this same step.

3. Locate the anchor points in the code. Grep the repo for every file, symbol, command, and error string the issue mentions, until you can name lines:

   grep -rn 'GITEA_LOGIN' hooks/ skills/
   

   Work that does not exist yet still has anchor points — the files the change will land in, and the ones that will call it.

4. Gather the missing context. What has to be there when you are done:

   • code references in the path/file.ext:line form, for every place the change lands;
   • reproduction steps — exact commands and their real output (type/bug splits them across ## Steps to reproduce / ## Expected / ## Actual);
   • acceptance criteria that are objectively checkable: a command that exits 0, a file that exists, a section that is present — not aspirations;
   • a real value for ## Spec — a repo path, a URL, or the literal none.

   A missing fact is either found in the repository or becomes a question to the user. Inventing one is forbidden. Ask in one batch, and keep none in ## Spec as the legitimate answer it is — never a plausible-looking link.

5. Rewrite the sections with Edit: every section of the template, in the template's order, English headers and Russian prose. Replace the body; do not append a second telling of the same issue below the old one.

6. Check it:

   python3 <skill-base-dir>/scripts/issue_check.py wire-sqlc-appclick
   

   Errors mean malformed, warnings mean the type's template is not fully filled in. Re-run issue_index.py if the labels changed.

The procedure is identical for origin: local and origin: gitea — it works on tmp/issues/<id>.md, and this layer does not know the difference. Getting the rewritten body into the tracker is a separate decision — push.py --update in /tea:sync — and is no part of this.

Evicting closed issues

The store is a working set, not an archive. A closed issue is not a unit of work any more, and one command takes it out — no rm, no rebuilding INDEX.md by hand:

python3 <skill-base-dir>/scripts/issue_evict.py --dry-run   # what would go
python3 <skill-base-dir>/scripts/issue_evict.py             # every closed one
python3 <skill-base-dir>/scripts/issue_evict.py old-thing   # just this one

Two conditions, both read off the file, and the second one is the whole safety argument:

state:	origin:	what eviction does
closed	a tracker	removes <id>.md and every sidecar under that slug
closed	local	keeps it, always, and says why
open	anything	keeps it

origin: local is never evicted, in any state, not even when you name it on the command line. That file is the issue; there is no copy to fetch back. Only a file whose own metadata says the work lives somewhere else may go — the same trade push.py makes when it drops a file the tracker just confirmed.

• --dry-run prints what would go and writes nothing at all, INDEX.md included.
• INDEX.md is rebuilt afterwards, so the table and the directory agree. It is rebuilt only when something was actually removed.
• .remote.json is not pruned, deliberately: it is the number → slug ledger, and its entries are supposed to outlive the files they name (that is what makes pull.py <n> land on the same slug after a push). An evicted issue is in exactly the state a pushed one is.
• This is not a one-off migration. pull.py <n> fetches an issue in any state — a number is an address, not a query — so a closed issue pulled after an eviction lands on disk again. Not a regression: evict it again when you are done reading it.

This command is offline and decides from state: in the file, which is only as fresh as the last pull. To have the tracker's answer instead — an issue closed in the web UI five minutes ago — use /tea:sync's evict.py, which refreshes state: first and then calls exactly this decision.

Dependency graph

depends: is the authoritative edge list; the body's ## Depends on section is prose for humans. issue_check.py warns when they disagree.

python3 <skill-base-dir>/scripts/issue_tree.py                 # all roots
python3 <skill-base-dir>/scripts/issue_tree.py wire-sqlc-appclick --write

A type/feature plus its children read as one document: draw the tree once for the shape, then grep the files.

Layering rule

This skill must keep working with skills/sync/ deleted. Every import under scripts/ is stdlib, and subprocess is not among them:

grep -rhn '^import\|^from' skills/issue/scripts/ | sort -u

If you find yourself wanting a tracker concept here — an issue number, a login, an HTTP call — it belongs in /tea:sync.