@erclx/aitk 3.14.0 → 3.14.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/claude/.claude-plugin/plugin.json +1 -1
- package/claude/skills/claude-address-review/SKILL.md +8 -5
- package/claude/skills/claude-pr-review/SKILL.md +4 -0
- package/claude/skills/git-followup/REQUIREMENT.md +2 -0
- package/claude/skills/git-followup/SKILL.md +8 -4
- package/package.json +1 -1
- package/standards/pr.md +1 -0
|
@@ -78,11 +78,14 @@ the `git-followup` skill, invoked with `reply-owned` so it stages, commits,
|
|
|
78
78
|
pushes, and refreshes the open PR body without posting its own comment. This
|
|
79
79
|
skill owns the reply. Do not reimplement that flow here.
|
|
80
80
|
|
|
81
|
-
|
|
82
|
-
|
|
83
|
-
|
|
84
|
-
|
|
85
|
-
the
|
|
81
|
+
`git-followup` syncs the body and title against the fix commit on every
|
|
82
|
+
invocation, including `reply-owned`, so the merge record reflects what this pass
|
|
83
|
+
changed rather than only what opened the PR. The reply comment still carries the
|
|
84
|
+
fix log mapped to each finding, since the two serve different readers: the body
|
|
85
|
+
is the merge record and the reply is the review's own thread. A rebase in step 5
|
|
86
|
+
rewrote the branch, so that push is a force-push and `git-followup` resolves it
|
|
87
|
+
from the tracking branch. Worker branches are single-owner here, which is what
|
|
88
|
+
makes overwriting the remote safe.
|
|
86
89
|
|
|
87
90
|
`git-followup` stops on an unchanged tree. A run that answered every finding as a
|
|
88
91
|
conscious-accept and whose rebase left the generated files alone has nothing for
|
|
@@ -87,6 +87,8 @@ Then read the description's `## Testing` section, which is the one part of a pul
|
|
|
87
87
|
|
|
88
88
|
Test every unchecked box against the testing discipline in `${CLAUDE_SKILL_DIR}/../../standards/pr.md`, which reserves an unchecked box for a capability the agent lacks. Raise the box when it names no human at all, when the human it names is a live agent session, or when it names a person for a step the repository ships a harness for, `scripts/sandbox/run.sh` and `scripts/eval/run.sh` being the two. Cost alone is not an answer, since authorizing a spend is the operator's and performing the run is not. A refusal the author actually met is an answer, and it names which one.
|
|
89
89
|
|
|
90
|
+
Test every ticked box too, bounded to one naming a file or a command. Confirm what it names still exists at `<headRefOid>`, `git show <headRefOid>:<path>` for a file or `git grep <command> <headRefOid>` for a command, rather than re-running what it claims. A box naming neither stays untested, since nothing here can confirm a claim carrying no artifact. A box ticked before a later commit removed or replaced what it names is a `should-fix` finding on the body itself, filed under a `**PR body**` block ahead of the file blocks, since what it corrupts is the merge record rather than a file in the diff.
|
|
91
|
+
|
|
90
92
|
Ask rather than grade. Whether a human is genuinely required is a reading the branch author may hold a reason this session cannot see, so the question carries no severity and enters no count. What it does carry is the heading and the dispatch, on the rule Step 4 states, because a question the author never receives corrects nothing and the author is the only party who can answer it. Answering it closes it, and the answer may be that the requirement holds.
|
|
91
93
|
|
|
92
94
|
Read `## For the reviewer` the same way, bounded to the bullets under that heading rather than the Summary or the Technical Context around it. Those two carry the author's argument for the change, and reading them while judging it is most of what an independent pass exists to avoid, so the read stops at the section itself.
|
|
@@ -140,6 +142,8 @@ X critical, Y should-fix, Z minor. Reviewed against project docs and the board.
|
|
|
140
142
|
🤖 Reviewed by Claude Code
|
|
141
143
|
```
|
|
142
144
|
|
|
145
|
+
A stale ticked box goes in a `**PR body**` block, in place of a `**`path/to/file.ext`**` block and ahead of every one of those, since it precedes the code the diff carries rather than sitting inside it.
|
|
146
|
+
|
|
143
147
|
A later pass carrying findings keeps that shape and changes only the summary line:
|
|
144
148
|
|
|
145
149
|
```markdown
|
|
@@ -11,6 +11,8 @@ Without this skill, an edit made after a pull request is already open ships as a
|
|
|
11
11
|
|
|
12
12
|
A caller that rebased the branch before handing over hits a rejected push, since the tracking branch no longer reaches the head. A branch entered through a worktree hits the opposite shape, carrying an open pull request with no tracking ref at all, which read as a branch that had never been pushed.
|
|
13
13
|
|
|
14
|
+
A fix commit answering a review is the sharpest case of the first paragraph, since it always changes what shipped. The routing that once picked whether to sync the body keyed off the same branch that decides whether to reply, so reaching `reply-owned` or a nonzero comment count meant the sync never ran at all. The description a merge record carries was true when the pull request opened and false by the time review finished, with nothing between the two that read it back.
|
|
15
|
+
|
|
14
16
|
## Must
|
|
15
17
|
|
|
16
18
|
- Refuse unless the branch has an open pull request, since every later step addresses it
|
|
@@ -8,7 +8,7 @@ description: Ships a small self-review edit on the current PR branch by staging,
|
|
|
8
8
|
Ship a small self-review edit on the current PR branch in one pass.
|
|
9
9
|
|
|
10
10
|
When invoked with `reply-owned`, a caller such as `claude-address-review` posts
|
|
11
|
-
its own reply, so skip the comment in step
|
|
11
|
+
its own reply, so skip the comment in step 7. The push and body sync still run.
|
|
12
12
|
|
|
13
13
|
## Guards
|
|
14
14
|
|
|
@@ -30,10 +30,14 @@ A missing tracking ref is no longer a guard. An open pull request proves the bra
|
|
|
30
30
|
The lease is what stops the force from overwriting a commit this session never read. Run the ancestry test only where an upstream resolves, since it reads `@{u}`.
|
|
31
31
|
|
|
32
32
|
5. Check for existing review comments: `gh api 'repos/{owner}/{repo}/pulls/<number>/comments' --jq 'length'`, resolving `<number>` from `gh pr view --json number`.
|
|
33
|
-
6.
|
|
34
|
-
-
|
|
33
|
+
6. Sync the body and title on every invocation, before the routing below decides on the reply.
|
|
34
|
+
- Run `gh pr view --json url,title,body` and update the body with `gh pr edit --body` when the new commit changes scope, and the title with `gh pr edit --title` when the scope shifted enough to make it inaccurate.
|
|
35
|
+
- A fix commit answering a review changes what shipped exactly as much as an ordinary followup does, so the sync cannot wait on the invocation or the comment count below.
|
|
36
|
+
- A body a person edited by hand between rounds gets no special handling: judge it against the tree the same way regardless of who wrote it last, since a hand-edit the fix commit has made stale is the exact drift this sync exists to close.
|
|
37
|
+
7. Route on the invocation and the comment count for the reply alone.
|
|
38
|
+
- When invoked with `reply-owned`, skip this step: the caller posts its own reply.
|
|
35
39
|
- Otherwise, if the count is above zero, the followup addresses review feedback: post a one-line summary of the fix with `gh pr comment --body`, first running the scan in `${CLAUDE_SKILL_DIR}/../../standards/publish.md` against it, since the hook does not see an inline comment body.
|
|
36
|
-
- If it is zero,
|
|
40
|
+
- If it is zero, nothing further runs. The sync in step 6 already did this branch's job.
|
|
37
41
|
|
|
38
42
|
## After completion
|
|
39
43
|
|
package/package.json
CHANGED
package/standards/pr.md
CHANGED
|
@@ -51,6 +51,7 @@ Does not govern:
|
|
|
51
51
|
- Run the check before writing its line. A `- [ ]` reports a check that has not run rather than one that is planned.
|
|
52
52
|
- Tick the box and state the observed result. `- [x] npm test passes, 42 tests` beats `- [ ] run npm test`.
|
|
53
53
|
- Quote the count or output the run reported, never a figure carried from elsewhere.
|
|
54
|
+
- A ticked box describes the tree as it stands, not as it stood when it was written. A later commit that removes or replaces what it names makes the box false, and the branch that made that commit corrects it in the same pass, the same as any other stale claim in the body.
|
|
54
55
|
- Leave a box unchecked only when a human is required, and name which human and why on the same line.
|
|
55
56
|
- Human-only covers visual or aesthetic judgment, anything needing credentials or a live third-party service, anything needing a second machine or a fresh OS, and judgment about whether a boundary or an abstraction reads correctly. The agent runs everything else.
|
|
56
57
|
- What makes a human required is a capability the agent lacks, never the cost of the run. Authorizing a spend is the operator's and performing the run is not, so an arm the repository ships a harness for gets driven once the operator has cleared the spend, and the box records what it returned.
|