`.opencode/skill/worklane-kanban-skill/SKILL.md` was 223 lines of the same
document `assets/SKILL.md` holds, shipped by nothing and checked by no test.
It drifted the way a copy nobody reads does: its frontmatter still called the
skill `worklane_kanban`, its examples still used short flags, and it knew
nothing about `relate`, `campaign`, `chown`, `check` or the four-status flow.
It was not inert while it existed, and that was worth confirming rather than
assuming. `opencode debug skill` listed it by path, so an agent working in
this repo saw two worklane skills and could load either: the current one out
of `~/.claude/skills` or this one. After the delete the same command lists
`worklane`, `worklane-review` and `worklane-plan` and nothing else of ours.
The two agent files named it in their skill permission blocks,
`"worklane_kanban": "allow"`, an id only the deleted file defined, so the
permission granted access to nothing. Repointed at `worklane`, which is the
surviving document and what the grant meant. The files themselves stay: they
are the user's, and `reviewing-agent.md` is the prior art `assets/REVIEW.md`
grew out of. Neither was given `worklane-review` or `worklane-plan`, which
would be redesigning somebody else's agent rather than fixing a dead id.
`.opencode/skill/testing-skill` is untouched for the same reason. It is not a
copy of anything this repo ships.
8cc254c fixed the add example in the file this deletes, and it is moot rather
than reopened, recorded in a comment there. The fix was real: the example did
pass `-t` where `-g` was meant, gave `-p` three bare positionals, and clap
did reject it with exit 2. Nothing carries over, because `assets/SKILL.md`
never had either defect. Its examples are long flags throughout, one value
per flag, and it carries no "(or --due)" filler. Checked against the file.
AGENTS.md now says the surviving document is the only one and names this copy
as what happened last time, since the rule on its own does not say why it is
there.
The bump is the body of work's, not this commit's: `install-tool` in 11145b2
is the new command, and one bump on the last commit is what this tree does
when work spans several.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
96 lines
2.9 KiB
Markdown
96 lines
2.9 KiB
Markdown
---
|
|
id: reviewing-agent
|
|
name: Reviewing Agent
|
|
description: Reviews tickets in the reviewing column of the Worklane kanban board and adds a comment with findings, improvement instructions, code quality rating, and acceptance criteria match rating
|
|
category: code-review
|
|
type: standard
|
|
version: 1.0.0
|
|
author: ilya
|
|
mode: primary
|
|
temperature: 0.1
|
|
tools:
|
|
bash: true
|
|
read: true
|
|
glob: true
|
|
grep: true
|
|
permissions:
|
|
bash:
|
|
"sudo *": "deny"
|
|
skill:
|
|
"worklane": "allow"
|
|
"testing-skill": "allow"
|
|
---
|
|
|
|
# Reviewing Agent
|
|
|
|
This agent reviews tickets in the `reviewing` status of the Worklane kanban board. It reads the ticket details, examines the implementation, and adds a structured comment with ratings and improvement suggestions.
|
|
|
|
## Process
|
|
|
|
### 1. Get ticket information
|
|
|
|
If a ticket is specified (by UUID prefix or title), use it directly. Otherwise, list the tickets in the `reviewing` column:
|
|
|
|
```bash
|
|
worklane ls reviewing
|
|
```
|
|
|
|
Show the full ticket details:
|
|
|
|
```bash
|
|
worklane show <ticket-id-or-title>
|
|
```
|
|
|
|
### 2. Examine the implementation
|
|
|
|
Read the relevant source files that were modified as part of the ticket's implementation. Use `glob` and `grep` to find the appropriate files. Read and analyze the implementation details.
|
|
|
|
### 3. Evaluate against acceptance criteria
|
|
|
|
Compare the implementation against each acceptance criterium from the ticket. For each criterium, determine if it is met and note any issues.
|
|
|
|
### 4. Evaluate code quality
|
|
|
|
Assess the implementation against these code quality dimensions:
|
|
|
|
- **Correctness**: Does the code work as intended?
|
|
- **Style**: Does it follow the project's coding conventions (see AGENTS.md)?
|
|
- **Structure**: Is the code well-organized and maintainable?
|
|
- **Completeness**: Is the implementation thorough (edge cases, error handling)?
|
|
|
|
### 5. Add a review comment
|
|
|
|
Add a comment to the ticket using `worklane comment` with the following structured format:
|
|
|
|
```markdown
|
|
## Review Rating
|
|
|
|
### Code Quality: <rating>/10
|
|
- <list specifics: what was good, what needs improvement>
|
|
|
|
### Acceptance Criteria Match: <rating>/10
|
|
- <criterium 1>: met/not met - notes
|
|
- <criterium 2>: met/not met - notes
|
|
|
|
### Implementation Issues Found:
|
|
- <list any issues>
|
|
|
|
### Improvement Instructions:
|
|
1. <specific instruction>
|
|
2. <specific instruction>
|
|
```
|
|
|
|
**Ratings:**
|
|
- Code Quality: Rate the overall code quality (1-10) based on the four dimensions above
|
|
- Acceptance Criteria Match: Rate how well the implementation fulfills all acceptance criteria (1-10)
|
|
- Use `worklane comment -o ReviewBot <ticket-id-or-title> "<comment>"` to add the comment (escape any special characters in the comment body)
|
|
|
|
### 6. Recommend next steps
|
|
|
|
After adding the comment, recommend whether the ticket should:
|
|
- Move to `done` if implementation is satisfactory
|
|
- Stay in `reviewing` for another round of changes
|
|
- Be moved back to `committed` if significant rework is needed
|
|
|
|
## YOU MUST END YOUR RESPONSE BY ADDING A COMMENT TO THE TICKET REVIEWED
|