Improve agent commands/skills - #359
Merged
Merged
Conversation
Contributor
WalkthroughThis PR updates Claude command, skill, and Docker guideline documentation for container deployment, GitHub workflow analysis, AI model syncing, and container debugging. It also removes obsolete Python PRP command/template files and a credits file section. ChangesDocumentation and command guidance updates
Estimated code review effort: 3 (Moderate) | ~20 minutes Possibly related PRs
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
Contributor
There was a problem hiding this comment.
Actionable comments posted: 5
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In @.claude/commands/implement-container-deployment.md:
- Around line 42-51: The service registration instructions are using the wrong
schema for config-example/docker/myhost/services.yaml; update them to reflect
that categories are nested under the top-level services list rather than as
top-level keys. Adjust the guidance in implement-container-deployment.md so the
service is added under services with the appropriate category grouping, keeping
the existing formatting and category structure used by labctl.py / task
docker:apply.
In @.claude/commands/improve-github-workflows.md:
- Around line 30-36: The gh run list projection in the workflow guidance is
missing startedAt, which the timing analysis depends on. Update the workflow
instructions to include startedAt alongside the existing fields in the gh run
list command, and keep the rest of the timing workflow unchanged so the later
startedAt/completedAt comparison works correctly.
- Line 19: The GitHub CLI guidance here uses an invalid `--limit 3-5` range and
omits `startedAt` from the `gh run list` JSON fields. Update the command
examples in `improve-github-workflows.md` to use a single integer value for
`--limit` (for example, 5) and include `startedAt` in the `--json` list when
timing data is needed. Keep the guidance aligned with the `gh run list` usage
shown in this section and the token-management note.
In @.claude/commands/update-ai-models.md:
- Around line 63-70: The Ollama sync rule in the update-ai-models guide
currently applies the chat model mapping to every ollama-local-* entry, but
embeddings need a separate treatment. Update the config.yaml sync instructions
so chat models still use ollama_chat/<model> and stay one-to-one with the
Taskfile, while nomic-embed-text is called out as a special case that must use
ollama/nomic-embed-text:latest and not be matched to the chat-model rule. Keep
the existing exceptions and references to the ollama-local-* entries, but
explicitly separate embeddings from the chat sync logic.
In @.claude/skills/debug-container-service/SKILL.md:
- Around line 172-176: The downgrade workflow in the skill docs is missing an
explicit image pull before recreating the service, so `scripts/labctl.py service
recreate` may still fail if the pinned tag is not cached. Update the downgrade
instructions around the `service recreate` step to include a pull of the pinned
image first, then recreate the container and continue with the log re-check;
reference the downgrade guidance that mentions setting the service YAML image
tag and running `scripts/labctl.py service recreate`.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
Run ID: f42a1f85-cd8c-481c-9c83-44c8d710efe8
📒 Files selected for processing (10)
.claude/commands/CREDITS.claude/commands/implement-container-deployment.md.claude/commands/implement-python.md.claude/commands/improve-github-workflows.md.claude/commands/plan-container-deployment.md.claude/commands/plan-python.md.claude/commands/update-ai-models.md.claude/skills/debug-container-service/SKILL.mddocker/guidelines.mddocs/PRPs/templates/prp-python.md
💤 Files with no reviewable changes (4)
- .claude/commands/CREDITS
- .claude/commands/plan-python.md
- .claude/commands/implement-python.md
- docs/PRPs/templates/prp-python.md
Contributor
There was a problem hiding this comment.
Actionable comments posted: 1
♻️ Duplicate comments (1)
.claude/skills/debug-container-service/SKILL.md (1)
172-176: 🩺 Stability & Availability | 🟡 Minor | ⚡ Quick winAdd the missing pull before recreate.
service recreatecan still fail on a clean host if the pinned tag is not cached yet. Pull the image first, then recreate and re-check logs.Suggested fix
-**Downgrading:** If a recent update introduced the regression, note the last known-good version, set the image tag in the service YAML back to it, and recreate the container: -```bash -scripts/labctl.py service recreate category/service-name -``` +**Downgrading:** If a recent update introduced the regression, note the last known-good version, set the image tag in the service YAML back to it, pull that image, and recreate the container: +```bash +scripts/labctl.py service pull category/service-name --quiet +scripts/labctl.py service recreate category/service-name +```🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In @.claude/skills/debug-container-service/SKILL.md around lines 172 - 176, The downgrade flow in SKILL.md is missing the image pull step before recreating the service, which can fail on a clean host if the pinned tag is not cached. Update the “Downgrading” instructions to tell users to pin the last known-good image tag in the service YAML, then run the service pull command before calling scripts/labctl.py service recreate, and finally re-check the logs and report that the version was pinned; use the existing “Downgrading” section text so it stays consistent.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In @.claude/commands/implement-container-deployment.md:
- Around line 19-23: Update the container deployment instructions to avoid
copying upstream .env files verbatim: in implement-container-deployment.md, keep
the compose setup reference flow in the section that mentions fetching from a
git repository, but change the guidance around the referenced compose and .env
files so upstream .env files are treated as reference only and any target
example file is regenerated with placeholder values instead of reused unchanged.
Use the existing container deployment wording and the fetch/clone steps as the
anchor, and make sure the instruction explicitly preserves the placeholder-only
rule while still allowing compose files and any additional referenced config
files to be copied as needed.
---
Duplicate comments:
In @.claude/skills/debug-container-service/SKILL.md:
- Around line 172-176: The downgrade flow in SKILL.md is missing the image pull
step before recreating the service, which can fail on a clean host if the pinned
tag is not cached. Update the “Downgrading” instructions to tell users to pin
the last known-good image tag in the service YAML, then run the service pull
command before calling scripts/labctl.py service recreate, and finally re-check
the logs and report that the version was pinned; use the existing “Downgrading”
section text so it stays consistent.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
Run ID: 1df7115c-9950-4763-80f7-47d88eafec5e
📒 Files selected for processing (6)
.claude/commands/implement-container-deployment.md.claude/commands/improve-github-workflows.md.claude/commands/plan-container-deployment.md.claude/commands/update-ai-models.md.claude/skills/debug-container-service/SKILL.mddocker/guidelines.md
✅ Files skipped from review due to trivial changes (1)
- docker/guidelines.md
🚧 Files skipped from review as they are similar to previous changes (2)
- .claude/commands/improve-github-workflows.md
- .claude/commands/plan-container-deployment.md
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary by CodeRabbit
Summary by CodeRabbit
ghconsistently with clearer preflight/token and input parsing.