chore(skills): add self-improving devflow skill#1288
Open
markturansky wants to merge 1 commit intoalphafrom
Open
chore(skills): add self-improving devflow skill#1288markturansky wants to merge 1 commit intoalphafrom
markturansky wants to merge 1 commit intoalphafrom
Conversation
Establishes the end-to-end development workflow as a Claude skill: ticket → branch → spec → PR → review → code → deploy → verify. Seeded Known Pitfalls from existing context files and guide lessons. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
Contributor
📝 WalkthroughWalkthroughAdded a new skill documentation file that outlines the complete development workflow for the Ambient Code Platform, including ticket/branch setup, implementation phases, component-specific build/test commands, known pitfalls with corrections, and a self-improving log section with turn-counter reminders. Changes
🚥 Pre-merge checks | ✅ 6✅ Passed checks (6 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
✨ Simplify code
Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Actionable comments posted: 2
🧹 Nitpick comments (1)
.claude/skills/devflow/SKILL.md (1)
334-340: Strengthen--no-verifyguidance with a required follow-up.Line 338 is useful as an escape hatch, but without a required follow-up it can normalize skipping quality gates.
Proposed edit
git commit --no-verify # skip pre-commit hooks (use sparingly)-But prefer fixing the lint/format issue instead.
+If used, run the equivalent checks manually before push and fix failures immediately.
+But prefer fixing the lint/format issue instead.</details> <details> <summary>🤖 Prompt for AI Agents</summary>Verify each finding against the current code and only fix it if needed.
In @.claude/skills/devflow/SKILL.md around lines 334 - 340, Update the
"Pre-commit Hooks" guidance to strengthen the--no-verifyescape hatch: after
mentioninggit commit --no-verify, add a required follow-up sentence
instructing the developer to run the equivalent pre-commit checks manually
(e.g., the same linters/formatters from .pre-commit-config.yaml) before pushing
and to fix any failures immediately; keep the existing "But prefer fixing the
lint/format issue instead." line afterward.</details> </blockquote></details> </blockquote></details> <details> <summary>🤖 Prompt for all review comments with AI agents</summary>Verify each finding against the current code and only fix it if needed.
Inline comments:
In @.claude/skills/devflow/SKILL.md:
- Around line 34-50: The fenced workflow block starting at the list of steps
should include a language tag to satisfy markdown linting; update the
triple-backtick fence that encloses the numbered steps (the fenced workflow
block) to use a language like "text" (e.g., ```text) so the block is explicitly
typed and renders consistently.- Around line 187-196: Replace the "TBD" steps under "5b. Update GitOps
Repository" and "5c. Verify Deployment" with concrete commands and process: use
skopeo inspect to obtain the immutable image digest (reference skopeo inspect
and jq to extract .Digest), update the GitOps manifests to pin the image as
@sha256:, commit the change and open/merge a PR; after merge, verify
rollout by running kubectl -n ambient-code get deploy,pods and kubectl -n
ambient-code rollout status deploy/ambient-api-server --timeout=120s, perform
quick smoke checks and then run the component/e2e test commands referenced in
this skill's quick reference.
Nitpick comments:
In @.claude/skills/devflow/SKILL.md:
- Around line 334-340: Update the "Pre-commit Hooks" guidance to strengthen the
--no-verifyescape hatch: after mentioninggit commit --no-verify, add a
required follow-up sentence instructing the developer to run the equivalent
pre-commit checks manually (e.g., the same linters/formatters from
.pre-commit-config.yaml) before pushing and to fix any failures immediately;
keep the existing "But prefer fixing the lint/format issue instead." line
afterward.</details> <details> <summary>🪄 Autofix (Beta)</summary> Fix all unresolved CodeRabbit comments on this PR: - [ ] <!-- {"checkboxId": "4b0d0e0a-96d7-4f10-b296-3a18ea78f0b9"} --> Push a commit to this branch (recommended) - [ ] <!-- {"checkboxId": "ff5b1114-7d8c-49e6-8ac1-43f82af23a33"} --> Create a new PR with the fixes </details> --- <details> <summary>ℹ️ Review info</summary> <details> <summary>⚙️ Run configuration</summary> **Configuration used**: Path: .coderabbit.yaml **Review profile**: CHILL **Plan**: Pro **Run ID**: `75e38c71-9a5a-4f83-8ebb-3d24b789f821` </details> <details> <summary>📥 Commits</summary> Reviewing files that changed from the base of the PR and between 23002c1dc85b7b0d0c25c60cf261b754a5183ea8 and bab5e8704feab4f63d71d96a49efd1bf90df8995. </details> <details> <summary>📒 Files selected for processing (1)</summary> * `.claude/skills/devflow/SKILL.md` </details> </details> <!-- This is an auto-generated comment by CodeRabbit for review status -->
Comment on lines
+34
to
+50
| ``` | ||
| 1. Ticket (optional) | ||
| 2. Branch (from ticket name if available) | ||
| 3. Spec change (load + modify the component's .spec.md) | ||
| 4. Commit spec → push → PR against `alpha` | ||
| 5. Review (agentic: thorough PR review; human: desired but optional) | ||
| 6. On spec acceptance → load the component's .guide.md (the implementation workflow) | ||
| 7. Branch (from ticket name if available) | ||
| 8. Commit order: | ||
| a. Guide/skill/workflow self-improvement changes (1 commit) | ||
| b. Code changes grouped by component | ||
| 9. Push → PR against `alpha` | ||
| 10. Review (human + bot comments; local review too) | ||
| 11. On merge → await quay.io image | ||
| 12. Update gitops repository with new image SHA (Skill TBD) | ||
| 13. After deployment → run tests / e2e suite (TBD) | ||
| ``` |
Contributor
There was a problem hiding this comment.
Add a language to the fenced workflow block.
Line 34 uses a fenced code block without a language tag, which trips markdown lint and reduces rendering consistency.
Proposed edit
-```
+```text
1. Ticket (optional)
2. Branch (from ticket name if available)
...
13. After deployment → run tests / e2e suite (TBD)</details>
<!-- suggestion_start -->
<details>
<summary>📝 Committable suggestion</summary>
> ‼️ **IMPORTANT**
> Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
```suggestion
🧰 Tools
🪛 markdownlint-cli2 (0.22.0)
[warning] 34-34: Fenced code blocks should have a language specified
(MD040, fenced-code-language)
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In @.claude/skills/devflow/SKILL.md around lines 34 - 50, The fenced workflow
block starting at the list of steps should include a language tag to satisfy
markdown linting; update the triple-backtick fence that encloses the numbered
steps (the fenced workflow block) to use a language like "text" (e.g., ```text)
so the block is explicitly typed and renders consistently.
Comment on lines
+187
to
+196
| ### 5b. Update GitOps Repository | ||
|
|
||
| > **Skill TBD.** This step will be formalized as experience accumulates. | ||
|
|
||
| Get the image SHA from quay.io and update the gitops repository's image references. Due to lack of autodeploy, this is a manual step. | ||
|
|
||
| ### 5c. Verify Deployment | ||
|
|
||
| After deployment, run all available tests. E2E test suite TBD. | ||
|
|
Contributor
There was a problem hiding this comment.
Deployment section is still non-executable for an “end-to-end” skill.
Lines 187–196 leave GitOps update and post-deploy verification as TBD. That creates a real reliability gap in the documented workflow and can leave changes unverified in practice.
Proposed edit
### 5b. Update GitOps Repository
-> **Skill TBD.** This step will be formalized as experience accumulates.
-
-Get the image SHA from quay.io and update the gitops repository's image references. Due to lack of autodeploy, this is a manual step.
+Get the image digest from quay and update image references in the gitops repo in a dedicated commit:
+```bash
+# Example: capture immutable digest from the built tag
+skopeo inspect docker://quay.io/ambient_code/vteam_api_server:<sha-or-tag> | jq -r '.Digest'
+# Update gitops manifests to use `@sha256`:<digest>, commit, open PR, merge
+```
### 5c. Verify Deployment
-After deployment, run all available tests. E2E test suite TBD.
+After deployment, run smoke checks first, then full tests:
+```bash
+kubectl -n ambient-code get deploy,pods
+kubectl -n ambient-code rollout status deploy/ambient-api-server --timeout=120s
+# Then run component test commands from this skill's quick reference
+```📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| ### 5b. Update GitOps Repository | |
| > **Skill TBD.** This step will be formalized as experience accumulates. | |
| Get the image SHA from quay.io and update the gitops repository's image references. Due to lack of autodeploy, this is a manual step. | |
| ### 5c. Verify Deployment | |
| After deployment, run all available tests. E2E test suite TBD. | |
| ### 5b. Update GitOps Repository | |
| Get the image digest from quay and update image references in the gitops repo in a dedicated commit: |
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In @.claude/skills/devflow/SKILL.md around lines 187 - 196, Replace the "TBD"
steps under "5b. Update GitOps Repository" and "5c. Verify Deployment" with
concrete commands and process: use skopeo inspect to obtain the immutable image
digest (reference skopeo inspect and jq to extract .Digest), update the GitOps
manifests to pin the image as `@sha256`:<digest>, commit the change and open/merge
a PR; after merge, verify rollout by running kubectl -n ambient-code get
deploy,pods and kubectl -n ambient-code rollout status deploy/ambient-api-server
--timeout=120s, perform quick smoke checks and then run the component/e2e test
commands referenced in this skill's quick reference.
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
.claude/skills/devflow/SKILL.md— the end-to-end development workflow skill covering ticket → branch → spec → PR → review → code → deploy → verify.Test plan
@.claude/skills/devflowand walk through a small code change to validate the workflow steps🤖 Generated with Claude Code
Summary by CodeRabbit