feat: add daily-summary skill - #909
Conversation
Add skill that generates a repo-grouped standup digest from memsearch activity logs for a given date (defaults to yesterday). Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
|
Warning Review limit reached
Next review available in: 56 minutes Enable usage-based reviews in Billing to review now. Otherwise, wait until the next included review is available. How can I continue?After more reviews become available, a review can be triggered using the To avoid repeated limits, reduce automatic review volume by pausing incremental auto-reviews earlier, using label-based review opt-in, excluding WIP or generated PR titles, or requesting reviews manually when the PR is ready. If your team needs uninterrupted high-volume reviews, an organization admin can enable usage-based reviews. How do review limits work?CodeRabbit enforces per-developer PR review limits for each organization. Most developers receive the normal plan review availability. For paid Pro and Pro+ PR reviews, CodeRabbit uses adaptive limits for sustained high-volume activity. When a developer's recent PR review activity reaches the 95th percentile or higher among CodeRabbit users, additional reviews become available more gradually as earlier reviews age out of the rolling window. Please refer docs for additional details. Review details⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Pro Plus Run ID: 📒 Files selected for processing (2)
📝 WalkthroughWalkthroughAdds a ChangesDaily summary skill
Estimated code review effort: 1 (Trivial) | ~5 minutes Poem
🚥 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 |
✅MegaLinter analysis: Success
Notices📣 MegaLinter 9.5.0 is out! Discover the new features and security recommendations in the release announcement. (Skip this info by defining See detailed reports in MegaLinter artifacts Your project could benefit from a custom flavor, which would allow you to run only the linters you need, and thus improve runtime performances. (Skip this info by defining
|
✅MegaLinter analysis: Success
Notices📣 MegaLinter 9.5.0 is out! Discover the new features and security recommendations in the release announcement. (Skip this info by defining See detailed reports in MegaLinter artifacts Your project could benefit from a custom flavor, which would allow you to run only the linters you need, and thus improve runtime performances. (Skip this info by defining
|
✅
|
| Descriptor | Linter | Files | Fixed | Errors | Warnings | Elapsed time |
|---|---|---|---|---|---|---|
| ✅ ACTION | actionlint | 5 | 0 | 0 | 0.28s | |
| ✅ ACTION | zizmor | 5 | 0 | 0 | 0 | 0.59s |
| ✅ BASH | bash-exec | 5 | 0 | 0 | 0.01s | |
| ✅ BASH | shellcheck | 5 | 0 | 0 | 0.14s | |
| ✅ BASH | shfmt | 5 | 0 | 0 | 0 | 0.02s |
| ✅ COPYPASTE | jscpd | yes | no | no | 0.08s | |
| ✅ EDITORCONFIG | editorconfig-checker | 86 | 0 | 0 | 0.13s | |
| ✅ JSON | prettier | 7 | 0 | 0 | 0 | 0.37s |
| ✅ JSON | v8r | 11 | 0 | 0 | 3.32s | |
| ✅ MARKDOWN | markdownlint | 10 | 0 | 0 | 0 | 0.87s |
| ✅ MARKDOWN | markdown-table-formatter | 12 | 0 | 0 | 0 | 0.21s |
| ✅ REPOSITORY | betterleaks | yes | no | no | 2.27s | |
| ✅ REPOSITORY | checkov | yes | no | no | 23.12s | |
| ✅ REPOSITORY | gitleaks | yes | no | no | 1.39s | |
| ✅ REPOSITORY | git_diff | yes | no | no | 0.01s | |
| ✅ REPOSITORY | grype | yes | no | no | 58.74s | |
| ✅ REPOSITORY | osv-scanner | yes | no | no | 0.21s | |
| ✅ REPOSITORY | secretlint | yes | no | no | 1.25s | |
| ✅ REPOSITORY | syft | yes | no | no | 3.49s | |
| ✅ REPOSITORY | trivy | yes | no | no | 10.51s | |
| ✅ REPOSITORY | trivy-sbom | yes | no | no | 0.19s | |
| ✅ REPOSITORY | trufflehog | yes | no | no | 4.44s | |
| lychee | 35 | 9 | 0 | 1.05s | ||
| ✅ YAML | prettier | 11 | 0 | 0 | 0 | 0.63s |
| ✅ YAML | v8r | 11 | 0 | 0 | 7.16s | |
| ✅ YAML | yamllint | 11 | 0 | 0 | 0.49s |
Detailed Issues
⚠️ SPELL / lychee - 9 errors
📝 Summary
---------------------
🔍 Total...........32
🔗 Unique..........24
✅ Successful......23
⏳ Timeouts.........0
🔀 Redirected.......3
👻 Excluded.........0
❓ Unknown..........0
🚫 Errors...........9
⛔ Unsupported......9
Errors in chezmoi/.chezmoitemplates/mcp_servers.json
[406] https://mcp.deepwiki.com/mcp (at 11:15) | Rejected status code: 406 Not Acceptable
Errors in chezmoi/.chezmoitemplates/opencode.json
[406] https://mcp.deepwiki.com/mcp (at 32:15) | Rejected status code: 406 Not Acceptable
Errors in chezmoi/private_dot_agents/skills/okf/templates/concept.md
[ERROR] file://chezmoi/private_dot_agents/skills/okf/templates/url (at 24:5) | File not found. Check if file exists and path is correct
Errors in chezmoi/private_dot_agents/skills/okf/templates/index.md
[ERROR] file://chezmoi/private_dot_agents/skills/okf/templates/relative-url (at 3:3) | File not found. Check if file exists and path is correct
[ERROR] file://chezmoi/private_dot_agents/skills/okf/templates/relative-url (at 4:3) | File not found. Check if file exists and path is correct
[ERROR] file://chezmoi/private_dot_agents/skills/okf/templates/subdir (at 8:3) | File not found. Check if file exists and path is correct
Errors in chezmoi/private_dot_agents/skills/okf/templates/log.md
[ERROR] file://chezmoi/private_dot_agents/skills/okf/templates/bundle-relative-path (at 5:36) | File not found. Check if file exists and path is correct
[ERROR] file://chezmoi/private_dot_agents/skills/okf/templates/bundle-relative-path (at 6:30) | File not found. Check if file exists and path is correct
[ERROR] file://chezmoi/private_dot_agents/skills/okf/templates/bundle-relative-path (at 7:39) | File not found. Check if file exists and path is correct
Hint: Followed 3 redirects. You might want to consider replacing redirecting URLs with the resolved URLs. Use verbose mode (`-v`/`-vv`) to see redirection details.
Hint: You can configure accepted/rejected response codes with `-a` or `--accept`
Notices
📣 MegaLinter 9.5.0 is out! Discover the new features and security recommendations in the release announcement. (Skip this info by defining SECURITY_SUGGESTIONS: false)
See detailed reports in MegaLinter artifacts
Your project could benefit from a custom flavor, which would allow you to run only the linters you need, and thus improve runtime performances. (Skip this info by defining FLAVOR_SUGGESTIONS: false)
- Documentation: Custom Flavors
- Command:
npx mega-linter-runner@9.6.0 --custom-flavor-setup --custom-flavor-linters ACTION_ACTIONLINT,ACTION_ZIZMOR,BASH_EXEC,BASH_SHELLCHECK,BASH_SHFMT,COPYPASTE_JSCPD,EDITORCONFIG_EDITORCONFIG_CHECKER,JSON_V8R,JSON_PRETTIER,MARKDOWN_MARKDOWNLINT,MARKDOWN_MARKDOWN_TABLE_FORMATTER,REPOSITORY_CHECKOV,REPOSITORY_GIT_DIFF,REPOSITORY_GITLEAKS,REPOSITORY_BETTERLEAKS,REPOSITORY_GRYPE,REPOSITORY_OSV_SCANNER,REPOSITORY_SECRETLINT,REPOSITORY_SYFT,REPOSITORY_TRIVY,REPOSITORY_TRIVY_SBOM,REPOSITORY_TRUFFLEHOG,SPELL_LYCHEE,YAML_PRETTIER,YAML_YAMLLINT,YAML_V8R
Show us your support by starring ⭐ the repository
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request introduces a new agent skill, daily-summary, which generates a daily standup digest from memsearch activity logs grouped by repository, along with a symlink to register the skill. The review feedback highlights two key areas for improvement: adding a fallback grouping (e.g., "Other") for tasks not associated with a specific repository to prevent model confusion, and resolving a contradiction regarding the maximum nesting levels in the output format instructions.
Important
The consumer version of Gemini Code Assist on GitHub is being sunset. Starting June 18, 2026, new organization installations will be blocked, and all code review activity will officially cease on July 17, 2026.
For more details on the timeline and next steps, please review the Help Documentation.
| 3. **Map** — identify every repo mentioned; assign each task to the repo where | ||
| the code change happened. Done when every distinct repo is identified and | ||
| every substantive task is assigned. |
There was a problem hiding this comment.
To prevent the model from getting stuck or hallucinating repository names for tasks that aren't associated with a specific repository, consider adding a fallback grouping (e.g., "Other" or "General"). This ensures the condition "every substantive task is assigned" can always be met.
| 3. **Map** — identify every repo mentioned; assign each task to the repo where | |
| the code change happened. Done when every distinct repo is identified and | |
| every substantive task is assigned. | |
| 3. **Map** — identify every repo mentioned; assign each task to the repo where | |
| the code change happened (or group under "Other" if no specific repo is associated). Done when every distinct repo is identified and | |
| every substantive task is assigned. |
| 4. **Output** the standup in a fenced code block. No preamble. One bullet per | ||
| distinct task. Each bullet ≤10 words. Nest sub-tasks only when they are | ||
| genuinely distinct steps of the parent, not just elaborations. Max 2 levels. | ||
| Skip sessions with no substantive outcome. |
There was a problem hiding this comment.
There is a contradiction between the instruction "Max 2 levels" on line 25 and the provided output template on lines 30-32, which demonstrates 3 levels of nesting:
- <repo-path>(Level 1)- <task>(Level 2)- <sub-task if distinct>(Level 3)
To prevent model confusion and ensure consistent output, please clarify if you mean "Max 2 levels of task nesting (excluding the repo name)" or if the maximum list depth should be updated to 3 levels.
| 4. **Output** the standup in a fenced code block. No preamble. One bullet per | |
| distinct task. Each bullet ≤10 words. Nest sub-tasks only when they are | |
| genuinely distinct steps of the parent, not just elaborations. Max 2 levels. | |
| Skip sessions with no substantive outcome. | |
| 4. **Output** the standup in a fenced code block. No preamble. One bullet per | |
| distinct task. Each bullet ≤10 words. Nest sub-tasks only when they are | |
| genuinely distinct steps of the parent, not just elaborations. Max 3 levels of list nesting (Repo > Task > Sub-task). | |
| Skip sessions with no substantive outcome. |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 3
🤖 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 `@chezmoi/private_dot_agents/skills/daily-summary/SKILL.md`:
- Around line 15-17: Clarify the date selection in the daily-summary
instructions by explicitly defining the timezone used when calculating
“yesterday,” and apply that same timezone to the YYYY-MM-DD value used to load
the memory file.
- Around line 15-17: Update the date-handling step before constructing the
memory path to require an exact, calendar-valid YYYY-MM-DD value, rejecting path
separators and all other malformed input. Only after validation should the load
step read ~/.memsearch/memory/<date>.md, preserving the existing yesterday
default and missing-file behavior.
- Line 5: Update the daily-summary skill’s date argument binding to use
supported Claude Code syntax, such as $ARGUMENTS or a named/positional argument,
so the supplied date reaches the skill. Change the argument hint from
"<YYYY-MM-DD>" to "[YYYY-MM-DD]" only if the date is optional.
🪄 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: Organization UI
Review profile: CHILL
Plan: Pro Plus
Run ID: 93dfe4b0-d3fd-4c92-a065-52854f08f350
📒 Files selected for processing (2)
chezmoi/private_dot_agents/skills/daily-summary/SKILL.mdchezmoi/private_dot_claude/skills/symlink_daily-summary
- Use $ARGUMENTS instead of args for argument binding - Change argument-hint to optional bracket syntax [YYYY-MM-DD] - Add timezone + date validation (calendar-valid YYYY-MM-DD only) - Add Other fallback group for tasks not tied to a repo - Clarify nesting: one level deep only, resolve "max 2 levels" contradiction Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
- Clarify $ARGUMENTS handling: treat absent or empty string as omitted, default to yesterday (fixes empty-arg treated as malformed) - Fix nesting anchor: "under each task" not "under each repo" to match template - Define "substantive outcome" concretely: skip only pure read/search/ investigation sessions with no resulting change or decision - Add daily-summary to README Current plugins list Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
…kills - Remove tautological Map completion criterion - Collapse "if provided and non-empty; treat absent or empty as omitted" to "if non-empty" (same meaning, half the tokens) - Drop "before proceeding" no-op in date step - Drop "identify every repo mentioned" (implied by assign) - Compact Output constraints to one line - Replace session-filter enumeration with leading word "exploration" Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
1 participant
Summary
daily-summaryskill that produces a repo-grouped standup digest from memsearch activity logsYYYY-MM-DDdate argument (defaults to yesterday)disable-model-invocation: true— user-invoked only, zero token cost unless calledprivate_dot_claude/skills/so it's available in Claude Code sessionsTest plan
/daily-summarywith no args → produces yesterday's standup/daily-summary 2026-07-16→ produces that date's standup grouped by repo🤖 Generated with Claude Code
Summary by CodeRabbit
YYYY-MM-DDdate (defaults to yesterday).