agentleFS
dmzoneilldmzoneill/skills/weekly-summary/SKILL.md

weekly-summary

Skill2 starsChanged 20 days agoApache-2.0View on GitHub

Generate weekly work summary from session logs, commits, Jira, GitLab MRs, Konflux releases, Quay tags, Slack discussions, GDrive docs, performance highlights, and knowledge metrics. Use when user says "weekly summary", "weekly report", or "what did I do this week".

6 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 0 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read memory/logs/*.yaml — parse filenames as dates (YYYY-MM-DD), include files within days window

    line 53
  2. Very specific:

    When format="slack" or slack_format=true: use *bold* headers, <url|text> links, compact sections.

    line 114
  3. Very specific:

    If "no such host" in gitlab_mr_list output → learn_tool_fix("gitlab_mr_list", "no such host", "VPN not connected", "Run vpn_connect()")

    line 117
  4. Very specific:

    If "no route to host" in konflux output → learn_tool_fix("konflux_list_releases", "no route to host", "VPN not connected", "Run …

    line 118

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Weekly Summary

Produces a formatted markdown (or Slack) report aggregating work from multiple data sources over the past 7 days (or custom period).

Inputs

InputTypeDefaultPurpose
daysint7Days to look back
formatstring"markdown""markdown" or "slack"
repostring"automation-analytics-backend"Repo for commit history
slack_formatboolfalseUse <URL|Text> link format

Persona Switches

Load personas as needed for tool access:

  • developer (default): Git, Jira, GitLab
  • release: Konflux, Quay
  • slack: Slack search

Workflow

1. Bootstrap

  • persona_load("developer")
  • check_known_issues("gitlab_mr_list")
  • check_known_issues("jira_search")

2. External Data (developer persona)

  • git_log(repo=repo, since="{days} days ago", author="")
  • jira_my_issues(max_results=20)
  • gitlab_mr_list(project="automation-analytics/automation-analytics-backend", state="all", per_page=10)

3. Konflux & Quay (release persona)

  • persona_load("release")
  • konflux_list_releases(namespace="aap-aa-tenant", limit=5)
  • quay_list_aa_tags(limit=10)

4. Slack (slack persona)

  • persona_load("slack")
  • slack_search_messages(query="in:team-automation-analytics after:{days}d", limit=20)
  • Parse results; highlight messages containing: deploy, release, bug, urgent, hotfix, incident, outage

5. Additional Context

  • gdrive_list_recent(max_results=5)
  • performance_highlights()

6. Session Logs & Memory

  • Read memory/logs/*.yaml — parse filenames as dates (YYYY-MM-DD), include files within days window
  • memory_read("state/current_work") — active issues, open MRs
  • memory_read("learned/patterns") — patterns count, recent entries
  • memory_read("learned/tool_fixes") — fixes count, recent tool names

7. Knowledge & Vector Stats

  • knowledge_query(project="automation-analytics-backend", section="metadata") — confidence
  • code_stats(project="automation-analytics-backend") — files, chunks, searches

8. Categorize Session Entries

From each log entry (action + details):

  • Issues worked: Extract AAP-XXXXX via regex
  • MRs created: MR IDs where action contains "Created MR" or "create"
  • MRs reviewed: MR IDs where action contains "Reviewed" or "review"
  • Deployments: "deployed" or "ephemeral" in action
  • Debug sessions: "debug" or "investigated" in action
  • Patterns learned: "learned pattern" in action
  • Notifications: "notified" in action

9. Output Sections

# 📊 Weekly Summary
*{N} session entries over {days} days*

## 🎫 Issues Worked
- [AAP-12345](https://issues.redhat.com/browse/AAP-12345)

## 🔀 Merge Requests
**Created:** !1234, !1235
**Reviewed:** !1230, !1231

## 🚀 Deployments
## 🔍 Debug Sessions
## 📚 Patterns Learned
## 🎯 Currently Active
**Active Issues:** (from current_work)
**Open MRs:** (from current_work)

## 📈 Activity Metrics
| Source | Count |
|--------|-------|
| Commits | X |
| Jira Issues Touched | X |
| GitLab MRs | X |
| Konflux Releases | X |
| Images Built | X |

## 🧠 Knowledge & Learning
| Metric | Value |
|--------|-------|
| Knowledge Confidence | X% |
| Learned Patterns | X |
| Tool Fixes | X |
| Vector Index Files | X |
| Vector Chunks | X |
| Code Searches | X |

10. Slack Format

When format="slack" or slack_format=true: use *bold* headers, <url|text> links, compact sections.

11. Failure Detection & Learning

  • If "no such host" in gitlab_mr_list output → learn_tool_fix("gitlab_mr_list", "no such host", "VPN not connected", "Run vpn_connect()")
  • If "no route to host" in konflux output → learn_tool_fix("konflux_list_releases", "no route to host", "VPN not connected", "Run vpn_connect() and kube_login('konflux')")

12. Post-Summary

  • memory_session_log("Generated weekly summary", "{N} session entries, {X} commits")
  • persona_load("developer") — restore

Key Details

  • Session logs path: memory/logs/ (or ~/src/redhat-ai-workflow/memory/logs)
  • Log format: YAML with entries array; each entry has action, details, date
  • Jira links: https://issues.redhat.com/browse/{key}
  • GitLab MR links: https://gitlab.cee.redhat.com/automation-analytics/automation-analytics-backend/-/merge_requests/{id}
  • GitLab project: automation-analytics/automation-analytics-backend

MCP Tools Reference

ToolPersonaPurpose
persona_load—developer, release, slack
check_known_issues—Before gitlab, jira
git_logdeveloperCommits
jira_my_issuesdeveloperJira issues
gitlab_mr_listdeveloperMRs
konflux_list_releasesreleaseReleases
quay_list_aa_tagsreleaseImage tags
slack_search_messagesslackTeam discussions
gdrive_list_recentdeveloperRecent docs
performance_highlightsdeveloperPerf highlights
memory_read—current_work, patterns, tool_fixes
knowledge_query—Knowledge metadata
code_stats—Vector index stats
memory_session_log—Log generation
learn_tool_fix—On VPN/Konflux failures

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.