check-ic-activity
Skill94 starsChanged 5 months agoMITView on GitHub
Use this skill whenever the user wants to analyze the activity of an IC or engineer. You have access to a CLI tool that retrieves activity data for an IC from Jira and GitHub.
In this repository15 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- check-boardSkill
- check-epicSkill
- check-issueSkill
- jiraSkill
- mentor-meSkill
- one-on-oneSkill
- plan-initiativeSkill
- us-mappingSkill
- write-epic-buildSkill
- write-epic-technical-discoverySkill
- write-strategySkill
- write-updateSkill
- write-usSkill
- write-visionSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 11
Run this script using the Bash tool:
- Very specific: line 60
Look up the user's github_username and jira_email from data/team_*.csv
- Distinctive: line 61
Run the script with the Bash tool
- Distinctive: line 83
If the individual scores differ, show each metric's score inline next to its value in the report.
- Distinctive: line 135
Prefer interpretation over raw data repetition
- Distinctive: line 137
Do not hallucinate missing data
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Tool
Run this script using the Bash tool:
bash .claude/skills/check-ic-activity/scripts/run_ic_activity.sh <github_username> <jira_email> <from_date> <to_date>github_username: the user's GitHub handle (e.g.jcesarperez-mews)jira_email: the user's Jira email (e.g.julio.perez@mews.com)from_date: start date inYYYY-MM-DDformat (e.g.2026-02-01)to_date: end date inYYYY-MM-DDformat (e.g.2026-02-28)
To resolve github_username and jira_email for a team member, check data/team_*.csv files first.
Date resolution — convert user expressions to from_date and to_date before calling the script. If no time range is specified, default to the last 14 days:
- (no date specified) → FROM = today - 14 days, TO = today
- "last 14 days" → FROM = today - 14 days, TO = today
- "last month" → FROM = first day of previous month, TO = last day of previous month
- "February 2026" → FROM = 2026-02-01, TO = 2026-02-28
- "this week" → FROM = Monday of current week, TO = today
The script outputs JSON metrics (alphabetically sorted, prefixed by category):
{
"col_avg_time_to_first_review_as_reviewer_hours": number,
"col_reviews": number,
"col_reviews_per_week": number,
"del_issue_cycle_time_days": number,
"del_pr_cycle_time_days": number,
"del_commits": number,
"del_commits_per_pr": number,
"del_issues_by_type": { "Bug": number, "Story": number, "Task": number, ... },
"del_issues_completed": number,
"del_issues_per_week": number,
"del_prs_merged": number,
"del_prs_per_week": number,
"del_total_loc": number,
"foc_open_prs": number,
"foc_wip_count": number,
"period_days": number,
"qua_avg_pr_size": number,
"qua_comments_per_pr": number,
"qua_prs_cancelled": number
}Instructions
- Look up the user's
github_usernameandjira_emailfromdata/team_*.csv - Run the script with the Bash tool
- Analyze the returned metrics
- Produce a structured report with scoring and recommendations
Scoring Logic
Delivery
Single metric — score directly:
- del_issues_per_week: High ≥ 6 | Medium 3–5 | Low < 3
Focus
Single metric — score directly:
- foc_wip_count: High ≤ 2 | Medium 3–4 | Low > 4
- Special case: foc_wip_count = 0 is a red flag (⚠️), not a High score. It likely indicates work is not being tracked in Jira. Do not assign a score — flag it instead.
Quality
Score each metric independently, then average (round down to nearest tier):
- qua_avg_pr_size: High < 500 | Medium 500–1000 | Low > 1000
- qua_comments_per_pr: High < 6 | Medium 6–12 | Low > 12
If the individual scores differ, show each metric's score inline next to its value in the report.
Collaboration
Score each metric independently, then average (round down to nearest tier):
- col_reviews_per_week: High ≥ 8 | Medium 4–8 | Low < 4
- col_avg_time_to_first_review_as_reviewer_hours: High < 24h | Medium 24–48h | Low > 48h
If the individual scores differ, show each metric's score inline next to its value in the report.
Return ONLY this format:
IC Activity Report (FROM to TO)
Delivery
- X issues completed (~X.X issues/week)
- X Stories, X Tasks, X Bugs, X Sub-tasks, ...
- Issue cycle time: Xd
- Y PRs merged (~Y.Y PRs/week) — X LOC total
- PR cycle time: Xd
- Score: High | Medium | Low
Current Focus
- Issues in progress (WIP): X ← if 0, show ⚠️ Red flag: no WIP tracked — work may not be linked to Jira issues
- Open PRs: X
- Score: High | Medium | Low ← omit score and show ⚠️ Red flag instead when WIP = 0
Quality
- Avg PR size: X LOC
- Comments per PR: X
- Cancelled PRs: X
- Score: High | Medium | Low
Collaboration
- Reviews given: X (~X.X/week)
- Avg time to first review as reviewer: Xh
- Score: High | Medium | Low
Summary
- 2–3 concise insights about behavior and patterns
Recommendations
- 2–4 actionable, practical suggestions
- Focus on trade-offs (speed vs quality, focus vs multitasking, etc.)
Style Guidelines
- Be concise and direct (engineering manager tone)
- Avoid fluff
- Prefer interpretation over raw data repetition
- Highlight trade-offs, not just metrics
- Do not hallucinate missing data
Example Summary (style reference)
- Consistent delivery with solid throughput
- Slightly high parallel work impacting focus
- Good collaboration habits, responsive to feedback
Example Recommendations (style reference)
- Reduce WIP to improve cycle time
- Aim for smaller PRs to lower rework
- Maintain strong review participation
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
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.

