agentleFS
joris887joris887/exosuit/.claude/skills/dashboard/SKILL.md

dashboard

Skill9 starsChanged 3 months agoMITView on GitHub

Sprint status overview with session insights, sprint trends, and actionable next steps.

64 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use activity, telemetry and 9 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • gokite-aiSkill

    activity

    View transaction history and recent account activity. Invoke when the user asks about past spending, wants to verify a payment went through, check if an order completed, review wallet transfers, or see a log of all account actions. Covers wallet transfers, faucet drops, API payments, shopping checkouts, agent registrations, and session approvals.

    Also in 3 projects that use this

  • OpenAISkill

    telemetry

    Add and verify lightweight macOS runtime telemetry. Use when wiring Logger events or inspecting logs for windows, sidebars, menus, and actions.

    Also in 3 projects that use this

  • soilmassSkill

    export

    Animation export configurations including format selection, resolution, framerate, quality, and optimization settings. Use when rendering animations for web, mobile, video, or social media. Provides tokens for all export parameters across Lottie, GIF, video, and sprite sheet formats.

    Also in 4 projects that use this

  • seongjaeryuSkill

    save

    Complete and save your current thinking to Bindly

    Also in 4 projects that use this

  • seongjaeryuSkill

    organize

    Organize knowledge into Sets

    Also in 3 projects that use this

  • admin-remixSkill

    workspace

    Google Workspace administration - manage users, groups, email, Drive, calendars, and devices through natural conversation. Triggers on: Google Workspace, G Suite, user management, group management, admin tasks, offboarding, onboarding, email forwarding, Drive permissions, suspended users, organizational units, ChromeOS devices, audit logs, admin reports.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 2 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 50 edited versions we read keep these.

  • 2

    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:

    Metrics snapshot: Read docs/progress.md → ## Metrics table.

    line 42
  2. Very specific:

    Read docs/reference/BACKLOG_INDEX.md for story counts:

    line 49
  3. Very specific:

    Run the discover-commands micro-component from .claude/prompts/discover-commands.md, then:

    line 56
  4. Very specific:

    Read docs/progress.md → ## Sprint History table.

    line 124
  5. Distinctive:

    Keep output concise — this is a quick status check, not a deep analysis

    line 210
  6. Distinctive:

    Always end with a suggested next action

    line 212

“Common” is measured: kept by at least 6 in 10 of the 50 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

dashboard

Show sprint status overview.

1. Git State

BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
DIRTY=$(git status --porcelain 2>/dev/null | wc -l | tr -d ' ')
AHEAD=$(git rev-list --count origin/$(git symbolic-ref refs/remotes/origin/HEAD 2>/dev/null | sed 's@^refs/remotes/origin/@@' || echo main)..HEAD 2>/dev/null || echo "?")
LAST_COMMIT=$(git log -1 --format="%cr — %s" 2>/dev/null || echo "no commits")

2. Sprint State

# Current sprint from progress.md
SPRINT=$(grep -m1 'Sprint\*\*:' docs/progress.md 2>/dev/null | sed 's/.*: *//' | tr -d ' ')

Sprint spec: Find the current sprint spec file (docs/sprints/sprint-*.md). Read it to extract:

  • Sprint goal (from ## Goal section) — display prominently as the first sprint line
  • Stories table — count by status (🔲 todo, 🔄 in-progress, ✅ done, ⏭️ carried over)
  • Capacity — sessions available vs sessions used (count ✅ stories as sessions consumed based on their Size)
  • Boundaries — out of scope items (brief)

Metrics snapshot: Read docs/progress.md → ## Metrics table. Extract rows that have data (Current column is not "—"). This data is displayed in section 8.

Work item age check: For any story with 🔄 status, check docs/sessions/.activity-log.jsonl for its status-change to in-progress event. Read the current cycle time value from docs/progress.md → ## Metrics table (row "Cycle time (days)", Current column). If available, use this as the average cycle time reference. Fall back to computing from Sprint History if no data. Flag stories in-progress longer than the average:

"⚠️ [Story ID] has been in-progress for [N] days (avg cycle time: [M] days)"

3. Backlog Snapshot

Read docs/reference/BACKLOG_INDEX.md for story counts:

  • Total stories across all epics
  • Done / In Progress / TODO counts
  • Current focus area

4. Test Health

Run the discover-commands micro-component from .claude/prompts/discover-commands.md, then:

<IF condition="test command configured"> ```bash # Run tests and capture summary ``` Report: X passing, Y failing, coverage if available. </IF> <ELSE> Report: "No test command configured" </ELSE>

5. Open PRs

gh pr list --author @me --state open --json number,title,reviewDecision,statusCheckRollup 2>/dev/null || echo "gh not available"

6. Session State

Check for:

  • .failure-state.md — interrupted workflow
  • Latest session-*.md — last handoff date
  • .auto-save.md — last auto-save

7. Framework Health (Quick)

Quick checks (subset of /doctor):

  • Hook scripts exist and are executable
  • At least one formatter available
  • GROUND_RULES.md has content

8. Session Insights

Parse docs/sessions/.activity-log.jsonl (if it exists and has entries) for this session's activity:

# Count entries by tool type
ACTIVITY_LOG="docs/sessions/.activity-log.jsonl"
if [ -f "$ACTIVITY_LOG" ] && [ -s "$ACTIVITY_LOG" ]; then
  # Top 5 most edited files
  grep '"tool":"Edit\|Write"' "$ACTIVITY_LOG" | grep -o '"target":"[^"]*"' | sort | uniq -c | sort -rn | head -5
  # Count edits vs test runs
  EDIT_COUNT=$(grep -c '"tool":"Edit\|Write"' "$ACTIVITY_LOG" 2>/dev/null || echo 0)
  TEST_RUNS=$(grep -c '"test_result"' "$ACTIVITY_LOG" 2>/dev/null || echo 0)
  # Skill invocations
  grep '"type":"skill"' "$ACTIVITY_LOG" | grep -o '"skill":"[^"]*"' | sort | uniq -c | sort -rn | head -5
fi

Present insights (only sections with data):

### Session Insights
- **Most edited:** `src/auth/login.ts` (8 edits), `src/api/users.ts` (5 edits)
- **Edit-to-test ratio:** 12 edits / 3 test runs (ratio: 4.0 — consider running tests more often)
- **Test failures this session:** 2 (both recovered)
- **Skills used:** /story-cycle (3x), /commit (2x), /debug-session (1x)

Edit-to-test ratio guidance:

  • ≤2.0: Good TDD discipline
  • 2.1-5.0: Acceptable, could test more frequently
  • 5.0: TDD drift — many edits between test runs

9. Sprint Trends

<IF condition="docs/progress.md has ≥2 rows in Sprint History table"> Read `docs/progress.md` → `## Sprint History` table. Extract trends:
### Sprint Trends
- **Cycle time:** 2.1 → 1.8 → 1.5 days (improving)
- **Coverage:** 78% → 82% → 84% (improving)
- **Change failure rate:** 15% → 12% → 8% (improving)

Flag any metric that worsened for 2+ consecutive sprints. </IF> <ELSE> Skip this section — not enough sprint data yet. </ELSE>

10. Present Dashboard

## Sprint Dashboard

### Git
- **Branch:** `sprint-N` (X commits ahead, Y uncommitted files)
- **Last commit:** 2 hours ago — "feat(auth): add login endpoint"

### Sprint N: [Sprint Goal]
- **Progress:** 3/5 stories done (2 remaining: E01-004 🔄, E01-005 🔲)
- **Capacity:** ~6/8 sessions used (buffer: 1 session)
- **Out of scope:** [from boundaries]
- ⚠️ E01-004 in-progress for 3 days (avg cycle time: 1.5 days)

### Backlog
- 3 done / 1 in progress / 8 TODO

### Tests
- **Status:** 47 passing, 0 failing
- **Coverage:** 82% (+3% this sprint)

### PRs
- None open

### Session
- **Last handoff:** 2 days ago
- **Interrupted workflow:** None

### Metrics Health
| Metric | Current | Target | Trend | Status |
|:-------|:-------:|:------:|:-----:|:------:|
| Cycle time (days) | 2.1 | ≤3.0 | ▇▆▅▄▃▂ | 🟢 |
| Change failure rate | 12% | ≤15% | ▂▃▂▄▅▃ | 🟡 |
[Show only metrics rows with data — skip rows where Current is "—"]
[If any 🟡/🔴: show sprint note from progress.md]

### Session Insights
- **Most edited:** `src/auth/login.ts` (8 edits)
- **Edit-to-test ratio:** 4.0 (12 edits / 3 test runs)
- **Skills used:** /story-cycle (3x), /commit (2x)

### Sprint Trends
- Cycle time: 2.1 → 1.8 → 1.5 days (improving)
- Coverage: 78% → 82% → 84%

### Framework
- **Health:** All checks passing

### Suggested Next Action
→ `/story-cycle "E01-004"` — Continue with the next backlog story

Suggested Actions Logic

Based on state, suggest the most relevant next action:

StateSuggestion
On main, no sprint/sprint-start
On sprint branch, no story in progress/story-cycle <next-TODO-story>
Story in progress"Continue current story"
Interrupted workflow"Resume with /continue"
Sprint complete, no PR/sprint-end
PR open and approved"Merge PR: gh pr merge --squash"
PR with review feedback"Address feedback on PR #N"
All stories done/sprint-end or /retrospective

Rules

  • This skill is READ-ONLY — no modifications, no side effects
  • Keep output concise — this is a quick status check, not a deep analysis
  • Show only relevant sections — skip sections with no data
  • Always end with a suggested next action

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.