Skill

stats

Show ContextStellar scoring statistics, RLM learning progress, and grade distribution for the current project. Use when the user asks about their scoring stats, prompt quality trends, or RLM weight learning.

npx claudepluginhub sunnypatneedi/claude-code-contextstellar

Tool Access

This skill uses the workspace's default tool permissions.

Preview

Show scoring statistics and RLM learning progress for the current project.

SKILL.md

Similar Skills

insights

2.1k

Generates session analytics including learning patterns, correction trends, heatmaps, and productivity metrics from Claude learnings, session history, and git logs. Use for stats, progress reviews, or dashboards.

pro-workflow

dashboard

103

Generates usage analytics dashboard from Claude Code sessions with epistemic protocol coverage metrics, friction analysis, growth timelines, and improvement recommendations.

1 file

epistemic-cooperative

ctx-insight

14.3k

Opens a browser-based analytics dashboard showing personal Claude Code metrics: session activity, tool usage, error rate, parallel work patterns, project focus, and actionable insights. First run installs dependencies (~30s).

context-mode

Stats

Stars0

Forks0

Last CommitMar 10, 2026

Actions

View Source View Plugin View on GitHub View README

Help us improve

Share bugs, ideas, or general feedback.

ContextStellar Stats

Show scoring statistics and RLM learning progress for the current project.

What to do

Check that CONTEXTSTELLAR_API_KEY is set. If not, tell the user to run /contextstellar:setup.

Fetch the shell stats (lightweight summary):

curl -s "${CONTEXTSTELLAR_BASE_URL:-https://contextstellar.com}/api/v1/hooks/shell-stats" \ -H "Authorization: ${CONTEXTSTELLAR_API_KEY}"

If the user wants detailed stats, also fetch the full stats:

curl -s "${CONTEXTSTELLAR_BASE_URL:-https://contextstellar.com}/api/v1/hooks/stats?projectId=${CONTEXTSTELLAR_PROJECT_ID}" \ -H "Authorization: ${CONTEXTSTELLAR_API_KEY}"

Present the results:

Quick Summary (from shell-stats):

Score: {score} ({grade}) {trend arrow}

Success Rate: {successRate}%

RLM Confidence: {rlmConfidence}% ({rlmSamples} samples)

Total Events: {totalEvents}

Detailed View (from full stats, if requested):

Event counts by type (PreToolUse, PostToolUse, Stop)

Grade distribution (A+ through F with counts)

Learned weights vs default weights (show deltas)

Average latency

If RLM confidence is low (< 40%), suggest the user keep using Claude Code to accumulate more samples for better weight learning.

If the average score is below B, suggest running /contextstellar:optimize for improvement tips.

ContextStellar Stats

Show scoring statistics and RLM learning progress for the current project.

What to do

Check that CONTEXTSTELLAR_API_KEY is set. If not, tell the user to run /contextstellar:setup.
Fetch the shell stats (lightweight summary):

curl -s "${CONTEXTSTELLAR_BASE_URL:-https://contextstellar.com}/api/v1/hooks/shell-stats" \
  -H "Authorization: ${CONTEXTSTELLAR_API_KEY}"

If the user wants detailed stats, also fetch the full stats:

curl -s "${CONTEXTSTELLAR_BASE_URL:-https://contextstellar.com}/api/v1/hooks/stats?projectId=${CONTEXTSTELLAR_PROJECT_ID}" \
  -H "Authorization: ${CONTEXTSTELLAR_API_KEY}"

Present the results:

Quick Summary (from shell-stats):

Score: {score} ({grade}) {trend arrow}
Success Rate: {successRate}%
RLM Confidence: {rlmConfidence}% ({rlmSamples} samples)
Total Events: {totalEvents}

Detailed View (from full stats, if requested):

Event counts by type (PreToolUse, PostToolUse, Stop)
Grade distribution (A+ through F with counts)
Learned weights vs default weights (show deltas)
Average latency

If RLM confidence is low (< 40%), suggest the user keep using Claude Code to accumulate more samples for better weight learning.
If the average score is below B, suggest running /contextstellar:optimize for improvement tips.