When should I reflect on a session?

Use this at natural transitions: after a plan, after a development branch, before wrap-up, at pauses between phases, or when asked about skill-bus effectiveness.

What if telemetry is disabled?

Tell the user telemetry is disabled and instruct to set telemetry to true and observeUnmatched to true in the skill-bus config to enable session reflection.

How should I present results?

If there are suggestions, highlight the top 1-2 gaps and offer actions like adding a subscription or running a report; if everything is healthy, state that; if no data, indicate no telemetry data yet.

reflecting-on-sessions

Use Caution

npx machina-cli add skill ComposioHQ/awesome-claude-plugins/reflecting-on-sessions --openclaw

Files (1)

SKILL.md

2.2 KB

Reflecting on Sessions

Announce: "[skill-bus] Reflecting on this session's skill-bus activity."

When to Reflect

This skill is for natural transition moments:

After executing a plan (all tasks complete)
After finishing a development branch
Before session wrap-up or handover
At any natural pause between work phases
When asked about skill-bus effectiveness

Process

Step 1: Check telemetry status

SB_CLI=$(ls ~/.claude/plugins/cache/*/skill-bus/*/lib/cli.py ~/.claude/plugins/repos/skill-bus/lib/cli.py 2>/dev/null | tail -1)
python3 "$SB_CLI" status --cwd "$PWD"

If telemetry is off, tell the user:

"Skill-bus telemetry is disabled for this project. To enable session reflection, add "telemetry": true to your skill-bus config. For full coverage visibility, also add "observeUnmatched": true."

Stop here if telemetry is off.

Step 2: Run stats for this session

SB_CLI=$(ls ~/.claude/plugins/cache/*/skill-bus/*/lib/cli.py ~/.claude/plugins/repos/skill-bus/lib/cli.py 2>/dev/null | tail -1)
python3 "$SB_CLI" stats --cwd "$PWD"

Step 3: Interpret and present

Present the stats output to the user with brief interpretation:

If there are suggestions, highlight the top 1-2:

For uncovered skills: "I noticed [skill] ran N times without any subscription. Would you like to add one? I can run /skill-bus:add-sub."
For condition skips: "[insert] was skipped N times due to conditions. This might mean the condition is too restrictive for your current workflow."

If everything looks healthy (matches > 0, no suggestions):

"Skill-bus is working well this session — N skills intercepted, M inserts injected. No gaps detected."

If no telemetry data:

"No telemetry data for this project yet. Have you invoked any skills this session?"

Step 4: Offer next steps

If there are actionable suggestions:

"Would you like me to run /skill-bus:add-sub for any of these?"
"Run /skill-bus:report anytime to check coverage."

Source

git clone https://github.com/ComposioHQ/awesome-claude-plugins/blob/master/skill-bus/skills/reflecting-on-sessions/SKILL.md

View on GitHub

Overview

Reflecting on Sessions reviews skill-bus telemetry at natural transition moments to identify subscription gaps and suggest improvements. It guides you through checking telemetry, running per-session stats, and surfacing actionable next steps.

How This Skill Works

The skill follows a short four-step flow: check telemetry status with the SB_CLI snippet, run per-session stats using the same SB_CLI, interpret the results to surface top gaps, and propose concrete next steps such as adding subscriptions or generating a report. It emphasizes actionable outcomes and clear messaging for uncovered skills, condition skips, or healthy telemetry.

When to Use It

After executing a plan with all tasks complete
After finishing a development branch
Before session wrap-up or handover
At any natural pause between work phases
When asked about skill-bus effectiveness

Quick Start

Step 1: Check telemetry status with SB_CLI and confirm telemetry is enabled
Step 2: Run per-session stats with SB_CLI to collect current session data
Step 3: Interpret results, highlight top gaps, and propose next steps like adding subscriptions or running a report

Best Practices

Ensure telemetry is enabled and observeUnmatched is true in the skill-bus config for full coverage
Run stats for the current session and focus on the top gaps or skips
Provide concrete, actionable suggestions rather than vague feedback
Keep the reflection concise and oriented toward next actions
Follow up on gaps with add-sub or report commands when appropriate

Example Use Cases

After completing a sprint, reflect on which skills were triggered and if any subscriptions were missing
Following a feature branch merge, check for skipped conditions that may indicate overly strict rules
During project handover, review telemetry to ensure coverage before transitioning teams
During a pause between modules, reassess subscriptions and identify any gaps
When someone asks how well skill-bus performed this session, present the top findings and recommended actions

Frequently Asked Questions

Add this skill to your agents