Reflecting on Sessions
SkillAI & modelsThis skill lets your AI look back at its session telemetry after finishing a piece of work, like completing a plan or wrapping up a development branch. It reviews the stats to find where its skill coverage falls short and suggests improvements. The result is an agent that gets better at spotting its own blind spots over time.
Available today. Use it from your connected AI after setup.
No other account needed.
Add the skill, then let your AI use it whenever you complete a plan, finish a development branch, or wrap up a session. It will review the session telemetry and report any coverage gaps along with suggested improvements.
Then ask your AI: use the Reflecting on Sessions skill
What your AI can do with it
- Review session telemetry stats when a plan, branch, or session wraps up
- Identify gaps in skill coverage from that telemetry
- Suggest improvements to close the gaps it finds
- Run at natural transition points between work phases
What this skill tells your AI
The instructions your AI receives, as published by composio-community/awesome-claude-plugins in skill-bus/skills/reflecting-on-sessions/SKILL.md and read by ahel’s review.
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 "$PWD"
If telemetry is off, tell the user:
"Skill-bus telemetry is disabled for this project. To enable session reflection, add
"telemetry": trueto your skill-bus config. For full coverage visibility, also add"observeUnmatched": true."
Stop here if telemetry is off.
Step 2: Run stats for this session
SB_CLI=$(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-subfor any of these?" - "Run
/skill-bus:reportanytime to check coverage."
Signals
- GitHub stars
- 2k
- Forks
- 606
- Last commit
- Jul 2026
Advanced
- Catalog kind
- skill
- Gateway key
reflecting-on-sessions- Source
- github.com/composio-community/awesome-claude-plugins