Index of every page on this site: llms.txt
All skills
composio-community avatar

/reflecting-on-sessions

@c511c77
Run it yourself

Use when completing a plan, finishing a development branch, wrapping up a session, or at any natural transition between work phases — reviews skill-bus telemetry to identify subscription gaps and suggest improvements

  • 1 file
  • 2.2 KB
  • Updated 9 months ago
  • GitHub
Use this Skill: https://skilld.dev/gh/composio-community/awesome-claude-plugins/reflecting-on-sessions

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈61 tokens for metadata: the name and description. ≈504 when used: this file.

Description uses 3.0% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈241 characters, or 3.0%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

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: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No third-party reports yet.

Signed by skilld at c511c77. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last week.

Activeupdated 9 months ago

README badge

README badge for composio-community/awesome-claude-plugins/reflecting-on-sessions