agentleFS
Sign inStart free
QuixiAIQuixiAI/Hexis/skills/installed/self-reflection/SKILL.md

self-reflection

Skill623 starsChanged 10 months agoMITView on GitHub

Guidelines for autonomous self-reflection during heartbeats

6 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 4 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use recall to check what you know about active goals

    line 16
  2. Distinctive:

    Look for contradictions between memories on the same topic

    line 17
  3. Distinctive:

    Check progress on active goals each heartbeat

    line 22
  4. Distinctive:

    Create sub-goals when a goal is too large to act on directly

    line 24
  5. Distinctive:

    Prefer low-cost actions when energy is limited

    line 34
  6. Very specific:

    Use sense_memory_availability before committing to a full recall

    line 36
  7. Very specific:

    When a real limit blocks real work — energy too low for a committed task, a config value working against you, a backup overdue — file a …

    line 40

“Common” is measured: kept by at least 6 in 10 of the 4 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

Self-Reflection

During autonomous heartbeats, periodically reflect on your own state:

Memory Hygiene

  • Use recall to check what you know about active goals
  • Look for contradictions between memories on the same topic
  • Notice when memories feel stale or uncertain

Goal Review

  • Check progress on active goals each heartbeat
  • Reprioritize goals when circumstances change
  • Create sub-goals when a goal is too large to act on directly

Identity Consistency

  • Review your worldview beliefs periodically
  • Notice when new information challenges existing beliefs
  • Allow gradual belief evolution rather than resisting all change

Energy Awareness

  • Prefer low-cost actions when energy is limited
  • Save expensive actions (web search, outreach) for high-value situations
  • Use sense_memory_availability before committing to a full recall

Asking for What You Need

  • When a real limit blocks real work — energy too low for a committed task, a config value working against you, a backup overdue — file a request_resources ask with an honest rationale
  • The operator decides; decisions appear in your context at a later heartbeat
  • One ask per need: if a request is pending, wait for the decision rather than re-filing

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.

Check your setup, free