Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when... The skill's requirements and instructions are coherent with
Security
High Risk
Quality
Watch · 68
Install
manual only
Audit version
audit-standard-v2
Source metrics come from upstream registries/repositories. Platform metrics come from user actions on SkillTrust and are protected by dedupe/rate-limit anti-abuse rules.
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when... The skill's requirements and instructions are coherent with its stated purpose: it is an instruction-only, local memory/learning helper that reads and writes a dedicated ~/self-improving/ workspace and may non-destructively update workspace steering files; it requests no credentials or exotic installs. This skill is an instruction-only local memory/learning system and appears to do what it says: create and maintain ~/self-improving/ and update small workspace steering files non-destructively. Before installing or enabling it: (1) Confirm you are comfortable letting the agent read and write files under ~/self-improving/ and make limited edits to AGENTS.md/SOUL.md/HEARTBEAT.md; (2) Back up AGENTS.md and SOUL.md if you want an easy rollback; (3) Note the skill will not request credentials, but it will store user-provided corrections and preferences—review boundaries.md and ensure it meets your privacy expectations; (4) Only allow the optional 'Proactivity' companion to be installed if you review that skill first (it runs a network install); (5) Verify the skill's kill-switch and export/wipe flows work as promised (ask it to export and then to wipe on a test run) and limit file permissions on ~/self-improving/ if you want stricter local access control.
• Add explicit When to Use / Guidelines sections.
• Provide at least one concrete input-output example.
• Publish versioned changelog and update cadence.
• Document compatibility and breaking-change policy.
• Expand capability limits and boundary conditions.
Is this a security certification?
No. SkillTrust audit is advisory and should be combined with your own review controls.
Can I install directly from this page?
No one-click install is provided. Use command guidance and run in your controlled environment.
Clarifies the setup flow for proactive follow-through and safer installation behavior.
Official source did not expose a direct install command.
Open official docsInstall method: instruction-only
Quick install
Quick preflight
Read source docs and verify prerequisites manually.Preflight checks
Post-install signal
Installed successfully? Send an activation signal to improve ranking quality over time.
Audit score 60 / 100. Risk guidance is advisory only; review evidence before install.
• Add troubleshooting and FAQ for common failures.
• Improve discoverability through verified source channels.
• Publish usage examples to increase activation quality.
• Reduce shell/file/network scope and document least privilege.
• Expose explicit provenance, dependency pinning, and security notes.
• Provide structured install + rollback steps for each supported agent.
• Mark official/verified status and keep metadata timestamps fresh.
Updated recently within the last 45 days.
Audit guidance: 60 / 100 · high
Scores with similar values can still differ in confidence; use evidence and risk lines below for final install judgment.
Risk 60 · Δ +0 · Findings 5
Apr 2, 2026 · auto
Latest high risk result from audit-standard-v2.