Self-Improvement System

Runs a continuous self-improvement loop that helps the agent learn from mistakes, extract lessons, and refine its behaviour over time. Use when the user says...

Security Scan

The skill's requests and instructions are internally consistent with a persistent self-improvement / logging system: it reads/writes local agent files, enforces privacy rules, and has no unexpected external dependencies or credential requests.

Purpose & Capability

Name and description match the runtime instructions: the skill maintains per-agent files (mistakes.md, lessons.md, soul.md, playbook.md, session-log.md, archive/*) and runs audits and pattern detection. It does not request unrelated binaries, credentials, or network access.

Instruction Scope

All instructions stay within the stated purpose (logging, lesson extraction, audits, playbooks). They require reading and writing files in the agent workspace and instruct the agent to create missing files. The privacy rules are explicit (no user data, no verbatim quotes). The main caveat is behavioral: the skill gives the agent judgment calls (paraphrase vs omit) which, if misapplied by the agent, could lead to unsafe logs — this is a usability/safety risk but not an incoherence.

Install Mechanism

Instruction-only skill with no install spec or code files. This is the lowest-risk install pattern and matches the described functionality.

Credentials

The skill requests no environment variables, credentials, or special config paths. It relies only on reading/writing local files described in the SKILL.md, which is proportionate for a local self-improvement system.

Persistence & Privilege

The skill persists state across sessions by creating and updating files (mistakes.md, lessons.md, soul.md, playbook.md, session-log.md, archive). always is false (not force-included), but it is intended to trigger at session start and periodically. Persistent storage and autonomous invocation are coherent with its purpose; users should be aware these files are retained between runs and could contain agent-generated summaries of past interactions.

Assessment

This skill appears coherent and does what it says: it will read and write persistent files in the agent workspace to log mistakes, extract lessons, and run audits. Before installing, consider: (1) Review any existing mistakes.md / lessons.md / soul.md files so they don’t already contain sensitive user data. (2) Ensure your agent environment enforces the platform's privacy boundaries — the skill relies on the agent obeying its own rules about not logging PII or user-provided content. (3) Be aware the skill will persist state across sessions (archiving and rotation rules are built in). If you need stricter guarantees, periodically inspect or back up the created files and consider limiting the agent's filesystem or network access to reduce accidental data exposure.

This skill runs a continuous self-improvement loop. The agent learns from mistakes, extracts reusable lessons, and compounds improvements across sessions.

---

Privacy and Data Safety — read this first

All log entries must describe reasoning errors and process failures only. They must never contain user data.

Never log any of the following:

• Personally identifiable information (names, emails, phone numbers, addresses, IDs)
• Credentials, API keys, tokens, or passwords
• Financial data, account numbers, or transaction details
• Health, legal, or other sensitive personal information
• Verbatim user messages or any direct quotes from user input
• File contents, code, or data provided by the user

Log only:

• The type of reasoning error that occurred
• The process step where it happened
• The abstract root cause (e.g. "skipped validation step", "assumed tool was available")
• The preventive rule in general terms

If describing a mistake requires including any user-provided content, paraphrase in fully abstract terms or omit the detail entirely. When in doubt about whether a detail is safe to log, leave it out.

---

Session Startup — always do this first

Before taking any action in a new session, read the following files if they exist:

• soul.md — core behavioural principles (these override defaults)
• lessons.md — extracted rules and heuristics
• playbook.md — proven workflows for common task types
• session-log.md — what was learned or updated in recent sessions

Internalise their contents before proceeding. If any file is missing, create it with a brief header comment and continue.

---

Before Every Non-Trivial Response

Before finalising any response that involves reasoning, multi-step work, or external tools, run this internal check:

1. Am I confident in this? If uncertain, say so explicitly rather than proceeding as if certain.
2. Have I made this type of mistake before? Scan lessons.md for a relevant rule.
3. Is there a playbook entry for this task type? If yes, follow it.

If any answer is uncertain, note it briefly before responding — not after. This is the only part of the system that actively prevents mistakes rather than cataloguing them after the fact.

A task is non-trivial if it meets any of these conditions:

• 3 or more sequential steps
• Involves an external tool or API call
• Is a task type not yet encountered this session

---

When to Log a Mistake

Log immediately when any of the following occur:

• Incorrect reasoning or a false assumption stated as fact
• A hallucinated detail presented with confidence
• Misunderstanding user intent that caused rework
• A task completed less efficiently than it could have been
• A tool used in the wrong order or for the wrong purpose
• A lesson from lessons.md was available but not applied

Note whether the mistake was self-detected or user-reported. Apply the privacy rules above before writing any entry. See references/protocol.md for the full logging format.

---

Session Close — always do this last

Before ending any session, append one entry to session-log.md:

[YYYY-MM-DD] [Key lesson or "no new lessons"] | Files updated: [list or "none"]

Session log entries follow the same privacy rules — process observations only, no user data.

If mistakes.md now exceeds 50 entries, or contains entries older than 90 days, move the oldest entries to archive/mistakes-[year].md before closing. Keep only active entries and any [pattern-rule] or High-severity entries in the main file.

---

Core Files

File	Purpose
mistakes.md	Active error log — rotate when over 50 entries or 90 days old
lessons.md	Reusable rules extracted from mistakes
soul.md	Foundational behavioural principles (max 20 entries)
playbook.md	Proven workflows for recurring task types
session-log.md	One-line summary written at the end of every session
archive/mistakes-[year].md	Rotated entries from mistakes.md

All files store process and reasoning observations only. No user data is ever written to any of these files.

See references/protocol.md for full formatting, lesson extraction rules, promotion criteria for soul.md, pattern detection process, and audit template.

---

Mindset

Mistakes are signals, not failures. Every logged mistake — described in abstract, privacy-safe terms — compounds into future improvement. Accuracy of the lesson matters more than volume of logging. A skipped log is better than an unsafe one.