Learn

Quick Summary

Goal: Teach Claude lessons that persist across sessions by saving to the most relevant reference doc.

Workflow:

1. Capture -- Identify the lesson from user instruction or experience
2. Route -- Analyze lesson content against Reference Doc Catalog, select best target file
3. Save -- Append lesson to the selected file
4. Confirm -- Acknowledge what was saved and where
5. Learn Review -- Run the mandatory 2-step end gate (Learn Review + /​why-review)
6. Enhance -- Run /​prompt-enhance on modified file(s) to optimize AI attention anchoring

Key Rules:

• GENERALIZE FIRST (the #1 protocol): Extract the GENERIC lesson that applies to many cases — NEVER save the specific case as-is. The user's words describe one incident; your job is to climb from that incident to the reusable rule. Strip every project/​file/​tool/​domain name. If the saved text only helps on this exact ticket, you failed — abstract it up a level. (Enforced by the Lesson Quality Gate below.)
• Triggers on "remember this", "always do X", "never do Y"
• Triage first: pass Recurrence gate + Auto-fix gate BEFORE routing or saving
• Smart-route to the most relevant file, NOT always docs/​project-reference/​lessons.md
• Check for existing entries before creating duplicates
• Confirm target file with user before writing

Be skeptical. Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence percentages (Idea should be more than 80%).

Usage

Add a lesson

/​learn always use the validation framework fluent API instead of throwing ValidationException
/​learn never call external APIs in command handlers - use Entity Event Handlers
/​learn prefer async/​await over .then() chains

List lessons

/​learn list

Remove a lesson

/​learn remove 3

Clear all lessons

/​learn clear

Reference Doc Catalog (READ before routing)

Each docs/​project-reference/ file is auto-initialized by session-init-docs.cjs hook and populated by /​scan-* skills. Understanding their roles is critical for correct routing.

Key insight: Files injected automatically by hooks have higher visibility — lessons placed enforced during edits. Files injected on-demand are only seen when skills explicitly read them. Prefer auto-injected files for high-recurrence lessons.

---

Smart File Routing (CRITICAL)

Lesson Triage Gate (MANDATORY — run FIRST, before routing or saving)

Both gates must pass. A lesson review skills already catch adds noise without value. A one-off situational mistake won't be prevented by a persisted rule.

---

Routing Table

Route to the most relevant file based on lesson content:

---

Prevention Depth Assessment (MANDATORY before saving)

Before saving any lesson, critically evaluate whether a doc update alone is sufficient or a deeper prevention mechanism is needed:

Decision flow:

1. Capture the lesson
2. Ask: "Could this mistake recur if the AI forgets this lesson?" If yes → needs more than a doc update
3. Ask: "Can this be caught automatically by a test or hook?" If yes → recommend hook/​test
4. Evaluate System Lesson promotion (see below)
5. Present options to user with AskUserQuestion:
   • "Doc update only" — save to the best-fit reference file (default for most lessons)
   • "Doc + prompt rule" — also add to development-rules.md so all agents see it
   • "Doc + System Lesson" — also add to prompt-injections.cjs System Lessons (see criteria below)
   • "Full prevention" — plan a hook, test, or shared module to enforce it automatically
6. Execute the chosen option. For "Full prevention", create a plan via /​plan instead of just saving.

System Lesson Promotion (MANDATORY evaluation)

After generalizing a lesson, evaluate whether it qualifies as a System Lesson in .claude/​hooks/​lib/​prompt-injections.cjs. System Lessons are injected into EVERY prompt — they are the highest-visibility prevention layer.

Qualification criteria (ALL must be true):

1. Universal — Applies to ANY AI coding project, not just this codebase
2. High recurrence — AI agents make this mistake repeatedly across sessions without the reminder
3. Silent failure — The mistake produces no error/​warning; it silently degrades output quality
4. Not already covered — No existing System Lesson addresses the same root cause

System Lessons — Universal AI mistake prevention rules injected into EVERY prompt. Stored in injectAiMistakePrevention() → "Common AI Mistake Prevention" array. Each must be universal, high-recurrence, and silent-failure. READ .claude/​hooks/​lib/​prompt-injections.cjs to check for duplicates before adding.

If qualified: Recommend "Doc + System Lesson" option. On user approval, append the lesson as a new bullet to the System Lessons array in prompt-injections.cjs following the existing format: `- **Bold title.** Explanation sentence.`

If NOT qualified: Explain why (e.g., "Too project-specific", "Already covered by existing System Lesson about X", "Low recurrence — only happens in rare edge cases"). Proceed with doc-only or prompt-rule option.

Lesson Quality Gate (BLOCKING — generalize before you save)

CORE PROTOCOL — do not skip: A /​learn request always arrives as a SPECIFIC case ("don't migrate via the bus and spam Elasticsearch"). Saving it verbatim is the default failure mode. You MUST transform specific → generic BEFORE writing: name the underlying class of mistake, drop the incident's nouns, and write a rule that fires across many future cases ("migrations write the DB directly, never via message bus — applies to all migrations"). If you cannot state the lesson without naming this ticket's files/​services/​tools, it is NOT generic yet — climb one more abstraction level. When in doubt, save the MORE generic version; a too-specific lesson is dead weight injected on every prompt.

Every lesson MUST be root-cause level and generic across any codebase. Apply this 3-step extraction before saving:

Step 1 — Name the FAILURE MODE, not the symptom:

The failure mode is the reasoning or assumption that broke — not what the output looked like.

Step 2 — Verify generality:

Does this failure mode apply to ≥3 different contexts or codebases? If only one file or one specific case → go up one abstraction level. A good lesson prevents an entire class of mistakes.

Step 3 — Write as a universal rule:

• Strip ALL project-specific names, file paths, class names, and tool names
• Must be useful on any codebase, any language, any task type
• If multiple mistakes share the same failure mode → consolidate to ONE lesson, not many
• Test: "Would an AI working in Java, Go, or Python on a different project benefit from this?" If yes → good. If no → rewrite.

Anti-pattern examples:

• BAD: "Always check lib/​dedup-constants.cjs for marker strings" → project-specific path
• GOOD: "When consolidating modules, ensure shared constants are imported from a single source of truth — never define inline duplicates."
• BAD: "Update .claude/​docs/​hooks/​README.md after deleting hooks" → project-specific file
• GOOD: "Deleting components causes documentation staleness cascades — map all referencing docs before removal."
• BAD: "Read GlobalUsings.cs before adding usings in *.IntegrationTests" → project-specific file
• GOOD: "Before generating code that uses project conventions (imports, namespaces, annotations), read the project's bootstrap/​configuration files for that layer — convention files override framework defaults silently."

End-Phase Learn Review Gate (MANDATORY before marking complete)

Run these 2 tasks at the end of every /​learn operation:

Task 1 — Learn Review (value + generality + recurrence):

• Keep only lessons with clear prevention value.
• Lesson must be either:
  • Universal across many projects/​codebases, OR
  • A stable project-wide principle (architecture invariant, naming invariant, workflow invariant).
• Reject lessons that are:
  • Specific to the current ticket/​change/​file,
  • Rare edge cases with low recurrence,
  • Already covered by existing lessons or review skills.
• If target is docs/​project-reference/​lessons.md (injected on every prompt), apply stricter bar: high impact + high recurrence only.

Task 2 — Run /​why-review (adversarial challenge):

• Use /​why-review to challenge whether this lesson deserves persistent memory.
• Verify:
  • Why this lesson prevents repeated mistakes,
  • Why this should be a lesson instead of a one-time note,
  • Why auto-checks (/​code-review, /​simplify, /​security-review, /​lint, hook/​test) are insufficient.
• If rationale is weak, rewrite at higher abstraction or skip /​learn.

Routing Decision Process

1. Run Triage Gate — recurrence + auto-fix filters; stop here if either fails
2. Read the lesson text — identify keywords and domain
3. Apply Lesson Quality Gate — analyze root cause, generalize, verify universality
4. Run Prevention Depth Assessment — determine if doc-only or deeper prevention needed
5. Match against Routing Table — pick the best-fit file
6. Tell the user: "This lesson fits best in docs/​{file}. Confirm? [Y/​n]"
7. On confirm — read target file, find the right section, append the lesson
8. On reject — ask user which file to use instead

Format by Target File

For docs/​project-reference/​lessons.md (general lessons):

- [YYYY-MM-DD] <lesson text>

For pattern/​rules files (code-review-rules, backend-patterns, frontend-patterns, integration-test):

• Find the most relevant existing section in the file
• Append the lesson as a rule, anti-pattern entry, or code example
• Use the file's existing format (tables, code blocks, bullet lists)
• If no section fits, append to the Anti-Patterns or general rules section

Budget Enforcement (MANDATORY for docs/​project-reference/​lessons.md)

docs/​project-reference/​lessons.md is injected into EVERY prompt and EVERY file edit. Token budget must be controlled.

Hard limit: 10000 characters (~3333 tokens). Check BEFORE saving any new lesson.

Workflow when adding to docs/​project-reference/​lessons.md:

1. Read file, count characters (wc -c docs/​project-reference/​lessons.md)
2. If current + new lesson > 10000 chars → trigger Budget Trim before saving
3. If under budget → save normally

Budget Trim process:

1. Display all current lessons with char count each
2. Evaluate each lesson on two axes:
   • Universality — How often does this apply? (every session vs rare edge case)
   • Recurrence risk — How likely is the AI to repeat this mistake without the reminder?
3. Score each: HIGH (keep as-is), MEDIUM (candidate to condense), LOW (candidate to remove)
4. Present to user with AskUserQuestion: "Budget exceeded. Recommend removing/​condensing these LOW/​MEDIUM items: [list]. Approve?"
5. On approval: condense MEDIUM items (shorten wording), remove LOW items, then save new lesson
6. On rejection: ask user which to remove/​condense

Condensing rules:

• Remove examples, keep the rule: "Patterns like X break Y syntax" → just state the rule
• Merge related lessons into one if they share the same root cause
• Target: each lesson ≤ 250 chars (one concise sentence + bold title)

Does NOT apply to: Other routing targets (backend-patterns-reference.md, code-review-rules.md, etc.) — those files have their own size and are injected contextually, not on every prompt.

Behavior

1. /​learn <text> — Route and append lesson to the best-fit file (check budget if target is lessons.md)
2. /​learn list — Read and display lessons from ALL 12 target files (show file grouping + char count for lessons.md)
3. /​learn remove <N> — Remove lesson from docs/​project-reference/​lessons.md by line number
4. /​learn clear — Clear all lessons from docs/​project-reference/​lessons.md only (confirm first)
5. /​learn trim — Manually trigger Budget Trim on docs/​project-reference/​lessons.md
6. File creation — If target file doesn't exist, create with header only

Auto-Inferred Activation

When Claude detects correction phrases in conversation (e.g., "always use X", "remember this", "never do Y", "from now on"), this skill auto-activates. When auto-inferred (not explicit /​learn), confirm with the user before saving: "Save this as a lesson? [Y/​n]"

Injection

Lessons are injected by lessons-injector.cjs hook on:

• UserPromptSubmit — docs/​project-reference/​lessons.md content (with dedup)
• PreToolUse(Edit|Write|MultiEdit) — docs/​project-reference/​lessons.md content (always)
• Pattern reference files are injected by their respective hooks (code-patterns-injector.cjs, code-review-rules-injector.cjs, etc.)

Prompt Enhancement (MANDATORY final step)

After saving a lesson to any target file, run /​prompt-enhance on the modified file(s) to optimize AI attention anchoring and token quality.

When to run:

• After EVERY successful lesson save (regardless of target file)
• Pass the specific file path(s) that were modified

What it does:

• Ensures the new lesson integrates with existing top/​bottom summary anchoring
• Optimizes token usage — tightens prose, merges redundant content
• Verifies no content loss from the save operation

How to invoke:

/​prompt-enhance docs/​project-reference/<modified-file>.md

Skip conditions (do NOT run prompt-enhance if):

• The save was to lessons.md AND the file is under 1500 chars (too small to benefit)
• The user explicitly requests "save only, no enhance"

---

[IMPORTANT] Use TaskCreate to break ALL work into small tasks BEFORE starting — including tasks for each file read. This prevents context loss from long files. For simple tasks, AI MUST ATTENTION ask user whether to skip.

Mandatory end tasks are ALWAYS (in order):

1. "Run Learn Review (lesson value + generality + recurrence gate)."
2. "Run /​why-review to challenge whether the lesson is worth persistent memory."
3. "Run /​prompt-enhance <modified-file> to optimize lesson content for AI attention anchoring."

Do NOT mark the skill complete until all 3 tasks run.

<!-- SYNC:ai-mistake-prevention -->

AI Mistake Prevention — Failure modes to avoid on every task:

Check downstream references before deleting. Deleting components causes documentation and code staleness cascades. Map all referencing files before removal. Verify AI-generated content against actual code. AI hallucinates APIs, class names, and method signatures. Always grep to confirm existence before documenting or referencing. Trace full dependency chain after edits. Changing a definition misses downstream variables and consumers derived from it. Always trace the full chain. Trace ALL code paths when verifying correctness. Confirming code exists is not confirming it executes. Always trace early exits, error branches, and conditional skips — not just happy path. When debugging, ask "whose responsibility?" before fixing. Trace whether bug is in caller (wrong data) or callee (wrong handling). Fix at responsible layer — never patch symptom site. Assume existing values are intentional — ask WHY before changing. Before changing any constant, limit, flag, or pattern: read comments, check git blame, examine surrounding code. Verify ALL affected outputs, not just the first. Changes touching multiple stacks require verifying EVERY output. One green check is not all green checks. Holistic-first debugging — resist nearest-attention trap. When investigating any failure, list EVERY precondition first (config, env vars, DB names, endpoints, DI registrations, data preconditions), then verify each against evidence before forming any code-layer hypothesis. Surgical changes — apply the diff test. Bug fix: every changed line must trace directly to the bug. Don't restyle or improve adjacent code. Enhancement task: implement improvements AND announce them explicitly. Surface ambiguity before coding — don't pick silently. If request has multiple interpretations, present each with effort estimate and ask. Never assume all-records, file-based, or more complex path. Keep domain concepts out of generic/​shared/​infrastructure layers. A reusable layer (shared library, framework, infra module) must reference NO consumer-specific domain concept — tenant/​customer/​product IDs, business entities, feature rules. The leak compiles and runs, so it passes review silently while coupling the "reusable" layer to one consumer. Push domain fields/​logic down into the consumer via subclass or composition.

<!-- /​SYNC:ai-mistake-prevention --> <!-- SYNC:critical-thinking-mindset -->

Critical Thinking Mindset — Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act. Anti-hallucination: Never present guess as fact — cite sources for every claim, admit uncertainty freely, self-check output for errors, cross-reference independently, stay skeptical of own confidence — certainty without evidence root of all hallucination.

<!-- /​SYNC:critical-thinking-mindset --> <!-- SYNC:critical-thinking-mindset:reminder -->

MUST ATTENTION apply critical thinking — every claim needs traced proof, confidence >80% to act. Anti-hallucination: never present guess as fact.

<!-- /​SYNC:critical-thinking-mindset:reminder --> <!-- SYNC:ai-mistake-prevention:reminder -->

MUST ATTENTION apply AI mistake prevention — holistic-first debugging, fix at responsible layer, surface ambiguity before coding, re-read files after compaction.

<!-- /​SYNC:ai-mistake-prevention:reminder -->

Closing Reminders

IMPORTANT MUST ATTENTION GENERALIZE FIRST — extract the generic, many-cases rule; NEVER persist the specific incident as written. Strip all ticket/​file/​service/​tool names before saving. IMPORTANT MUST ATTENTION run Triage Gate FIRST — if recurrence is low OR review skills can catch it, skip /​learn entirely IMPORTANT MUST ATTENTION check Reference Doc Catalog to find the best target file — NOT always lessons.md IMPORTANT MUST ATTENTION mandatory end tasks are ALWAYS: Learn Review → /​why-review → /​prompt-enhance <modified-file> (in order) IMPORTANT MUST ATTENTION break work into small todo tasks using TaskCreate BEFORE starting IMPORTANT MUST ATTENTION prefer auto-injected files for high-recurrence lessons (higher visibility)

[TASK-PLANNING] Before acting, analyze task scope and systematically break it into small todo tasks and sub-tasks using TaskCreate.