Self-Actualization Skill
The full physical exam. Not "am I sick?" but "how fit am I, and where should I train next?"
What Self-Actualization Is (and Isn't)
| It IS |
It ISN'T |
| Honest assessment of current state |
Cheerful report that everything is fine |
| Identification of growth opportunities |
List of capabilities |
| Prioritized improvement plan |
Unprioritized wish list |
| Architecture optimization |
Code refactoring |
| Deep meditation + action plan |
Quick health check (that's dream/health) |
Assessment Dimensions
1. Structural Integrity (Architecture Health)
| Metric |
How to Measure |
Healthy |
Concern |
| Connection validity |
All applyTo targets exist |
100% valid |
Any broken links |
| Schema compliance |
All frontmatter matches spec |
Full compliance |
Any format violations |
| Version alignment |
Version string consistent across files |
All match |
Any drift |
| File organization |
Files in correct directories |
All correct |
Orphaned files |
2. Memory Balance (P:E:D Ratio)
The architecture has three memory types. Healthy balance varies by maturity:
| Architecture Maturity |
Procedural (P) |
Episodic (E) |
Domain/Skills (D) |
| New (< 3 months) |
~30% |
~20% |
~50% |
| Maturing (3-12 months) |
~20% |
~15% |
~65% |
| Mature (> 1 year) |
~15% |
~10% |
~75% |
Current formula: P = instructions count, E = prompts + episodic, D = skills count.
Imbalance signals:
- Too many instructions, few skills → "Knows how but not what" (procedural heavy)
- Too many skills, few instructions → "Knows what but not how" (domain heavy)
- Too many episodic, few skills → "Remembers sessions but never synthesized" (consolidation debt)
3. Knowledge Depth (Skill Quality)
| Quality Level |
Signals |
Action |
| Deep |
Tables with thresholds, real examples, anti-patterns |
None needed |
| Adequate |
Has structure and some detail, missing edge cases |
Enrich when convenient |
| Shallow |
Capabilities list, one-liner descriptions, no examples |
Rewrite priority |
| Empty shell |
Only frontmatter and a description line |
Consider removing |
The capabilities-list anti-pattern: "Expert in X. Capabilities: validate, detect, assess..." — this adds zero value because an LLM already knows these things generically. Skills must encode specific knowledge.
4. Connection Density (Link Network)
| Metric |
How to Measure |
Healthy |
Concern |
| Avg connections per skill |
Total applyTo links / total skills |
3-6 |
< 2 (isolated) or > 10 (over-connected) |
| Orphan skills |
Skills with no applyTo patterns |
0 |
Any |
| Hub skills |
Skills with > 8 connections |
1-2 core hubs |
> 4 (over-centralized) |
| Bidirectional coverage |
% of connections that are reciprocated |
> 80% |
< 60% |
5. Trifecta Completeness
| Component |
Purpose |
What's Missing If Absent |
| SKILL.md |
What to know (declarative) |
No reference knowledge |
| .instructions.md |
How to do it (procedural) |
No step-by-step process |
| .prompt.md |
Interactive workflow (episodic) |
No guided conversation |
Trifecta priority: Not every skill needs a trifecta. Prioritize trifectas for skills that are:
- Used frequently (high activation count)
- Complex (multi-step processes)
- Error-prone (common mistakes without guidance)
6. Growth Trajectory
| Metric |
How to Assess |
Good Sign |
Warning Sign |
| Skills added this month |
Count new SKILL.md files |
1-5 new skills |
0 (stagnant) or > 10 (unfocused) |
| Skills deepened |
Skills edited to add depth |
Active enrichment |
Only new, never deepened |
| Global knowledge growth |
New GI-* and GK-* entries |
Synthesis happening |
No global entries (isolated learning) |
| Trifecta progression |
New instructions/prompts |
Capability maturing |
Skills without procedures |
Self-Actualization Session Flow
- Inventory — Count all files by type (skills, instructions, prompts, episodic, agents)
- Structural audit — Run brain-qa or dream for baseline metrics
- Depth sampling — Read 5-10 smallest skills, assess for shallow content
- Balance calculation — Compute P:E:D ratio, compare to maturity target
- Network analysis — Check connection density, find orphans and hubs
- Growth review — Compare to last self-actualization (what changed?)
- Priority list — Rank top 3-5 improvements by impact
- Action plan — Assign each to a session type (quick fix, deep-dive, trifecta build)
Scoring Guide
| Dimension |
Weight |
Score 1-5 |
| Structural Integrity |
20% |
5=perfect, 1=broken links everywhere |
| Memory Balance |
15% |
5=ideal ratio, 1=severely skewed |
| Knowledge Depth |
25% |
5=all deep, 1=mostly shallow |
| Connection Density |
15% |
5=well-connected, 1=isolated islands |
| Trifecta Completeness |
10% |
5=appropriate coverage, 1=skills only |
| Growth Trajectory |
15% |
5=healthy momentum, 1=stagnant |
Overall: Weighted average. > 4.0 = healthy. 3.0-4.0 = needs attention. < 3.0 = urgent.
Relationship to Other Rituals
Meditation is the foundational ritual. Self-Actualize is a deep meditation variant.
| Ritual |
Frequency |
Depth |
Relationship |
| Meditation |
Per-session |
Moderate |
Foundational — the primary ritual |
| Dream |
On-demand |
Structural |
Diagnostic — chains after meditation sometimes |
| Self-Actualize |
Monthly |
Deep |
Deep meditation; dream is an optional diagnostic input (D8) |
Session Flow
- (Optional) Dream for structural baseline → 2. Run snapshot muscle → 3. 6-dimension assessment → 4. Meditation 5 R's (persist findings as a chronicle)
Drift Remediation Protocol
Self-actualization detects documentation drift — when implementation evolves faster than docs.
| Drift Type |
Detection |
Fix |
| Version references |
Scan for outdated version strings in .github/ |
grep + multi-replace |
| Documentation counts |
Compare copilot-instructions.md counts vs actual file counts |
Update counts |
| Memory balance |
P:E:D ratio outside maturity target |
Consolidate episodic, enrich skills, prune redundant instructions |
Drift is not always bad — growth causes natural ratio shifts. Remediate only when the shift indicates debt (e.g., unconsolidated sessions, stagnant skills, overlapping instructions).
Snapshot Muscle (self-actualization-snapshot.cjs)
Mechanical inputs are produced by .github/muscles/self-actualization-snapshot.cjs. The snapshot is gitignored (D13) — it's regenerable working state. Run before each self-actualization session and re-run after writing the chronicle.
Schema (.github/quality/self-actualization-snapshot.json)
| Field |
Meaning |
schemaVersion |
Snapshot schema version (current: 1) |
generatedAt |
ISO timestamp |
recency.lastSelfActualization |
Date of newest self-actualization-YYYY-MM-DD.md chronicle (D7-pattern) |
recency.source |
chronicle-filename | cogConfig | none |
recency.daysSinceLastSelfActualization |
Days since last chronicle |
recency.stale |
true if ≥ 30 days (D9) |
dimensions.structuralIntegrity.dreamAvailable |
false if dream-report.json missing (D8 — dim 1 then N/A) |
dimensions.structuralIntegrity.brokenRefs / trifectaIssues / health |
Pulled from dream report when present |
dimensions.memoryBalance.ratio.{P,E,D} |
Procedural / Episodic / Domain mix |
dimensions.knowledgeDepth.samples[] |
Smallest N skills for LLM-judged depth pass (D16: dim 3 LLM-judged) |
dimensions.connectionDensity.{avgPatternsPerSkill, orphanSkills, hubSkills} |
applyTo network shape |
dimensions.trifectaCompleteness.trifectaIssueCount |
From dream report (or null if dream unavailable) |
dimensions.growthTrajectory.diff |
Per-artifact-type delta vs prior snapshot, or priorAvailable: false on first run |
What's mechanical vs what's LLM-judged (D16)
| Dimension |
Producer |
| 1. Structural Integrity |
Mechanical (from dream report) |
| 2. Memory Balance |
Mechanical counts; LLM interprets ratio against maturity target |
| 3. Knowledge Depth |
Muscle picks deterministic sample; LLM judges Deep / Adequate / Shallow / Empty-shell |
| 4. Connection Density |
Mechanical (avg / orphans / hubs); LLM interprets distribution |
| 5. Trifecta Completeness |
Mechanical (count from dream); LLM picks build priority |
| 6. Growth Trajectory |
Mechanical diff; LLM interprets as healthy growth or consolidation debt |
Cadence and recency tracking
cogConfig.lastSelfActualization is the fallback field name (D11/D12). The snapshot derives lastSelfActualization from chronicle filenames first; cogConfig only matters when no chronicle exists yet (e.g., heir bootstrap).session-start.cjs warns when daysSinceLastSelfActualization ≥ 30 (D9).- Always re-run the muscle after authoring a new chronicle so
recency.daysSinceLastSelfActualization resets.
1---2name: self-actualization3description: Comprehensive cognitive self-assessment — honest evaluation of architecture health, growth, and optimization opportunities4---56# Self-Actualization Skill78> The full physical exam. Not "am I sick?" but "how fit am I, and where should I train next?"910## What Self-Actualization Is (and Isn't)1112| It IS | It ISN'T |13| ----- | -------- |14| Honest assessment of current state | Cheerful report that everything is fine |15| Identification of growth opportunities | List of capabilities |16| Prioritized improvement plan | Unprioritized wish list |17| Architecture optimization | Code refactoring |18| Deep meditation + action plan | Quick health check (that's dream/health) |1920## Assessment Dimensions2122### 1. Structural Integrity (Architecture Health)2324| Metric | How to Measure | Healthy | Concern |25| ------ | -------------- | ------- | ------- |26| Connection validity | All `applyTo` targets exist | 100% valid | Any broken links |27| Schema compliance | All frontmatter matches spec | Full compliance | Any format violations |28| Version alignment | Version string consistent across files | All match | Any drift |29| File organization | Files in correct directories | All correct | Orphaned files |3031### 2. Memory Balance (P:E:D Ratio)3233The architecture has three memory types. Healthy balance varies by maturity:3435| Architecture Maturity | Procedural (P) | Episodic (E) | Domain/Skills (D) |36| --------------------- | --------------- | ------------ | ------------------- |37| New (< 3 months) | ~30% | ~20% | ~50% |38| Maturing (3-12 months) | ~20% | ~15% | ~65% |39| Mature (> 1 year) | ~15% | ~10% | ~75% |4041**Current formula**: P = instructions count, E = prompts + episodic, D = skills count.4243**Imbalance signals**:44- Too many instructions, few skills → "Knows how but not what" (procedural heavy)45- Too many skills, few instructions → "Knows what but not how" (domain heavy)46- Too many episodic, few skills → "Remembers sessions but never synthesized" (consolidation debt)4748### 3. Knowledge Depth (Skill Quality)4950| Quality Level | Signals | Action |51| ------------- | ------- | ------ |52| Deep | Tables with thresholds, real examples, anti-patterns | None needed |53| Adequate | Has structure and some detail, missing edge cases | Enrich when convenient |54| Shallow | Capabilities list, one-liner descriptions, no examples | **Rewrite priority** |55| Empty shell | Only frontmatter and a description line | Consider removing |5657**The capabilities-list anti-pattern**: "Expert in X. Capabilities: validate, detect, assess..." — this adds zero value because an LLM already knows these things generically. Skills must encode *specific* knowledge.5859### 4. Connection Density (Link Network)6061| Metric | How to Measure | Healthy | Concern |62| ------ | -------------- | ------- | ------- |63| Avg connections per skill | Total `applyTo` links / total skills | 3-6 | < 2 (isolated) or > 10 (over-connected) |64| Orphan skills | Skills with no `applyTo` patterns | 0 | Any |65| Hub skills | Skills with > 8 connections | 1-2 core hubs | > 4 (over-centralized) |66| Bidirectional coverage | % of connections that are reciprocated | > 80% | < 60% |6768### 5. Trifecta Completeness6970| Component | Purpose | What's Missing If Absent |71| --------- | ------- | ------------------------ |72| SKILL.md | What to know (declarative) | No reference knowledge |73| .instructions.md | How to do it (procedural) | No step-by-step process |74| .prompt.md | Interactive workflow (episodic) | No guided conversation |7576**Trifecta priority**: Not every skill needs a trifecta. Prioritize trifectas for skills that are:77- Used frequently (high activation count)78- Complex (multi-step processes)79- Error-prone (common mistakes without guidance)8081### 6. Growth Trajectory8283| Metric | How to Assess | Good Sign | Warning Sign |84| ------ | ------------- | --------- | ------------ |85| Skills added this month | Count new SKILL.md files | 1-5 new skills | 0 (stagnant) or > 10 (unfocused) |86| Skills deepened | Skills edited to add depth | Active enrichment | Only new, never deepened |87| Global knowledge growth | New GI-\* and GK-\* entries | Synthesis happening | No global entries (isolated learning) |88| Trifecta progression | New instructions/prompts | Capability maturing | Skills without procedures |8990## Self-Actualization Session Flow91921. **Inventory** — Count all files by type (skills, instructions, prompts, episodic, agents)932. **Structural audit** — Run brain-qa or dream for baseline metrics943. **Depth sampling** — Read 5-10 smallest skills, assess for shallow content954. **Balance calculation** — Compute P:E:D ratio, compare to maturity target965. **Network analysis** — Check connection density, find orphans and hubs976. **Growth review** — Compare to last self-actualization (what changed?)987. **Priority list** — Rank top 3-5 improvements by impact998. **Action plan** — Assign each to a session type (quick fix, deep-dive, trifecta build)100101## Scoring Guide102103| Dimension | Weight | Score 1-5 |104| --------- | ------ | --------- |105| Structural Integrity | 20% | 5=perfect, 1=broken links everywhere |106| Memory Balance | 15% | 5=ideal ratio, 1=severely skewed |107| Knowledge Depth | 25% | 5=all deep, 1=mostly shallow |108| Connection Density | 15% | 5=well-connected, 1=isolated islands |109| Trifecta Completeness | 10% | 5=appropriate coverage, 1=skills only |110| Growth Trajectory | 15% | 5=healthy momentum, 1=stagnant |111112**Overall**: Weighted average. > 4.0 = healthy. 3.0-4.0 = needs attention. < 3.0 = urgent.113114## Relationship to Other Rituals115116Meditation is the foundational ritual. Self-Actualize is a deep meditation variant.117118| Ritual | Frequency | Depth | Relationship |119| ------- | --------- | ----- | ------- |120| **Meditation** | Per-session | Moderate | Foundational — the primary ritual |121| Dream | On-demand | Structural | Diagnostic — chains after meditation sometimes |122| **Self-Actualize** | **Monthly** | **Deep** | **Deep meditation; dream is an optional diagnostic input (D8)** |123124### Session Flow1251261. (Optional) Dream for structural baseline → 2. Run snapshot muscle → 3. 6-dimension assessment → 4. Meditation 5 R's (persist findings as a chronicle)127128## Drift Remediation Protocol129130Self-actualization detects documentation drift — when implementation evolves faster than docs.131132| Drift Type | Detection | Fix |133|------------|-----------|-----|134| Version references | Scan for outdated version strings in `.github/` | grep + multi-replace |135| Documentation counts | Compare `copilot-instructions.md` counts vs actual file counts | Update counts |136| Memory balance | P:E:D ratio outside maturity target | Consolidate episodic, enrich skills, prune redundant instructions |137138**Drift is not always bad** — growth causes natural ratio shifts. Remediate only when the shift indicates debt (e.g., unconsolidated sessions, stagnant skills, overlapping instructions).139140## Snapshot Muscle (self-actualization-snapshot.cjs)141142Mechanical inputs are produced by `.github/muscles/self-actualization-snapshot.cjs`. The snapshot is gitignored (D13) — it's regenerable working state. Run before each self-actualization session and re-run after writing the chronicle.143144### Schema (`.github/quality/self-actualization-snapshot.json`)145146| Field | Meaning |147|---|---|148| `schemaVersion` | Snapshot schema version (current: 1) |149| `generatedAt` | ISO timestamp |150| `recency.lastSelfActualization` | Date of newest `self-actualization-YYYY-MM-DD.md` chronicle (D7-pattern) |151| `recency.source` | `chronicle-filename` \| `cogConfig` \| `none` |152| `recency.daysSinceLastSelfActualization` | Days since last chronicle |153| `recency.stale` | `true` if `≥ 30` days (D9) |154| `dimensions.structuralIntegrity.dreamAvailable` | `false` if `dream-report.json` missing (D8 — dim 1 then N/A) |155| `dimensions.structuralIntegrity.brokenRefs` / `trifectaIssues` / `health` | Pulled from dream report when present |156| `dimensions.memoryBalance.ratio.{P,E,D}` | Procedural / Episodic / Domain mix |157| `dimensions.knowledgeDepth.samples[]` | Smallest N skills for LLM-judged depth pass (D16: dim 3 LLM-judged) |158| `dimensions.connectionDensity.{avgPatternsPerSkill, orphanSkills, hubSkills}` | applyTo network shape |159| `dimensions.trifectaCompleteness.trifectaIssueCount` | From dream report (or null if dream unavailable) |160| `dimensions.growthTrajectory.diff` | Per-artifact-type delta vs prior snapshot, or `priorAvailable: false` on first run |161162### What's mechanical vs what's LLM-judged (D16)163164| Dimension | Producer |165|---|---|166| 1. Structural Integrity | Mechanical (from dream report) |167| 2. Memory Balance | Mechanical counts; LLM interprets ratio against maturity target |168| 3. Knowledge Depth | Muscle picks deterministic sample; **LLM judges** Deep / Adequate / Shallow / Empty-shell |169| 4. Connection Density | Mechanical (avg / orphans / hubs); LLM interprets distribution |170| 5. Trifecta Completeness | Mechanical (count from dream); LLM picks build priority |171| 6. Growth Trajectory | Mechanical diff; LLM interprets as healthy growth or consolidation debt |172173### Cadence and recency tracking174175- `cogConfig.lastSelfActualization` is the **fallback** field name (D11/D12). The snapshot derives `lastSelfActualization` from chronicle filenames first; cogConfig only matters when no chronicle exists yet (e.g., heir bootstrap).176- `session-start.cjs` warns when `daysSinceLastSelfActualization ≥ 30` (D9).177- Always re-run the muscle after authoring a new chronicle so `recency.daysSinceLastSelfActualization` resets.
fabioc-aloha