system-awareness
Manages all other skills by detecting capability gaps, proposing new skills, and keeping the system registry in sync. Use when the user encounters something the system cannot do, wants to log a capability gap, review the skill backlog, propose or build a new skill, analyze recurring unmet needs, or run sync pipelines to update context files (CLAUDE.md, GEMINI.md, AGENTS.md) after skill changes.
What this skill does
# System Awareness - The Self-Evolving Skill Manager
> **Meta-Skill**: This skill manages all other skills. It observes gaps, proposes new capabilities, and helps the system evolve.
---
## Quick Start
### 1. Log a Gap
```bash
python scripts/gap_logger.py "I need to analyze ECG waveforms from images"
python scripts/gap_logger.py \
--request "Analyze ECG images for abnormalities" \
--context "User uploaded 12-lead ECG, wanted automated interpretation" \
--category "medical-imaging" \
--urgency "high"
```
### 2. Analyze Gaps
```bash
python scripts/gap_analyzer.py --list # List all gaps
python scripts/gap_analyzer.py --analyze # Analyze patterns
python scripts/gap_analyzer.py --report # Generate priority report
```
### 3. Build a Skill
```bash
# Propose from a logged gap
python scripts/skill_proposer.py --gap-id "gap_2024_001"
# Build from a proposal (one command does everything)
python scripts/skill_builder.py --proposal ecg-analyzer-proposal.md
# Or build directly from a gap (fast path)
python scripts/skill_builder.py --from-gap gap_xxxx
# Or build directly with name and purpose
python scripts/skill_builder.py --name "ecg-analyzer" --purpose "Analyze ECG images"
```
---
## Gap → Skill Pipeline
```
1. GAP DETECTED
└─► gap_logger.py → gap-log.json
2. GAPS ANALYZED
└─► gap_analyzer.py → patterns, priorities
3. SKILL PROPOSED
└─► skill_proposer.py → skill-templates/*.md
4. HUMAN REVIEW
└─► Approve / reject / modify proposal
5. SKILL BUILT ★
└─► skill_builder.py → skills/[category]/[name]/
├── Creates SKILL.md
├── Creates scripts/ & references/
├── Marks gap as resolved
└── Archives proposal
6. SYSTEM SYNCED (auto-runs)
└─► sync_skills.py → capability-registry.json
7. CONTEXT UPDATED (auto-runs)
└─► generate_context.py → CLAUDE.md, GEMINI.md, AGENTS.md
8. SKILL AVAILABLE ✓
└─► Ready to use in next conversation
```
### Approval Checklist (Step 4)
Before approving a new skill:
- [ ] **Frequency**: Is this needed often enough?
- [ ] **Impact**: Does it unblock important workflows?
- [ ] **Feasibility**: Can we actually build this?
- [ ] **Overlap**: Does an existing skill already do this?
- [ ] **Maintenance**: Can we keep this updated?
### Validation & Error Recovery
After each major step, verify before proceeding:
| Step | Verify | If it fails |
|------|--------|-------------|
| `sync_skills.py --update` | Check registry entry count increased | Re-run with `--dry-run` to inspect conflicts; resolve duplicate IDs manually |
| `generate_context.py --update` | Confirm AUTO-GENERATED markers are present in target files | Ensure markers exist: `<!-- AUTO-GENERATED SKILLS START -->` … `<!-- AUTO-GENERATED SKILLS END -->` |
| `skill_builder.py` | Validate new SKILL.md parses correctly | Check frontmatter for required `name`/`description` fields; re-run builder |
| Registry integrity | Run `python scripts/registry_updater.py --stats` | If count anomaly, diff against previous backup in `data/backups/` |
---
## Sync Architecture
Context files are rebuilt from a single source of truth:
```
skills/cardiology/* skills/scientific/* ...
└──────────────────┬───────────────┘
▼
sync_skills.py
▼
capability-registry.json
▼
generate_context.py
▼
CLAUDE.md GEMINI.md AGENTS.md SKILL-CATALOG.md
```
### Sync Commands
```bash
# Discover new skills
python scripts/sync_skills.py # Report only (dry run)
python scripts/sync_skills.py --update # Add to registry
# Regenerate context files
python scripts/generate_context.py --preview # Preview changes
python scripts/generate_context.py --update # Apply to all context files
# Full pipeline (run after adding any new skill)
python scripts/sync_skills.py --update && python scripts/generate_context.py --update
```
Context files must contain these markers for auto-update:
```markdown
<!-- AUTO-GENERATED SKILLS START -->
... skills content here ...
<!-- AUTO-GENERATED SKILLS END -->
```
### When to Run
- **After adding a new skill**: Run full pipeline
- **Weekly maintenance**: `sync_skills.py` to check for drift
- **Before major sessions**: Ensure registry is current
---
## Gap Detection (For Claude)
Log a gap whenever you encounter an inability, a missing capability, a pointer to an external tool, or repeated user frustration with the same task. When logging, note it in the response:
```
📋 **Gap Logged**: [brief description]
Category: [category] | Urgency: [low/medium/high]
Review gaps with: `python scripts/gap_analyzer.py --list`
```
For full JSON schema, proposal template format, and gap pattern examples, see:
- `references/json-schemas.md` — gap-log.json, capability-registry.json, skill-backlog.json schemas
- `references/proposal-template.md` — new skill proposal format
- `references/gap-patterns.md` — common gap pattern recognition
- `references/skill-anatomy.md` — what makes a good skill
---
## Commands Reference
```bash
# Gap Management
python scripts/gap_logger.py "description" # Log a new gap
python scripts/gap_analyzer.py --list # List all gaps
python scripts/gap_analyzer.py --analyze # Analyze patterns
python scripts/gap_analyzer.py --report # Generate priority report
# Skill Proposals & Building
python scripts/skill_proposer.py --gap-id "id" # Propose from gap
python scripts/skill_proposer.py --interactive # Interactive proposal builder
python scripts/skill_builder.py --list-proposals # See pending proposals
python scripts/skill_builder.py --list-gaps # See open gaps
python scripts/skill_builder.py --proposal FILE # Build from proposal
python scripts/skill_builder.py --from-gap ID # Build from gap (fast path)
python scripts/skill_builder.py --name X --purpose Y # Build directly
python scripts/skill_builder.py --no-sync # Skip auto-sync
# Registry
python scripts/registry_updater.py --scan # Scan for new skills
python scripts/registry_updater.py --stats # Show usage statistics
python scripts/registry_updater.py --unused # Find unused skills
```
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.