architect
Research-backed evolution advice for your knowledge system. Analyzes health reports, friction patterns, and derivation history to propose specific changes with research justification. Never auto-implements — proposals require your approval.
npx skills add majiayu000/claude-skill-registry --skill architect-lopewale-dev-ignition --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Analyzes health reports, friction patterns, and derivation history to propose specific changes with research justification. Never auto-implements — proposals require your approval.
How it works
The skill defines a seven-phase workflow:
- Locate system files and detect platform; 2) Read derivation to understand initial design intent; 3) Analyze health data and derive FAIL/WARN evidence if present or perform a live health check; 4) Scan for friction across surfaces and compile a friction inventory; 5) Consult a set of research references to ground claims; 6) Generate 3-5 ranked recommendations with full evidence chains; 7) Present to user and await approval before any modification.
Phases use explicit commands and file checks such as reading ops/derivation.md, ops/config.yaml, ops/health/, ops/observations/, ops/methodology/, vocabulary notes, and various mcp__qmd__ tools to search and query knowledge.
The execution begins with target parsing: if a specific area is named, focus there; if empty, analyze all dimensions; if --dry-run, perform analysis without offering implementation. Then it proceeds through the seven phases sequentially.
When to use it
Use when you want evidence-based evolution recommendations for a knowledge system and you require explicit human approval before applying changes. It is intended for analyzing health, friction, and derivation history to propose concrete changes with research justification.
What it can touch
The workflow references and generates changes to system configuration and knowledge structures. It relies on tools listed in the frontmatter such as Read, Write, Edit, Grep, Glob, Bash, and several mcp__qmd__ commands to perform deep search, vector search, and multi-get operations. It specifies that recommendations require user approval before any files are modified.
Caveats
Never auto-implements. Proposals require explicit user approval before any files are modified. Recommendations are grounded in a seven-phase process leveraging derivation, health data, friction inventory, and research references; outcomes dependent on user validation.
## Runtime Configuration (Step 0 — before any processing) Read these files to configure domain-specific behavior: 1. **`ops/derivation-manifest.md`** — vocabulary mapping, platform hints - Use `vocabulary.notes` for the notes folder name - Use `vocabulary.note` / `vocabulary.note_plural` for note type references - Use `vocabulary.topic_map` / `vocabulary.topic_map_plural` for MOC references - Use `vocabulary.inbox` for the inbox folder name - Use `vocabulary.cmd_reflect` for connection-finding command name - Use `vocabulary.cmd_reweave` for backward-pass command name - Use `vocabulary.cmd_verify` for verification command name - Use `vocabulary.architect` for the command name in output 2. **`ops/config.yaml`** — processing depth, pipeline chaining, automation settings 3. **`ops/derivation.md`** — original derivation record (the design intent baseline) If these files don't exist, use universal defaults and warn the user. --- ## EXECUTE NOW **Target: $ARGUMENTS** Parse immediately: - If target names a specific area (e.g., "schema", "processing", "MOC structure"): focus analysis on that area - If target is empty: run full-system analysis across all dimensions - If target is `--dry-run`
- Runtime Configuration (Step 0 — before any processing)
- EXECUTE NOW
- Philosophy
- PHASE 1: Locate
- PHASE 2: Read Derivation
- PHASE 3: Health Analysis
- PHASE 4: Read Friction
- 4a. Observation Notes
- 4b. Methodology Notes
- 4c. Session Logs
- 4d. Self Space
- 4e. Build Friction Inventory
- PHASE 5: Consult Research
- Research Matching Process
Find health reports from the last 7 days
find ops/health/ -name "*.md" -mtime -7 2>/dev/null | sort -r | head -1
Count total notes
Find orphans (notes with no incoming links)
for f in {vocabulary.notes}/*.md; do
done
Find dangling links
grep -ohP '\[\[([^\]]+)\]\]' {vocabulary.notes}/*.md | sort -u | while read -r link; do
Count inbox items
MOC sizesWhat does the architect skill do?
Research-backed evolution advice for your knowledge system. Analyzes health reports, friction patterns, and derivation history to propose specific changes with research justification. Never auto-implements — proposals require your approval.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill architect-lopewale-dev-ignition --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.