@vpxa/aikit 0.1.348 → 0.1.350

package/scaffold/dist/definitions/skills/aikit.mjs

@@ -25,7 +25,7 @@ Start:
 6. scope_map({ task }) for non-trivial work.
 
 During:
-- Prefer search/file_summary/compact/digest/symbol/trace/graph over raw reads.
+- Prefer search/file_summary/digest/symbol/trace/graph over raw reads.
 - Use stash for temporary findings; knowledge for durable decisions.
 - Run blast_radius before shared/public edits.
 - Validate with check + relevant test_run.
@@ -46,8 +46,8 @@ End:
 | **L0** | Flow-specific context | \`workflow:<flow>\` briefing card |
 | **L1** | Active flow state | \`knowledge({ action: 'withdraw', scope: 'flow', profile: '<role>' })\` |
 | **L2** | Prior decisions/conventions | \`search\` / \`knowledge\` |
-| **L2** | File structure | \`file_summary\` |
-| **L2** | Exact relevant section | \`compact\` |
+| **L2** | File structure | \`file_summary({ files, tier: 'T1' })\` |
+| **L2** | Exact relevant section | \`file_summary({ files, tier: 'T2' })\` |
 | **L2** | Many files | \`digest\` |
 | **L2** | Symbol defs/refs | \`symbol\` |
 | **L2** | Call/data flow | \`trace\` |
@@ -61,13 +61,13 @@ Raw read_file only for exact edit lines after compressed tools identify target.
 
 ## Context Reuse
 
-Before rereading path/topic, search exact path/topic first. If response gives ctxc_..., reuse with compact({ ref }) or compact({ ref, query }). Use enrich: true on tools that support it after first pass.
+Before rereading path/topic, search exact path/topic first. If response gives ctxc_..., reuse with file_summary({ ref }) or file_summary({ ref, query }). Use enrich: true on tools that support it after first pass.
 
 ## Patterns
 
-- New area: search -> scope_map -> file_summary/compact -> graph/trace -> stash.
-- Bug: search -> symbol -> trace -> compact -> test/check -> remember.
-- Refactor shared code: blast_radius -> checkpoint -> compact -> rename/codemod -> check -> test_run.
+- New area: search -> scope_map -> file_summary -> graph/trace -> stash.
+- Bug: search -> symbol -> trace -> file_summary -> test/check -> remember.
+- Refactor shared code: blast_radius -> checkpoint -> file_summary -> rename/codemod -> check -> test_run.
 - Web/API: web_search/web_fetch/http; browser only when JS/auth interaction needed. Browser snapshots now use ~200-400 tokens, making them practical for quick page state checks.
 
 ## Memory Discipline
@@ -85,7 +85,7 @@ Review decayed/stale entries periodically with knowledge({ action: 'flagged' }).
 Flows guide multi-step work. Read active step before acting. FORGE handles tiering/evidence/gates; load references only when main skill is too thin.
 
 ### Layered Knowledge Protocol
-- **L0** → Generated briefing cards: load \`workspace-core\` at session start via \`aikit://l0/workspace-core\` resource (full card, live-updated) or \`status({ includePrelude: true })\` (compact summary). Requires \`onboard()\` first — if card null, run \`onboard\` before session start. Add \`workflow:<flow>\` if flow active, or one task card if no flow. Use \`stratum_card\` / \`compact\` for content. Token-bounded.
+- **L0** → Generated briefing cards: load \`workspace-core\` at session start via \`aikit://l0/workspace-core\` resource (full card, live-updated) or \`status({ includePrelude: true })\` (compact summary). Requires \`onboard()\` first — if card null, run \`onboard\` before session start. Add \`workflow:<flow>\` if flow active, or one task card if no flow. Use \`file_summary({ tier: 'T1' })\` for structure, or \`file_summary({ tier: 'T2', query })\` for content. Token-bounded.
 - **L1** → Flow working context. Withdraw before dispatch; reuse before broad retrieval.
 - **L2** → Canonical curated knowledge. Retrieve on demand; never preload broadly.
 - **L3** → Evidence/auto-knowledge. Inspect only for provenance, conflict, or promotion assessment.
@@ -172,7 +172,7 @@ Need real usage examples?    → find({ mode: 'examples' })
 Need call/data flow?         → trace
 Need import/module graph?    → graph
 Need file reading plan?      → scope_map
-Need one file section?       → compact
+Need one file section?       → file_summary({ tier: "T2", query })
 Need many files compressed?  → digest
 ~~~
 
@@ -182,13 +182,13 @@ Need many files compressed?  → digest
 - Use \`symbol\` when the question is definition, imports, or refs.
 - Use \`trace\` when you care about execution path.
 - Use \`graph\` when you care about who depends on what.
-- Use \`compact\` after you already know the file and the question.
-- Use \`file_summary\` before \`compact\` if you still need structure.
+- Use \`file_summary\` after you already know the file and the question.
+- Use \`file_summary({ tier: 'T1' })\` for structure, or \`file_summary({ tier: 'T2', query })\` for specific content.
 
 ## Compression Ladder
 
 ~~~text
-file_summary → compact → digest → read_file only for edit lines
+file_summary (T1=structure, T2=content) or digest (multi-file synthesis). Read_file ONLY for edit lines
 ~~~
 
 ## Rule of Thumb
@@ -204,7 +204,7 @@ Fast, compact task setup loaded at session start.
 
 - **Auto-injected**: \`workspace-core\` (800-1200 tokens) — available via \`status({ includePrelude: true })\` after \`onboard()\` generates the card. If null → run \`onboard({ path, mode: 'generate' })\` then retry status.
 - **If flow active**: Load \`workflow:<flow>\` (500-900 tokens) via flow start refs (replaces task card)
-- **If no flow**: Optionally load one task card via \`stratum_card\` / \`compact\`
+- **If no flow**: Optionally load one task card via \`file_summary\`
 - **Budget**: ≤ 2,100 tokens total
 - **Storage**: Generated workspace cache (path from server config)
 - **Card families**: \`workspace-core\`, \`architecture\`, \`testing-release\`, \`known-issues\`, \`workflow:<flow>\`
@@ -216,7 +216,7 @@ Fast, compact task setup loaded at session start.
 Active run state and role-filtered dispatch context.
 
 - Withdraw via \`knowledge({ action: 'withdraw', scope: 'flow', profile: '<role>', budget: 6000 })\`
-- Use withdrawn refs before calling \`compact\`, \`file_summary\`, \`stratum_card\`, \`scope_map\`, \`blast_radius\`, or \`search\`
+- Use withdrawn refs before calling \`file_summary\`, \`scope_map\`, \`blast_radius\`, or \`search\`
 - Each step has a declared \`contextProfile\` (implementer, reviewer, researcher, documenter, debugger)
 
 ## L2 — Canonical Curated Knowledge

package/scaffold/dist/definitions/skills/c4-architecture.mjs

@@ -139,7 +139,7 @@ Default: Context + Container. Add Component only for a complex container and a c
 
 1. **Study examples first**: Load references/ example files to understand visual patterns, label density, and layout conventions before generating.
 2. Identify audience and decision the diagram supports.
-3. Gather evidence with AI Kit: analyze/graph/search/compact.
+3. Gather evidence with AI Kit: analyze/graph/search/file_summary.
 4. Pick level(s); avoid mixing levels in one diagram.
 5. **Generate structured diagram JSON** conforming to the centralized diagram schema (see ~/.aikit/resources/renderers/schemas/). Render via CLI: