skillwiki 0.9.0 → 0.9.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "skillwiki",
3
- "version": "0.9.0",
3
+ "version": "0.9.1",
4
4
  "type": "module",
5
5
  "bin": {
6
6
  "skillwiki": "dist/cli.js"
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "skillwiki",
3
- "version": "0.9.0",
3
+ "version": "0.9.1",
4
4
  "skills": "./",
5
5
  "description": "Project-aware Karpathy-style knowledge base for Claude Code: 18 prompt-only skills (wiki-*, proj-*, using-skillwiki) backed by the deterministic `skillwiki` CLI.",
6
6
  "author": {
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "skillwiki",
3
- "version": "0.9.0",
3
+ "version": "0.9.1",
4
4
  "description": "Project-aware Karpathy-style knowledge base for Codex with 18 prompt-only skills backed by the deterministic skillwiki CLI.",
5
5
  "author": {
6
6
  "name": "karlorz",
@@ -36,7 +36,7 @@ You are a PRD format adapter specializing in mapping foreign design document for
36
36
  | Requirements list | `concepts/` or `entities/` |
37
37
  | Architecture decisions | `concepts/` with `tags: [architecture]` |
38
38
  | Motivation / context | `entities/` |
39
- | Trade-offs / comparisons | `comparisons/` |
39
+ | Trade-offs / comparisons | `comparisons/` with a `Decision Closeout` block |
40
40
  | Action items / next steps | Skip (project management, not knowledge) |
41
41
 
42
42
  **Execution Process:**
@@ -51,6 +51,15 @@ You are a PRD format adapter specializing in mapping foreign design document for
51
51
  - `## TL;DR` as first section
52
52
  - Preserve requirement IDs as tags or inline references
53
53
  - Convert internal links to `[[wikilinks]]` where pages exist
54
+ - For generated comparison or evaluation pages, end with:
55
+ ```markdown
56
+ ## Decision Closeout
57
+
58
+ Disposition: no-op | concept | ADR | work-item | evidence-needed
59
+ Reason: ...
60
+ Follow-up: ...
61
+ ```
62
+ Use exactly one disposition. Keep skipped action items out of typed knowledge unless the closeout disposition is `work-item`.
54
63
  7. **Validate.** `skillwiki validate <page>` for each page. If any non-zero, STOP.
55
64
  8. **Apply writes:** raw → pages → `index.md` → `log.md`.
56
65
 
@@ -32,6 +32,15 @@ You are a knowledge crystallizer specializing in distilling raw session material
32
32
  - Citations using `^[raw/...]` markers for every factual claim
33
33
  - For pages tagged `architecture` or explaining workflows: a Mermaid diagram (`graph TB` or `sequenceDiagram`)
34
34
  - Tags must come from `{vault}/SCHEMA.md` taxonomy only. If no relevant tag exists, use `[dev-loop]`.
35
+ - For `comparison`, evaluation-style `query`, or research-summary pages, end with:
36
+ ```markdown
37
+ ## Decision Closeout
38
+
39
+ Disposition: no-op | concept | ADR | work-item | evidence-needed
40
+ Reason: ...
41
+ Follow-up: ...
42
+ ```
43
+ Use exactly one disposition. Keep this as a prompt/template convention, not validation or lint enforcement.
35
44
  6. **Validate.** Run `skillwiki validate <page>`. If non-zero, fix issues and re-validate. Do NOT proceed until validation passes.
36
45
  7. **Apply writes in order:** Page file → add entry to `{vault}/index.md` → append entry to `{vault}/log.md`.
37
46
 
@@ -34,6 +34,15 @@ You are a vault ingestion specialist converting source material (URLs, files, te
34
34
  - `^[raw/...]` citations for every factual claim
35
35
  - Mermaid diagram if tagged `architecture` or explaining workflows
36
36
  - `confidence: low` if only one source cited
37
+ - For generated `comparisons/` pages or evaluation-style `queries/` pages, end with:
38
+ ```markdown
39
+ ## Decision Closeout
40
+
41
+ Disposition: no-op | concept | ADR | work-item | evidence-needed
42
+ Reason: ...
43
+ Follow-up: ...
44
+ ```
45
+ Use exactly one disposition. This is a prompt convention, not a validator rule.
37
46
  6. **Validate.** For each page: `skillwiki validate <page>`. If any non-zero, fix issues and re-validate. Do NOT proceed until all pages pass.
38
47
  7. **Apply writes in order:** raw file(s) → page(s) → update `index.md` → append `log.md`.
39
48
 
@@ -34,7 +34,15 @@ You are a vault search and synthesis specialist using E2 4-signal ranking to fin
34
34
  - Type affinity: 1.0×
35
35
  6. **Read top candidates.** Read frontmatter + body of highest-scored pages.
36
36
  7. **Synthesize answer.** Compose with explicit citations to candidate pages using `^[page-path]` markers.
37
- 8. **Optional file.** If the task asks to persist: write to `queries/<slug>.md` or `comparisons/<slug>.md` with full frontmatter, validate, then update `index.md` → `log.md`.
37
+ 8. **Optional file.** If the task asks to persist: write to `queries/<slug>.md` or `comparisons/<slug>.md` with full frontmatter, validate, then update `index.md` → `log.md`. If the filed page is a research/evaluation answer, recommendation, or comparison, end it with:
38
+ ```markdown
39
+ ## Decision Closeout
40
+
41
+ Disposition: no-op | concept | ADR | work-item | evidence-needed
42
+ Reason: ...
43
+ Follow-up: ...
44
+ ```
45
+ Use exactly one disposition. This is a prompt convention only; do not add CLI enforcement here.
38
46
 
39
47
  ### Verification Rule
40
48
  When a wiki page (especially a work item tasks.md) claims fixes were applied or features completed, **verify on disk before accepting**. Check file existence, grep config, inspect crontab. The filesystem is the source of truth — wiki pages can drift.
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@skillwiki/skills",
3
- "version": "0.9.0",
3
+ "version": "0.9.1",
4
4
  "private": true,
5
5
  "files": [
6
6
  "wiki-*",
@@ -48,7 +48,7 @@ Map source sections to typed-knowledge pages:
48
48
  | Requirements list | `concepts/` or `entities/` | Each major requirement becomes its own page or a section in a compound page |
49
49
  | Architecture decisions | `concepts/` | Map to concept pages with `tags: [architecture]` |
50
50
  | Motivation / context | `entities/` | Capture as entity pages describing the system or component |
51
- | Trade-offs / comparisons | `comparisons/` | Create comparison pages when the source weighs alternatives |
51
+ | Trade-offs / comparisons | `comparisons/` | Create comparison pages when the source weighs alternatives; include a `Decision Closeout` block |
52
52
  | Action items / next steps | Skip | Not knowledge — track in project work items instead |
53
53
 
54
54
  ### Cross-reference handling
@@ -65,6 +65,15 @@ Map source sections to typed-knowledge pages:
65
65
  3. Write raw capture: frontmatter + full body → `raw/articles/<slug>.md`.
66
66
  4. Run `skillwiki hash <raw-file>`, embed sha256.
67
67
  5. Generate typed-knowledge pages following the mapping strategy.
68
+ For generated comparison or evaluation pages, end the body with:
69
+ ```markdown
70
+ ## Decision Closeout
71
+
72
+ Disposition: no-op | concept | ADR | work-item | evidence-needed
73
+ Reason: ...
74
+ Follow-up: ...
75
+ ```
76
+ Use exactly one disposition. Preserve action items as skipped project-management content unless the closeout explicitly says `work-item`.
68
77
  6. For each page: run `skillwiki validate <page>`. If any fails, STOP.
69
78
  7. Write pages, then update `index.md` and `log.md`.
70
79
 
@@ -17,6 +17,15 @@ Standard four reads. If cwd is inside `projects/{slug}/`, also read project READ
17
17
  3. Compose the page with citations pre-attached. Reuse existing `raw/` sources where possible. Every page MUST include:
18
18
  - `> **TL;DR:**` blockquote as the first content after the title heading — a one-sentence summary of the page's key takeaway (under 200 chars). See SCHEMA.md `## TL;DR Convention`.
19
19
  - For pages tagged `architecture` or explaining workflows/systems: include a Mermaid diagram (`graph TB` or `sequenceDiagram`) in the body. Follow Obsidian-compatible Mermaid rules (see SCHEMA.md `## Mermaid Diagrams`).
20
+ For `comparison`, evaluation-style `query`, or research-summary pages, end the body with:
21
+ ```markdown
22
+ ## Decision Closeout
23
+
24
+ Disposition: no-op | concept | ADR | work-item | evidence-needed
25
+ Reason: ...
26
+ Follow-up: ...
27
+ ```
28
+ Use exactly one disposition. Keep this as a prompt/template convention; do not add validation or lint enforcement.
20
29
  4. `skillwiki validate <page>`. If non-zero, STOP.
21
30
  5. Apply writes: page → `index.md` → `log.md`.
22
31
  ## Stop conditions
@@ -23,6 +23,15 @@ Run `skillwiki lang` at the start. Generate page-body prose, narrative sections,
23
23
  5. **Generate page(s).** Compose typed-knowledge page(s) with citations pre-attached (`^[raw/...]` markers). Every page MUST include:
24
24
  - `> **TL;DR:**` blockquote as the first content after the title heading — a one-sentence summary of the page's key takeaway (under 200 chars). See SCHEMA.md `## TL;DR Convention`.
25
25
  - For pages tagged `architecture` or explaining workflows/systems: include a Mermaid diagram (`graph TB` or `sequenceDiagram`) in the body. Follow Obsidian-compatible Mermaid rules (see SCHEMA.md `## Mermaid Diagrams`).
26
+ For generated `comparisons/` pages or evaluation-style `queries/` pages, end the body with:
27
+ ```markdown
28
+ ## Decision Closeout
29
+
30
+ Disposition: no-op | concept | ADR | work-item | evidence-needed
31
+ Reason: ...
32
+ Follow-up: ...
33
+ ```
34
+ Use exactly one disposition. Keep this as a prompt convention, not a validator rule.
26
35
  6. **Validate.** For each generated page: run `skillwiki validate <page>`. If exit ≠ 0, STOP — do not write index/log.
27
36
  7. **Apply writes in order.** raw → page(s) → `index.md` → `log.md`.
28
37
  8. **Confidence flag.** If only one source is cited, set `confidence: low`.
@@ -22,7 +22,15 @@ Standard four reads (SCHEMA, index, log, project context if applicable).
22
22
  - Type affinity: 1.0×
23
23
  5. **Read top candidates** in full (frontmatter + body).
24
24
  6. **Synthesize answer** with explicit citations to the candidate pages.
25
- 7. **Optional file.** If user accepts: write to `queries/<slug>.md` or `comparisons/<slug>.md` with full frontmatter, validate, then update `index.md` then `log.md`.
25
+ 7. **Optional file.** If user accepts: write to `queries/<slug>.md` or `comparisons/<slug>.md` with full frontmatter, validate, then update `index.md` then `log.md`. If the filed page is a research/evaluation answer, recommendation, or comparison, end it with:
26
+ ```markdown
27
+ ## Decision Closeout
28
+
29
+ Disposition: no-op | concept | ADR | work-item | evidence-needed
30
+ Reason: ...
31
+ Follow-up: ...
32
+ ```
33
+ Use exactly one disposition. This is a prompt convention only; do not add CLI enforcement here.
26
34
  ## Stop conditions
27
35
  - Zero matching pages.
28
36
  - User declines to file.
@@ -48,7 +48,7 @@ Map source sections to typed-knowledge pages:
48
48
  | Requirements list | `concepts/` or `entities/` | Each major requirement becomes its own page or a section in a compound page |
49
49
  | Architecture decisions | `concepts/` | Map to concept pages with `tags: [architecture]` |
50
50
  | Motivation / context | `entities/` | Capture as entity pages describing the system or component |
51
- | Trade-offs / comparisons | `comparisons/` | Create comparison pages when the source weighs alternatives |
51
+ | Trade-offs / comparisons | `comparisons/` | Create comparison pages when the source weighs alternatives; include a `Decision Closeout` block |
52
52
  | Action items / next steps | Skip | Not knowledge — track in project work items instead |
53
53
 
54
54
  ### Cross-reference handling
@@ -65,6 +65,15 @@ Map source sections to typed-knowledge pages:
65
65
  3. Write raw capture: frontmatter + full body → `raw/articles/<slug>.md`.
66
66
  4. Run `skillwiki hash <raw-file>`, embed sha256.
67
67
  5. Generate typed-knowledge pages following the mapping strategy.
68
+ For generated comparison or evaluation pages, end the body with:
69
+ ```markdown
70
+ ## Decision Closeout
71
+
72
+ Disposition: no-op | concept | ADR | work-item | evidence-needed
73
+ Reason: ...
74
+ Follow-up: ...
75
+ ```
76
+ Use exactly one disposition. Preserve action items as skipped project-management content unless the closeout explicitly says `work-item`.
68
77
  6. For each page: run `skillwiki validate <page>`. If any fails, STOP.
69
78
  7. Write pages, then update `index.md` and `log.md`.
70
79
 
@@ -17,6 +17,15 @@ Standard four reads. If cwd is inside `projects/{slug}/`, also read project READ
17
17
  3. Compose the page with citations pre-attached. Reuse existing `raw/` sources where possible. Every page MUST include:
18
18
  - `> **TL;DR:**` blockquote as the first content after the title heading — a one-sentence summary of the page's key takeaway (under 200 chars). See SCHEMA.md `## TL;DR Convention`.
19
19
  - For pages tagged `architecture` or explaining workflows/systems: include a Mermaid diagram (`graph TB` or `sequenceDiagram`) in the body. Follow Obsidian-compatible Mermaid rules (see SCHEMA.md `## Mermaid Diagrams`).
20
+ For `comparison`, evaluation-style `query`, or research-summary pages, end the body with:
21
+ ```markdown
22
+ ## Decision Closeout
23
+
24
+ Disposition: no-op | concept | ADR | work-item | evidence-needed
25
+ Reason: ...
26
+ Follow-up: ...
27
+ ```
28
+ Use exactly one disposition. Keep this as a prompt/template convention; do not add validation or lint enforcement.
20
29
  4. `skillwiki validate <page>`. If non-zero, STOP.
21
30
  5. Apply writes: page → `index.md` → `log.md`.
22
31
  ## Stop conditions
@@ -23,6 +23,15 @@ Run `skillwiki lang` at the start. Generate page-body prose, narrative sections,
23
23
  5. **Generate page(s).** Compose typed-knowledge page(s) with citations pre-attached (`^[raw/...]` markers). Every page MUST include:
24
24
  - `> **TL;DR:**` blockquote as the first content after the title heading — a one-sentence summary of the page's key takeaway (under 200 chars). See SCHEMA.md `## TL;DR Convention`.
25
25
  - For pages tagged `architecture` or explaining workflows/systems: include a Mermaid diagram (`graph TB` or `sequenceDiagram`) in the body. Follow Obsidian-compatible Mermaid rules (see SCHEMA.md `## Mermaid Diagrams`).
26
+ For generated `comparisons/` pages or evaluation-style `queries/` pages, end the body with:
27
+ ```markdown
28
+ ## Decision Closeout
29
+
30
+ Disposition: no-op | concept | ADR | work-item | evidence-needed
31
+ Reason: ...
32
+ Follow-up: ...
33
+ ```
34
+ Use exactly one disposition. Keep this as a prompt convention, not a validator rule.
26
35
  6. **Validate.** For each generated page: run `skillwiki validate <page>`. If exit ≠ 0, STOP — do not write index/log.
27
36
  7. **Apply writes in order.** raw → page(s) → `index.md` → `log.md`.
28
37
  8. **Confidence flag.** If only one source is cited, set `confidence: low`.
@@ -22,7 +22,15 @@ Standard four reads (SCHEMA, index, log, project context if applicable).
22
22
  - Type affinity: 1.0×
23
23
  5. **Read top candidates** in full (frontmatter + body).
24
24
  6. **Synthesize answer** with explicit citations to the candidate pages.
25
- 7. **Optional file.** If user accepts: write to `queries/<slug>.md` or `comparisons/<slug>.md` with full frontmatter, validate, then update `index.md` then `log.md`.
25
+ 7. **Optional file.** If user accepts: write to `queries/<slug>.md` or `comparisons/<slug>.md` with full frontmatter, validate, then update `index.md` then `log.md`. If the filed page is a research/evaluation answer, recommendation, or comparison, end it with:
26
+ ```markdown
27
+ ## Decision Closeout
28
+
29
+ Disposition: no-op | concept | ADR | work-item | evidence-needed
30
+ Reason: ...
31
+ Follow-up: ...
32
+ ```
33
+ Use exactly one disposition. This is a prompt convention only; do not add CLI enforcement here.
26
34
  ## Stop conditions
27
35
  - Zero matching pages.
28
36
  - User declines to file.