@antoneeo/kb-agentic-skill 1.4.3 → 1.4.5
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/CHANGELOG.md
CHANGED
|
@@ -2,6 +2,23 @@
|
|
|
2
2
|
|
|
3
3
|
Every significant change to this skill is recorded here.
|
|
4
4
|
|
|
5
|
+
## [1.4.5] - 2026-08-06
|
|
6
|
+
|
|
7
|
+
### Changed
|
|
8
|
+
- **Shared-spine sync: Functional Spec clause (inert in this lens).** The shared
|
|
9
|
+
`review.md` gains the code lens's Functional Spec findings (absence on behavior change,
|
|
10
|
+
Solution-leakage inside the spec, uncovered cases, acceptance criteria without tests).
|
|
11
|
+
The kb lens defines no `## Functional Spec` template section, so the clause stays inert
|
|
12
|
+
here — spine parity only.
|
|
13
|
+
|
|
14
|
+
## [1.4.4] - 2026-08-05
|
|
15
|
+
|
|
16
|
+
### Changed
|
|
17
|
+
- **Shared-spine sync: use-case grounding clause (inert in this lens).** The shared `review.md`
|
|
18
|
+
gains the code lens's use-case-grounding finding — a product name in no EXISTS/NEW/METAPHOR
|
|
19
|
+
bucket, or a use-case tracing to no Vision benefit. The kb lens defines no `## Use Cases`
|
|
20
|
+
template section, so the clause stays inert here — spine parity only.
|
|
21
|
+
|
|
5
22
|
## [1.4.3] - 2026-08-05
|
|
6
23
|
|
|
7
24
|
### Changed
|
package/gemini-extension.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "kb-agentic-skill",
|
|
3
|
-
"version": "1.4.
|
|
3
|
+
"version": "1.4.5",
|
|
4
4
|
"description": "Knowledge-Base & Document-First protocol with risk triage, Vision governance, signal distillation and optional devPNT integration.",
|
|
5
5
|
"author": "Antonio Pinto (https://github.com/Antoneeo)"
|
|
6
6
|
}
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@antoneeo/kb-agentic-skill",
|
|
3
|
-
"version": "1.4.
|
|
3
|
+
"version": "1.4.5",
|
|
4
4
|
"description": "Knowledge-Base & Document-First protocol for Claude Code, Gemini CLI, Google Antigravity and Codex with risk triage, Vision governance, signal distillation and optional devPNT integration.",
|
|
5
5
|
"keywords": [
|
|
6
6
|
"claude-code",
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: kb-agentic
|
|
3
|
-
version: 1.4.
|
|
3
|
+
version: 1.4.5
|
|
4
4
|
description: Knowledge-Base & Document-First protocol with risk-proportional triage, Vision as a guide, Signal Distillation, a complete Standalone mode and optional symbiosis with devPNT. Use for user documentation, knowledge extraction, SOPs, research notes, decision logs and knowledge management.
|
|
5
5
|
author: Antonio Pinto (https://github.com/Antoneeo)
|
|
6
6
|
copyright: (c) 2026 Antonio Pinto
|
|
@@ -146,6 +146,34 @@ When you are the reviewer:
|
|
|
146
146
|
which one is current. The rule bites hardest across domains, where the same slot
|
|
147
147
|
("threat model", "vision", "handoff") carries a different meaning under each lens and
|
|
148
148
|
a copy looks like an independent second source.
|
|
149
|
+
- **Use-case grounding (same reviews; the two-check gate whose owning definition
|
|
150
|
+
is the code lens's `templates.md` `## Use Cases / User Needs` comment — cite it,
|
|
151
|
+
never restate it).** On an L3 impact/solution analysis (Standalone) or `D-UC`
|
|
152
|
+
(Hybrid), two findings live here and nowhere else: **a product name in no
|
|
153
|
+
bucket** — the use-cases name a thing that neither EXISTS in the product (called
|
|
154
|
+
by the term the product itself uses; a renamed existing thing is a phantom), nor
|
|
155
|
+
is declared NEW in this change, nor is a pure METAPHOR kept out of the interface;
|
|
156
|
+
it invents system reality that is not there. And **a use-case that traces to no
|
|
157
|
+
Vision / M-VISION benefit** — a need the vision does not want, which is drift.
|
|
158
|
+
This gate checks the use-cases are GROUNDED and runs BEFORE the owner's own
|
|
159
|
+
review, never replacing it; coverage of each use-case by the Impact, and the
|
|
160
|
+
Actor it serves, stay the conformance-statement clause above. A lens whose
|
|
161
|
+
template defines no `## Use Cases` section never fires this clause.
|
|
162
|
+
- **Functional Spec (same reviews; fires only in the lens whose template defines
|
|
163
|
+
the section — the code lens today).** When the change adds or alters observable
|
|
164
|
+
behavior (the trigger's owning definition is the code lens's `templates.md`
|
|
165
|
+
`## Functional Spec` section comment — cite it, never restate it), **an L3
|
|
166
|
+
artifact carrying NO `## Functional Spec` is itself a finding** — absence is
|
|
167
|
+
what a skipped spec looks like, not a reason to skip the check. When the spec
|
|
168
|
+
is there, these findings live here: **a component, file or mechanism named
|
|
169
|
+
inside it** — the spec is component-free by construction; that is
|
|
170
|
+
Solution-leakage (component names belong to the Interface Contract, mechanism
|
|
171
|
+
to the Impact); a behavior whose edge, error or state-dependent cases are
|
|
172
|
+
absent with no stated reason; an acceptance criterion no `## Test Strategy`
|
|
173
|
+
item covers; a behavior serving no use case, or a use case whose behavior the
|
|
174
|
+
spec leaves unstated; and an Interface Contract flow realizing a behavior the
|
|
175
|
+
spec does not state. A lens whose template defines no such section (knowledge,
|
|
176
|
+
marketing) never fires this clause.
|
|
149
177
|
- **Capability Ledger (same reviews).** **An L3 impact/solution analysis or design
|
|
150
178
|
that carries NO Capability Ledger is itself a finding** — the lens's capability
|
|
151
179
|
pass (`architect.md` in the code lens, `taxonomy.md` in the knowledge lens) left
|