website-build-skill 0.1.5 → 0.1.6
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/.claude-plugin/plugin.json +1 -1
- package/CHANGELOG.md +10 -0
- package/CLAUDE.md +1 -1
- package/README.md +1 -1
- package/adapters/grok.md +1 -1
- package/docs/COMPATIBILITY.md +2 -1
- package/docs/evidence/content-review.json +31 -13
- package/docs/evidence/host-trial-grok-build-2026-09-24.json +74 -0
- package/package.json +1 -1
- package/skills/website-build-skill/manifest.json +1 -1
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "website-build-skill",
|
|
3
|
-
"version": "0.1.
|
|
3
|
+
"version": "0.1.6",
|
|
4
4
|
"description": "A skill pack that teaches your AI current website-building expertise: research, design, code, accessibility, performance, search and security.",
|
|
5
5
|
"author": {
|
|
6
6
|
"name": "website-build-skill contributors"
|
package/CHANGELOG.md
CHANGED
|
@@ -6,6 +6,16 @@ Version policy: [Semantic Versioning 2.0.0](https://semver.org/spec/v2.0.0.html)
|
|
|
6
6
|
|
|
7
7
|
## [Unreleased]
|
|
8
8
|
|
|
9
|
+
## [0.1.6] - 2026-09-24
|
|
10
|
+
|
|
11
|
+
### Added
|
|
12
|
+
|
|
13
|
+
- Dated native-loading receipt for the Grok Build CLI 1.0.40 (SOLO, macOS, trusted folder, 2026-09-24) in `docs/evidence/`, linked from compatibility and the Grok adapter ([#15](https://github.com/aunysillyme/website-build-skill/issues/15)).
|
|
14
|
+
|
|
15
|
+
### Changed
|
|
16
|
+
|
|
17
|
+
- The Grok adapter says to trust the project folder: Grok Build offers project skills only in a trusted folder, found during the trial. Grok Bot (the Bots app) is named separately as still awaiting its trial.
|
|
18
|
+
|
|
9
19
|
## [0.1.5] - 2026-09-24
|
|
10
20
|
|
|
11
21
|
### Added
|
package/CLAUDE.md
CHANGED
|
@@ -13,5 +13,5 @@ node --test test/*.test.mjs
|
|
|
13
13
|
```
|
|
14
14
|
|
|
15
15
|
The installer is real; the native worker generator is not. Do not imply seven workers start.
|
|
16
|
-
Native SOLO loading is tested on Claude Code and
|
|
16
|
+
Native SOLO loading is tested on Claude Code, Codex and the Grok Build CLI (one run each, receipts in docs/evidence/).
|
|
17
17
|
Other hosts, TEAM, account tools and independent-review access are UNVERIFIED until a real trial.
|
package/README.md
CHANGED
|
@@ -124,7 +124,7 @@ With any of these missing, the AI hands you the exact next step (a query plan, f
|
|
|
124
124
|
## Choose your host
|
|
125
125
|
|
|
126
126
|
Each guide below has a documented setup with its own loading check. Native loading is tested
|
|
127
|
-
on Claude Code and
|
|
127
|
+
on Claude Code, Codex and the Grok Build CLI with dated receipts (one run each, limitations listed), and [compatibility](docs/COMPATIBILITY.md) tracks
|
|
128
128
|
current status host by host.
|
|
129
129
|
|
|
130
130
|
| Host | Set it up | What you get |
|
package/adapters/grok.md
CHANGED
|
@@ -7,7 +7,7 @@ See [compatibility](../docs/COMPATIBILITY.md) for setup evidence and host trials
|
|
|
7
7
|
|
|
8
8
|
- SOLO: paste the starter in [zero-install](zero-install.md), or give a file-capable session the complete canonical skill.
|
|
9
9
|
- TEAM: install or attach all five [bundles](../docs/bundles/team.md), open the seven sessions yourself, then paste the setup request below in each session.
|
|
10
|
-
- Native skill
|
|
10
|
+
- Native skill (Grok Build CLI): install with `--target grok`, which writes `.grok/skills/website-build-skill/`, then trust the project folder (accept the trust prompt, or run `grok --trust` there once). Grok Build offers project skills only in a trusted folder. Native loading was tested on Grok Build CLI 1.0.40 (macOS, SOLO, trusted folder, 2026-09-24; one run, limitations in the [receipt](../docs/evidence/host-trial-grok-build-2026-09-24.json)); `grok inspect --json` lists the skill with source `project` when it is available to you. Grok Bot (the Bots app) is awaiting its own trial. Current status: [compatibility](../docs/COMPATIBILITY.md).
|
|
11
11
|
- Independence: workers from one model family leave the independent release gate BLOCKED.
|
|
12
12
|
- Reference: [Bot setup](https://docs.x.ai/grok-bot/bots), [collaboration](https://docs.x.ai/grok-bot/chat-and-collaboration), [skills](https://docs.x.ai/build/features/skills-plugins-marketplaces). Use these references when checking the installed controls.
|
|
13
13
|
|
package/docs/COMPATIBILITY.md
CHANGED
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
## Tested hosts
|
|
4
4
|
|
|
5
|
-
|
|
5
|
+
Three hosts have a dated native-loading receipt. Each covers SOLO skill discovery and loading
|
|
6
6
|
on the exact version below, from one run under the operator's existing client configuration
|
|
7
7
|
(each receipt lists its limitations); the full SOLO build route, TEAM and deployment stay
|
|
8
8
|
documented until a trial records them.
|
|
@@ -11,6 +11,7 @@ documented until a trial records them.
|
|
|
11
11
|
|---|---|---|---|---|
|
|
12
12
|
| Claude Code | 2.1.281, macOS 26.6.2 arm64 | SOLO, native loading tested | 2026-09-24 | [receipt](evidence/host-trial-claude-code-2026-09-24.json) |
|
|
13
13
|
| Codex CLI | 0.154.0, macOS 26.6.2 arm64 | SOLO, native loading tested | 2026-09-24 | [receipt](evidence/host-trial-codex-2026-09-24.json) |
|
|
14
|
+
| Grok Build CLI | 1.0.40, macOS 26.6.2 arm64 | SOLO, native loading tested in a trusted folder | 2026-09-24 | [receipt](evidence/host-trial-grok-build-2026-09-24.json) |
|
|
14
15
|
|
|
15
16
|
Every other host has a documented setup and
|
|
16
17
|
a check you run, in its own adapter guide, to confirm it loaded on yours. A host moves from
|
|
@@ -10,24 +10,28 @@
|
|
|
10
10
|
"disposition": "instructions-and-qualified-status-only"
|
|
11
11
|
},
|
|
12
12
|
"CHANGELOG.md": {
|
|
13
|
-
"sha256": "
|
|
13
|
+
"sha256": "b3dc41e64c3a2d05c81ebbfec4ecc6e559db14b7381931e539a00bf24dc7ed21",
|
|
14
14
|
"disposition": "instructions-and-qualified-status-only",
|
|
15
|
-
"review": "0.1.2: the installer prompt block became a two-row choice table and one save-location sentence; reviewed by Claude against install-choice.txt and SKILL.md, same facts. Reviewed the added 0.1.1 framing note against the presentation copy changes; publication is a separate release action. Implementation-agent editorial review; independent review remains pending. Reviewed the copied-install checker ladder fix against the canonical instructions and regression test. Live host retrial remains pending release. Reviewed for the ROUND 1 audit: added Fixed/Added/Changed lines for the restored positive-and-accurate adapter, SKILL.md, designer.md, grok.md and validate.mjs fixes. Claude (builder, non-author fixer) editorial review; independent review remains pending. 0.1.3: reviewed the #13 description check and #14 Hermes path documentation entries against the implementation and regression tests; publication remains a separate maintainer action. Implementation-agent editorial review; independent review remains pending. 0.1.4: reviewed the added coding-research description and fourteen-domain wording against the canonical prompts and checklists; package release remains a separate maintainer action. Implementation-agent editorial review; independent review remains pending. Reviewed #16 manual-gate instructions against the explicit skips, packed consumer test and configured OS matrix; reviewed #17 TEAM wording against file-only installation and human session/handoff responsibilities. Implementation-agent editorial review only; host trials and independent review remain pending. Reviewed the #15 Fixed line for the symlinked-parent receipt path against src/install.mjs and installer tests 7e-7g, and the #15 Added line against the two receipts. 0.1.5 (#15): host-status wording promoted only for SOLO native loading on the exact client versions in the 2026-09-24 receipts; Claude (orchestrator, ran both trials) editorial review, independent review remains pending. 0.1.5 release heading moved the Unreleased lines under [0.1.5] - 2026-09-24 unchanged."
|
|
15
|
+
"review": "0.1.2: the installer prompt block became a two-row choice table and one save-location sentence; reviewed by Claude against install-choice.txt and SKILL.md, same facts. Reviewed the added 0.1.1 framing note against the presentation copy changes; publication is a separate release action. Implementation-agent editorial review; independent review remains pending. Reviewed the copied-install checker ladder fix against the canonical instructions and regression test. Live host retrial remains pending release. Reviewed for the ROUND 1 audit: added Fixed/Added/Changed lines for the restored positive-and-accurate adapter, SKILL.md, designer.md, grok.md and validate.mjs fixes. Claude (builder, non-author fixer) editorial review; independent review remains pending. 0.1.3: reviewed the #13 description check and #14 Hermes path documentation entries against the implementation and regression tests; publication remains a separate maintainer action. Implementation-agent editorial review; independent review remains pending. 0.1.4: reviewed the added coding-research description and fourteen-domain wording against the canonical prompts and checklists; package release remains a separate maintainer action. Implementation-agent editorial review; independent review remains pending. Reviewed #16 manual-gate instructions against the explicit skips, packed consumer test and configured OS matrix; reviewed #17 TEAM wording against file-only installation and human session/handoff responsibilities. Implementation-agent editorial review only; host trials and independent review remain pending. Reviewed the #15 Fixed line for the symlinked-parent receipt path against src/install.mjs and installer tests 7e-7g, and the #15 Added line against the two receipts. 0.1.5 (#15): host-status wording promoted only for SOLO native loading on the exact client versions in the 2026-09-24 receipts; Claude (orchestrator, ran both trials) editorial review, independent review remains pending. 0.1.5 release heading moved the Unreleased lines under [0.1.5] - 2026-09-24 unchanged. 0.1.6 (#15): Grok Build CLI 1.0.40 SOLO native-loading receipt added; wording promoted only for that client, in a trusted folder, one run; Grok Bot (Bots app) stays awaiting its trial. Claude (orchestrator, ran the trial) editorial review, independent review remains pending."
|
|
16
16
|
},
|
|
17
17
|
"CLAUDE.md": {
|
|
18
|
-
"sha256": "
|
|
18
|
+
"sha256": "4bc19853ddcdea0b2b751f82fba1d7c2451d2ae42f173dba1da2f6035df6e464",
|
|
19
19
|
"disposition": "status-claims-bound-to-receipts",
|
|
20
20
|
"claims": [
|
|
21
21
|
{
|
|
22
|
-
"text": "Native SOLO loading is tested on Claude Code and
|
|
22
|
+
"text": "Native SOLO loading is tested on Claude Code, Codex and the Grok Build CLI",
|
|
23
23
|
"evidence": "docs/evidence/host-trial-claude-code-2026-09-24.json"
|
|
24
24
|
},
|
|
25
|
+
{
|
|
26
|
+
"text": "Codex and the Grok Build CLI",
|
|
27
|
+
"evidence": "docs/evidence/host-trial-grok-build-2026-09-24.json"
|
|
28
|
+
},
|
|
25
29
|
{
|
|
26
30
|
"text": "(one run each, receipts in docs/evidence/)",
|
|
27
31
|
"evidence": "docs/evidence/host-trial-codex-2026-09-24.json"
|
|
28
32
|
}
|
|
29
33
|
],
|
|
30
|
-
"review": "0.1.5 (#15): status line narrowed to the two SOLO loading receipts; other hosts, TEAM, account tools and independent review stay UNVERIFIED. Claude editorial review."
|
|
34
|
+
"review": "0.1.5 (#15): status line narrowed to the two SOLO loading receipts; other hosts, TEAM, account tools and independent review stay UNVERIFIED. Claude editorial review. 0.1.6 (#15): Grok Build CLI 1.0.40 SOLO native-loading receipt added; wording promoted only for that client, in a trusted folder, one run; Grok Bot (Bots app) stays awaiting its trial. Claude (orchestrator, ran the trial) editorial review, independent review remains pending."
|
|
31
35
|
},
|
|
32
36
|
"CODE_OF_CONDUCT.md": {
|
|
33
37
|
"sha256": "9b32964f09663dbcf16e5ce39b4522928ba4c74d13c49f3fe6a9fb131b8ddd31",
|
|
@@ -43,17 +47,21 @@
|
|
|
43
47
|
"disposition": "instructions-and-qualified-status-only"
|
|
44
48
|
},
|
|
45
49
|
"README.md": {
|
|
46
|
-
"sha256": "
|
|
50
|
+
"sha256": "15e40dd0a81edb667484500a1f2c86e747fae08a70d39410805cc52091b0ae7e",
|
|
47
51
|
"disposition": "status-claims-bound-to-receipts",
|
|
48
|
-
"review": "0.1.2: the installer prompt block became a two-row choice table and one save-location sentence; reviewed by Claude against install-choice.txt and SKILL.md, same facts. Reviewed the requested skill-pack framing and each learning-table sentence against its linked canonical instructions; preserved the twelve stages, starter, setup card and sibling links. Demo URL awaits the separately recorded artifact. Implementation-agent editorial review; independent review remains pending. Reviewed for the ROUND 1 audit: restored the positive, once-stated native-loading status fact for adapters, README and compatibility docs, without implying native loading is proven. Claude (builder, non-author fixer) editorial review; independent review remains pending. 0.1.4: reviewed the added coding-research description and fourteen-domain wording against the canonical prompts and checklists; package release remains a separate maintainer action. Implementation-agent editorial review; independent review remains pending. Reviewed #16 manual-gate instructions against the explicit skips, packed consumer test and configured OS matrix; reviewed #17 TEAM wording against file-only installation and human session/handoff responsibilities. Implementation-agent editorial review only; host trials and independent review remain pending. 0.1.5 (#15): host-status wording promoted only for SOLO native loading on the exact client versions in the 2026-09-24 receipts; Claude (orchestrator, ran both trials) editorial review, independent review remains pending. ROUND 1 (2026-09-24): added the receipts' one-run and operator-configuration limitations to the promoted wording, per the code-reviewer finding.",
|
|
52
|
+
"review": "0.1.2: the installer prompt block became a two-row choice table and one save-location sentence; reviewed by Claude against install-choice.txt and SKILL.md, same facts. Reviewed the requested skill-pack framing and each learning-table sentence against its linked canonical instructions; preserved the twelve stages, starter, setup card and sibling links. Demo URL awaits the separately recorded artifact. Implementation-agent editorial review; independent review remains pending. Reviewed for the ROUND 1 audit: restored the positive, once-stated native-loading status fact for adapters, README and compatibility docs, without implying native loading is proven. Claude (builder, non-author fixer) editorial review; independent review remains pending. 0.1.4: reviewed the added coding-research description and fourteen-domain wording against the canonical prompts and checklists; package release remains a separate maintainer action. Implementation-agent editorial review; independent review remains pending. Reviewed #16 manual-gate instructions against the explicit skips, packed consumer test and configured OS matrix; reviewed #17 TEAM wording against file-only installation and human session/handoff responsibilities. Implementation-agent editorial review only; host trials and independent review remain pending. 0.1.5 (#15): host-status wording promoted only for SOLO native loading on the exact client versions in the 2026-09-24 receipts; Claude (orchestrator, ran both trials) editorial review, independent review remains pending. ROUND 1 (2026-09-24): added the receipts' one-run and operator-configuration limitations to the promoted wording, per the code-reviewer finding. 0.1.6 (#15): Grok Build CLI 1.0.40 SOLO native-loading receipt added; wording promoted only for that client, in a trusted folder, one run; Grok Bot (Bots app) stays awaiting its trial. Claude (orchestrator, ran the trial) editorial review, independent review remains pending.",
|
|
49
53
|
"claims": [
|
|
50
54
|
{
|
|
51
55
|
"text": "Native loading is tested",
|
|
52
56
|
"evidence": "docs/evidence/host-trial-claude-code-2026-09-24.json"
|
|
53
57
|
},
|
|
54
58
|
{
|
|
55
|
-
"text": "on Claude Code and
|
|
59
|
+
"text": "on Claude Code, Codex and the Grok Build CLI with dated receipts",
|
|
56
60
|
"evidence": "docs/evidence/host-trial-codex-2026-09-24.json"
|
|
61
|
+
},
|
|
62
|
+
{
|
|
63
|
+
"text": "and the Grok Build CLI with dated receipts",
|
|
64
|
+
"evidence": "docs/evidence/host-trial-grok-build-2026-09-24.json"
|
|
57
65
|
}
|
|
58
66
|
]
|
|
59
67
|
},
|
|
@@ -119,9 +127,15 @@
|
|
|
119
127
|
"review": "Reviewed setup instructions, tool fallback gates and compatibility links against the previous adapter; research status and safety requirements preserved. Implementation-agent editorial review; independent review remains pending. Reviewed for the ROUND 1 audit: restored the positive, once-stated native-loading status fact for adapters, README and compatibility docs, without implying native loading is proven. Claude (builder, non-author fixer) editorial review; independent review remains pending. Reviewed #16 manual-gate instructions against the explicit skips, packed consumer test and configured OS matrix; reviewed #17 TEAM wording against file-only installation and human session/handoff responsibilities. Implementation-agent editorial review only; host trials and independent review remain pending."
|
|
120
128
|
},
|
|
121
129
|
"adapters/grok.md": {
|
|
122
|
-
"sha256": "
|
|
123
|
-
"disposition": "
|
|
124
|
-
"review": "Reviewed setup instructions, tool fallback gates and compatibility links against the previous adapter; research status and safety requirements preserved. Implementation-agent editorial review; independent review remains pending. Reviewed for the ROUND 1 audit: restored the positive, once-stated native-loading status fact for adapters, README and compatibility docs, without implying native loading is proven. Claude (builder, non-author fixer) editorial review; independent review remains pending. 0.1.4: reviewed the added coding-research description and fourteen-domain wording against the canonical prompts and checklists; package release remains a separate maintainer action. Implementation-agent editorial review; independent review remains pending. Reviewed #16 manual-gate instructions against the explicit skips, packed consumer test and configured OS matrix; reviewed #17 TEAM wording against file-only installation and human session/handoff responsibilities. Implementation-agent editorial review only; host trials and independent review remain pending."
|
|
130
|
+
"sha256": "1119d57dbbaafeca3b158fc58994eba867b34a2a2df446423cb131b6a720bdcc",
|
|
131
|
+
"disposition": "status-claims-bound-to-receipts",
|
|
132
|
+
"review": "Reviewed setup instructions, tool fallback gates and compatibility links against the previous adapter; research status and safety requirements preserved. Implementation-agent editorial review; independent review remains pending. Reviewed for the ROUND 1 audit: restored the positive, once-stated native-loading status fact for adapters, README and compatibility docs, without implying native loading is proven. Claude (builder, non-author fixer) editorial review; independent review remains pending. 0.1.4: reviewed the added coding-research description and fourteen-domain wording against the canonical prompts and checklists; package release remains a separate maintainer action. Implementation-agent editorial review; independent review remains pending. Reviewed #16 manual-gate instructions against the explicit skips, packed consumer test and configured OS matrix; reviewed #17 TEAM wording against file-only installation and human session/handoff responsibilities. Implementation-agent editorial review only; host trials and independent review remain pending. 0.1.6 (#15): Grok Build CLI 1.0.40 SOLO native-loading receipt added; wording promoted only for that client, in a trusted folder, one run; Grok Bot (Bots app) stays awaiting its trial. Claude (orchestrator, ran the trial) editorial review, independent review remains pending.",
|
|
133
|
+
"claims": [
|
|
134
|
+
{
|
|
135
|
+
"text": "Native loading was tested on Grok Build CLI 1.0.40 (macOS, SOLO, trusted folder, 2026-09-24;",
|
|
136
|
+
"evidence": "docs/evidence/host-trial-grok-build-2026-09-24.json"
|
|
137
|
+
}
|
|
138
|
+
]
|
|
125
139
|
},
|
|
126
140
|
"adapters/hermes.md": {
|
|
127
141
|
"sha256": "bfb7624ce627d7a59328a16a663ed71aa96dbe24ede160bc349f13dd08cd1578",
|
|
@@ -134,7 +148,7 @@
|
|
|
134
148
|
"review": "Reviewed setup instructions, tool fallback gates and compatibility links against the previous adapter; research status and safety requirements preserved. Implementation-agent editorial review; independent review remains pending. Reviewed for the ROUND 1 audit: restored the positive, once-stated native-loading status fact for adapters, README and compatibility docs, without implying native loading is proven. Claude (builder, non-author fixer) editorial review; independent review remains pending."
|
|
135
149
|
},
|
|
136
150
|
"docs/COMPATIBILITY.md": {
|
|
137
|
-
"sha256": "
|
|
151
|
+
"sha256": "aaac6741324d456ac72618bd3d583c6211f0061958dd27daa6441997acf89425",
|
|
138
152
|
"disposition": "status-claims-bound-to-receipts",
|
|
139
153
|
"claims": [
|
|
140
154
|
{
|
|
@@ -144,9 +158,13 @@
|
|
|
144
158
|
{
|
|
145
159
|
"text": "| Codex CLI | 0.154.0, macOS 26.6.2 arm64 | SOLO, native loading tested | 2026-09-24 |",
|
|
146
160
|
"evidence": "docs/evidence/host-trial-codex-2026-09-24.json"
|
|
161
|
+
},
|
|
162
|
+
{
|
|
163
|
+
"text": "| Grok Build CLI | 1.0.40, macOS 26.6.2 arm64 | SOLO, native loading tested in a trusted folder | 2026-09-24 |",
|
|
164
|
+
"evidence": "docs/evidence/host-trial-grok-build-2026-09-24.json"
|
|
147
165
|
}
|
|
148
166
|
],
|
|
149
|
-
"review": "Reviewed documented setup routes and required trial evidence; retained the existing revision-bound hosted-check claim and receipt. Implementation-agent editorial review; independent review remains pending. Reviewed for the ROUND 1 audit: restored the positive, once-stated native-loading status fact for adapters, README and compatibility docs, without implying native loading is proven. Claude (builder, non-author fixer) editorial review; independent review remains pending. Reviewed #16 manual-gate instructions against the explicit skips, packed consumer test and configured OS matrix; reviewed #17 TEAM wording against file-only installation and human session/handoff responsibilities. Implementation-agent editorial review only; host trials and independent review remain pending. 0.1.5 (#15): host-status wording promoted only for SOLO native loading on the exact client versions in the 2026-09-24 receipts; Claude (orchestrator, ran both trials) editorial review, independent review remains pending. ROUND 1 (2026-09-24): added the receipts' one-run and operator-configuration limitations to the promoted wording, per the code-reviewer finding."
|
|
167
|
+
"review": "Reviewed documented setup routes and required trial evidence; retained the existing revision-bound hosted-check claim and receipt. Implementation-agent editorial review; independent review remains pending. Reviewed for the ROUND 1 audit: restored the positive, once-stated native-loading status fact for adapters, README and compatibility docs, without implying native loading is proven. Claude (builder, non-author fixer) editorial review; independent review remains pending. Reviewed #16 manual-gate instructions against the explicit skips, packed consumer test and configured OS matrix; reviewed #17 TEAM wording against file-only installation and human session/handoff responsibilities. Implementation-agent editorial review only; host trials and independent review remain pending. 0.1.5 (#15): host-status wording promoted only for SOLO native loading on the exact client versions in the 2026-09-24 receipts; Claude (orchestrator, ran both trials) editorial review, independent review remains pending. ROUND 1 (2026-09-24): added the receipts' one-run and operator-configuration limitations to the promoted wording, per the code-reviewer finding. 0.1.6 (#15): Grok Build CLI 1.0.40 SOLO native-loading receipt added; wording promoted only for that client, in a trusted folder, one run; Grok Bot (Bots app) stays awaiting its trial. Claude (orchestrator, ran the trial) editorial review, independent review remains pending."
|
|
150
168
|
},
|
|
151
169
|
"docs/EVALUATION.md": {
|
|
152
170
|
"sha256": "cb34b13e24b906496d0f05ef20187695bd51defe75b25abb7df8d5ad2935c32d",
|
|
@@ -0,0 +1,74 @@
|
|
|
1
|
+
{
|
|
2
|
+
"status": "PASS (native loading only, trusted folder)",
|
|
3
|
+
"packageCommit": "28d33366f49aa0e25ef0af222c97fbf72be300c9",
|
|
4
|
+
"packageVersion": "0.1.5 (npm, installed with npx website-build-skill@0.1.5)",
|
|
5
|
+
"mode": "solo",
|
|
6
|
+
"scope": "Native skill discovery and loading by the Grok Build CLI in a clean temporary git project with a synthetic brief. No website was built; research, mockup, build, review and handoff boundaries were not exercised. Grok Bot (the Bots app) was not tested.",
|
|
7
|
+
"negativeTrials": [
|
|
8
|
+
{
|
|
9
|
+
"case": "Untrusted project folder",
|
|
10
|
+
"result": "skill not offered",
|
|
11
|
+
"observed": "grok inspect --json in the fresh project reported projectTrusted false and listed no website-build-skill; Grok Build skips project skills in untrusted folders at startup (its own docs, user-guide/08-skills.md)."
|
|
12
|
+
}
|
|
13
|
+
],
|
|
14
|
+
"review": {
|
|
15
|
+
"candidateSha256": null,
|
|
16
|
+
"modelFamily": null,
|
|
17
|
+
"findings": [],
|
|
18
|
+
"dispositions": []
|
|
19
|
+
},
|
|
20
|
+
"trialId": "2026-09-24-grok-build-solo-load",
|
|
21
|
+
"client": {
|
|
22
|
+
"host": "Grok Build CLI",
|
|
23
|
+
"version": "grok 1.0.40 (eb1a2256660d) stable",
|
|
24
|
+
"os": "macOS 26.6.2 arm64",
|
|
25
|
+
"modelFamily": "xAI Grok (grok-4.7, recorded as modelId in the trial session transcript under ~/.grok/sessions)"
|
|
26
|
+
},
|
|
27
|
+
"invocation": "native project skill: installer wrote .grok/skills/website-build-skill/; the project folder was trusted; grok inspect --json then listed website-build-skill with source type project; headless grok -p asked to list native skills and load website-build-skill through its native skill mechanism",
|
|
28
|
+
"startedAt": "2026-09-24T07:31:08Z",
|
|
29
|
+
"finishedAt": "2026-09-24T07:34:01Z",
|
|
30
|
+
"commands": [
|
|
31
|
+
"npx --yes website-build-skill@0.1.5 --solo --target grok --dir <trial-project> --output-dir <trial-output> --receipt <trial-output>/install-receipt.json --yes",
|
|
32
|
+
"grok inspect --json (untrusted: skill absent)",
|
|
33
|
+
"trust <trial-project> (entry added to ~/.grok/trusted_folders.toml, removed after the trial)",
|
|
34
|
+
"grok inspect --json (trusted: skill listed, source project)",
|
|
35
|
+
"grok --output-format json -p '<synthetic loading brief>'"
|
|
36
|
+
],
|
|
37
|
+
"artifacts": [
|
|
38
|
+
"installed SKILL.md sha256 71cb5b229d68ae1b91a11d4168c6093a88d0c0f7da2dbcab0c933cb6a333c81b",
|
|
39
|
+
"57 files installed under .grok/skills/website-build-skill/"
|
|
40
|
+
],
|
|
41
|
+
"boundaries": [
|
|
42
|
+
{
|
|
43
|
+
"boundary": "Discovery",
|
|
44
|
+
"result": "PASS",
|
|
45
|
+
"observed": "Untrusted folder: not offered. Trusted folder: grok inspect lists website-build-skill with source type project and path .grok/skills/website-build-skill/SKILL.md."
|
|
46
|
+
},
|
|
47
|
+
{
|
|
48
|
+
"boundary": "Load",
|
|
49
|
+
"result": "PASS",
|
|
50
|
+
"observed": "Reported website-build-skill already in the session's native skills catalog before any file was opened; entrypoint .grok/skills/website-build-skill/SKILL.md; all 57 manifest assets READ (templates/install-choice.txt, tokens.json and handoff.yaml opened through line 3 only); docs/COMPATIBILITY.md not opened (not a manifest asset)."
|
|
51
|
+
},
|
|
52
|
+
{
|
|
53
|
+
"boundary": "First job",
|
|
54
|
+
"result": "PASS",
|
|
55
|
+
"observed": "Named Researcher first: ASK DATE from the canonical ladder, site-work/research/library/ on disk, AD01-AD08 then R01-R06 before any other role."
|
|
56
|
+
}
|
|
57
|
+
],
|
|
58
|
+
"limitations": [
|
|
59
|
+
"Run through the operator's cli-run wrapper, which adds a task-bundle frame to the prompt.",
|
|
60
|
+
"Project skills load only in a trusted folder; the trial trusted it by a config entry, the same state the interactive trust prompt or grok --trust saves.",
|
|
61
|
+
"Grok Build has no separate load-skill tool; loading means reading the SKILL.md path the catalog supplies.",
|
|
62
|
+
"SOLO loading only: TEAM, research, build and release boundaries are untested. Grok Bot (Bots app) is untested.",
|
|
63
|
+
"One run under the operator's existing client configuration."
|
|
64
|
+
],
|
|
65
|
+
"transcriptExcerpt": "1. Yes. `website-build-skill` was already in this session's native skills catalog before any file was opened. It was offered with the description \"Current website-building expertise for an AI: research, design, code, accessibility, performance, search and security...\" and the absolute path `.grok/skills/website-build-skill/SKILL.md`. This host has no separate load-skill tool. Loading means reading the `SKILL.md` path the catalog supplies. The filesystem was not searched to discover it.\n\n2. Entrypoint loaded: `.grok/skills/website-build-skill/SKILL.md`. `manifest.json` names 57 assets (`packageVersion` 0.1.5). Each one below was opened and returned content, so each is READ. `manifest.json` itself was opened in two reads because the first stopped at line 1000. `templates/install-choice.txt`, `templates/tokens.json`, and `templates/handoff.yaml` were opened only through line 3, so anything after line 3 in those three files is UNVERIFIED. Checksums in the manifest were not recomputed.\n\n- `SKILL.md` READ\n- `manifest.json` READ\n- `prompts/00-start.md` READ\n- `prompts/01-website-deep-research.md` READ\n- `archive/graphics-design-original.md` READ\n- `prompts/03-extract-brand-kit.md` READ\n- `prompts/04-three-mockups.md` READ\n- `prompts/05-stack-and-build.md` READ\n- `prompts/06-site-audit.md` READ\n- `prompts/07-accessibility-contrast.md` READ\n- `prompts/08-seo-aeo.md` READ\n- `prompts/09-security-headers.md` READ\n- `prompts/10-adversarial-pre-ship.md` READ\n- `prompts/11-ship-and-verify.md` READ\n- `prompts/12-web-design-team.md` READ\n- `prompts/13-coding-research.md` READ\n- `roles/researcher.md` READ\n- `roles/coordinator.md` READ\n- `roles/designer.md` READ\n- `roles/graphics.md` READ\n- `roles/builder.md` READ\n- `roles/optimizer.md` READ\n- `roles/reviewer.md` READ\n- `playbooks/choose-stack.md` READ\n- `playbooks/data-and-templates.md` READ\n- `playbooks/image-pipeline.md` READ\n- `playbooks/self-hosted-fonts.md` READ\n- `playbooks/embed-facades.md` READ\n- `playbooks/security-headers.md` READ\n- `playbooks/structured-data-and-llms.md` READ\n- `playbooks/performance-budgets.md` READ\n- `playbooks/accessibility.md` READ\n- `playbooks/research-and-memory.md` READ\n- `playbooks/deploy-and-operate.md` READ\n- `checklists/research.md` READ\n- `checklists/brand-and-mockups.md` READ\n- `checklists/build.md` READ\n- `checklists/code-quality.md` READ\n- `checklists/accessibility.md` READ\n- `checklists/performance-seo.md` READ\n- `checklists/security.md` READ\n- `checklists/ship.md` READ\n- `references/stacks/static-html.md` READ\n- `references/stacks/scripted-static.md` READ\n- `references/stacks/framework.md` READ\n- `templates/install-choice.txt` READ\n- `templates/brief.md` READ\n- `templates/brand.md` READ\n- `templates/tokens.json` READ\n- `templates/evidence.md` READ\n- `templates/handoff.yaml` READ\n- `templates/audit-brief.md` READ\n- `templates/site-operations.md` READ\n- `templates/status.md` READ\n- `examples/fictional-studio-brief.md` READ\n- `examples/fictional-studio-handoff.md` READ\n- `examples/audit-cases.md` READ\n\nThe entrypoint also names the repository file `docs/COMPATIBILITY.md`. That path is not a manifest asset. It was not opened. Whether it exists in this project is UNVERIFIED. No other entrypoint path failed to open. No website was built, no file was written, and the network was not used.\n\n3. The first job, before any downstream work, is Researcher. The manifest sets `entryRole` to `researcher`. Before intake or research, Researcher establishes ASK DATE from the canonical ladder in `playbooks/research-and-memory.md`, without asking the user and without using model knowledge, and records the rung and raw evidence in `site-work/research/library/scope.md`. Researcher then takes the request through `prompts/00-start.md` and `prompts/01-website-deep-research.md` and writes `site-work/research/library/`. No other role starts until that library exists on disk and its gate passes (AD01 through AD08, then R01 through R06). The install question about solo versus team is for the human at install and is not this first job.\n",
|
|
66
|
+
"reproduction": "docs/evaluation/host-trial.md steps 1-4 with the loadingBrief recorded in this receipt, after trusting the trial folder",
|
|
67
|
+
"command": "grok --output-format json -p '<synthetic loading brief>' (after npx --yes website-build-skill@0.1.5 --solo --target grok and trusting the folder)",
|
|
68
|
+
"environment": "Grok Build CLI 1.0.40 (grok-4.7), macOS 26.6.2 arm64, Node v22.22.3",
|
|
69
|
+
"date": "2026-09-24",
|
|
70
|
+
"exitCode": 0,
|
|
71
|
+
"artifactSha256": "71cb5b229d68ae1b91a11d4168c6093a88d0c0f7da2dbcab0c933cb6a333c81b",
|
|
72
|
+
"observed": "website-build-skill offered natively in the skills catalog once the folder was trusted; entrypoint .grok/skills/website-build-skill/SKILL.md; all 57 manifest assets read; Researcher named as the first job",
|
|
73
|
+
"loadingBrief": "## Task bundle\n\n**Context.** This is a host trial for the public npm package website-build-skill (issue #15 in this repository): does Grok Build natively discover and load the skill the installer writes to `.grok/skills/website-build-skill/`? Your current working directory is a clean temporary project where `npx website-build-skill@0.1.5 --solo --target grok` installed the skill. Matching receipts already exist for Claude Code and Codex. This is a synthetic loading trial only: no website is built.\n\n**Purpose.** Record whether the installed skill is offered and loaded natively by this Grok Build session, so the adapter claim can move past UNVERIFIED or stay there with a reason.\n\n**Scope of build.** None. Read-only trial. Deliverable is your text answer only.\n\n**Task class.** read_only\n\n**Granted scope.**\n- The current working directory and its `.grok/skills/website-build-skill/` folder.\n- Anything outside this list is out of scope.\n\n**Capabilities.** Your native skill mechanism; reading files inside the granted scope.\n\n**Vault reading.** none\n\n**The stack.** Not needed for this trial; answer from this session only.\n\n**Denied actions.** Do not write, create, move or delete any file. Do not build a website. Do not search the filesystem outside the current directory. Do not use the network.\n- Anything absent from Capabilities is denied.\n\n**Conventions you do not have.** Plain prose, no em dashes. Report only what you actually observed; say UNVERIFIED rather than guess.\n\n**Match the firmness.** Not applicable: this task interprets nothing the operator said. unrated.\n\n**Context packet.** none\n\n**Frozen invariants.** none\n\n**Resource inventory.** You hold your native skills catalog and file reads in this directory. You lack network access for this task and any tool outside this session.\n\n**Report contract.** Return exactly three numbered answers:\n1. Whether `website-build-skill` appears in the skills you were offered natively in this session, without searching the filesystem for it. Say how it was offered.\n2. Load it through your native skill mechanism. Give the entrypoint path you loaded, then list every asset named in its `manifest.json`, relative to the skill directory, each marked READ or UNREADABLE after actually opening it. Name any other file the entrypoint references that you could not read.\n3. One paragraph: what the skill says the first job is before any downstream work.\nState plainly anything you did not do or could not verify.\n\n**Exit parameters.** Stop after the three answers. Read at most the files the manifest names plus the entrypoint. If you hit a limit, report what you have and name what you did not cover.\n"
|
|
74
|
+
}
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "website-build-skill",
|
|
3
|
-
"version": "0.1.
|
|
3
|
+
"version": "0.1.6",
|
|
4
4
|
"description": "Skills that make your AI an expert website builder: current research, design, accessibility, performance, SEO, security and code, for any LLM or agent.",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"license": "MIT",
|