brand-xlsx

Name: brand-xlsx
Author: ferdinandobons

19installs26forks

How to install brand-xlsx?

ferdinandobons/brand-docs/brand-xlsx

$npx -y skills add ferdinandobons/brand-docs --skill brand-xlsx

Installs into the current project.

Summary

Brand-aware Excel engine. Use to (1) EXTRACT a company's brand from a .xlsx template into a reusable "Brand Profile", (2) COMPREHEND the template with the model (optional), (3) VERIFY it, (4) GENERATE a new on-brand .xlsx from a GridDocument fill manifest. Trigger on "extract our

Files · 1

View on GitHub

SKILL.md

1	# brand-xlsx
2
3	Use this skill when the user wants reusable branded Excel/workbook generation
4	from a company `.xlsx` template and variable user-provided data.
5
6	This is an AI-agent skill for Codex and Claude Code. The user should describe
7	the workbook/model they want filled; the agent maps that request to named cells
8	and named regions, invokes the internal Python engine, verifies the output, and
9	returns the generated `.xlsx`.
10
11	## The seven verbs: three deterministic + four model-assisted
12
13	Every brand skill (`brand-docx`, `brand-pptx`, `brand-xlsx`) implements the same
14	contract. The deterministic core is extract / verify / generate; on top of it
15	sit the optional learning verbs **comprehend / learn / propose-overrides /
16	refine**, each fail-closed (the engine validates every proposal and authors every
17	value).
18
19	\| Verb \| Input \| Output \|
20	\|---\|---\|---\|
21	\| extract \| a company `.xlsx` template \| a reusable Brand Profile \|
22	\| comprehend (optional, model-driven) \| a saved profile + a model-authored `comprehension.json` \| the profile with a validated, cached `comprehension` block \|
23	\| verify \| a saved Brand Profile \| QA findings + a verdict \|
24	\| generate \| data (a GridDocument) + a profile \| a new on-brand `.xlsx` \|
25	\| learn (deterministic distillation) \| the profile's cross-run generation history \| recurring QA findings distilled into shell-frozen overrides, advisory until `--accept` \|
26	\| propose-overrides (model-driven) \| the recurring remainder `learn` could not bind + a model-authored proposal \| shell-backed corrections through the same fail-closed sink, advisory until `--accept` \|
27	\| refine \| end-of-generation user feedback (text or a screenshot) as a `refinement.json` delta \| the existing comprehension overlaid for FUTURE generations, advisory until `--accept` \|
28
29	`comprehend` is optional: `generate` works on the deterministic profile alone.
30	See [reference/comprehension.md](reference/comprehension.md) for the full step.
31
32	## Hard Rules
33
34	- Treat `python scripts/cli.py ...` as an internal engine command, not the user-facing workflow.
35	- `scripts/cli.py` is a LAUNCHER that locates the engine root by itself: it works from this skill folder AND from the repo/plugin root (set `BRAND_DOCS_ROOT` to override). Never guess deeper paths like `scripts/brandkit/...`.
36	- Run the dependency preflight before starting extract / comprehend / verify / generate, and report missing or unusable dependencies before proceeding.
37	- Extract opens the source template read-only and saves `brand-kit/<name>/template/shell.xlsx` byte-for-byte.
38	- Generate opens the saved shell and resolves every named cell/region through `profile.json`.
39	- Do not put style names, colors, fonts, or brand identifiers in a GridDocument.
40	- If the user did not provide a template or enough data, ask for the missing input.
41	- Return the generated file path plus a QA summary.
42	- Consult `profile.json.artifact_catalog` before generation when the user asks to mimic a specific piece of the template.
43
44	## Preflight (always first)
45
46	Before doing any work, run:
47
48	```bash
49	python scripts/cli.py doctor
50	```
51
52	Use its output to decide the run mode:
53
54	- If a required Python dependency is missing, install/repair it before extraction
55	or generation; the core engine is not ready.
56	- If only visual renderers are missing or unusable (`soffice` plus `pdftoppm` or
57	optional PyMuPDF/`fitz`), the
58	core L0 workflow can still run, but a full visual audit cannot be claimed.
59	Tell the user what is missing, include the install/repair hint printed by
60	`doctor`, and either proceed with degraded QA or install the renderer first.
61	- If optional OCR (`tesseract`) is missing, the visual audit can still run, but
62	rendered residual-text proof is incomplete. Report that limitation when
63	judging stale placeholders or field caches.
64	- For `--qa deep` or `--qa strict`, prefer repairing/installing renderers before
65	generation. If the environment cannot run them, `deep` generates a degraded
66	manifest and `strict` fails with a visual proof blocker.
67
68	## Agent Workflow
69
70	1. Run the dependency preflight above and report any degraded capability.
71	2. Determine the brand name and locate the user-provided `.xlsx` template.
72	3. If no matching `brand-kit/<name>` exists, extract one.
73	4. Comprehend the template (optional, model-driven; see below). Skip when a
74	current comprehension is already cache

People who liked this also viewed

6 picks

Type

brand-xlsx

19installs26forks

View on GitHub

How to install brand-xlsx?

ferdinandobons/brand-docs/brand-xlsx

$npx -y skills add ferdinandobons/brand-docs --skill brand-xlsx

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# brand-xlsx
2
3	Use this skill when the user wants reusable branded Excel/workbook generation
4	from a company `.xlsx` template and variable user-provided data.
5
6	This is an AI-agent skill for Codex and Claude Code. The user should describe
7	the workbook/model they want filled; the agent maps that request to named cells
8	and named regions, invokes the internal Python engine, verifies the output, and
9	returns the generated `.xlsx`.
10
11	## The seven verbs: three deterministic + four model-assisted
12
13	Every brand skill (`brand-docx`, `brand-pptx`, `brand-xlsx`) implements the same
14	contract. The deterministic core is extract / verify / generate; on top of it
15	sit the optional learning verbs **comprehend / learn / propose-overrides /
16	refine**, each fail-closed (the engine validates every proposal and authors every
17	value).
18
19	\| Verb \| Input \| Output \|
20	\|---\|---\|---\|
21	\| extract \| a company `.xlsx` template \| a reusable Brand Profile \|
22	\| comprehend (optional, model-driven) \| a saved profile + a model-authored `comprehension.json` \| the profile with a validated, cached `comprehension` block \|
23	\| verify \| a saved Brand Profile \| QA findings + a verdict \|
24	\| generate \| data (a GridDocument) + a profile \| a new on-brand `.xlsx` \|
25	\| learn (deterministic distillation) \| the profile's cross-run generation history \| recurring QA findings distilled into shell-frozen overrides, advisory until `--accept` \|
26	\| propose-overrides (model-driven) \| the recurring remainder `learn` could not bind + a model-authored proposal \| shell-backed corrections through the same fail-closed sink, advisory until `--accept` \|
27	\| refine \| end-of-generation user feedback (text or a screenshot) as a `refinement.json` delta \| the existing comprehension overlaid for FUTURE generations, advisory until `--accept` \|
28
29	`comprehend` is optional: `generate` works on the deterministic profile alone.
30	See [reference/comprehension.md](reference/comprehension.md) for the full step.
31
32	## Hard Rules
33
34	- Treat `python scripts/cli.py ...` as an internal engine command, not the user-facing workflow.
35	- `scripts/cli.py` is a LAUNCHER that locates the engine root by itself: it works from this skill folder AND from the repo/plugin root (set `BRAND_DOCS_ROOT` to override). Never guess deeper paths like `scripts/brandkit/...`.
36	- Run the dependency preflight before starting extract / comprehend / verify / generate, and report missing or unusable dependencies before proceeding.
37	- Extract opens the source template read-only and saves `brand-kit/<name>/template/shell.xlsx` byte-for-byte.
38	- Generate opens the saved shell and resolves every named cell/region through `profile.json`.
39	- Do not put style names, colors, fonts, or brand identifiers in a GridDocument.
40	- If the user did not provide a template or enough data, ask for the missing input.
41	- Return the generated file path plus a QA summary.
42	- Consult `profile.json.artifact_catalog` before generation when the user asks to mimic a specific piece of the template.
43
44	## Preflight (always first)
45
46	Before doing any work, run:
47
48	```bash
49	python scripts/cli.py doctor
50	```
51
52	Use its output to decide the run mode:
53
54	- If a required Python dependency is missing, install/repair it before extraction
55	or generation; the core engine is not ready.
56	- If only visual renderers are missing or unusable (`soffice` plus `pdftoppm` or
57	optional PyMuPDF/`fitz`), the
58	core L0 workflow can still run, but a full visual audit cannot be claimed.
59	Tell the user what is missing, include the install/repair hint printed by
60	`doctor`, and either proceed with degraded QA or install the renderer first.
61	- If optional OCR (`tesseract`) is missing, the visual audit can still run, but
62	rendered residual-text proof is incomplete. Report that limitation when
63	judging stale placeholders or field caches.
64	- For `--qa deep` or `--qa strict`, prefer repairing/installing renderers before
65	generation. If the environment cannot run them, `deep` generates a degraded
66	manifest and `strict` fails with a visual proof blocker.
67
68	## Agent Workflow
69
70	1. Run the dependency preflight above and report any degraded capability.
71	2. Determine the brand name and locate the user-provided `.xlsx` template.
72	3. If no matching `brand-kit/<name>` exists, extract one.
73	4. Comprehend the template (optional, model-driven; see below). Skip when a
74	current comprehension is already cache

People who liked this also viewed

6 picks

Type