review-brand

Name: review-brand
Author: gtrabanco

32installs2forks

How to install review-brand?

gtrabanco/agentic-workflow/review-brand

$npx -y skills add gtrabanco/agentic-workflow --skill review-brand

Installs into the current project.

Summary

Internal brand & copy review pass of the agentic-workflow review pack — composed in-turn by review-change and product-audit; not a menu entry. Checks changed user-facing copy against the project's brand doc: voice, terminology, and honesty of claims — applies only to surfaces wit

Files · 1

View on GitHub

SKILL.md

1	# Review Brand & Copy (internal)
2
3	Composed by `review-change` / `product-audit` within their conversation — on any
4	agent, follow this file inline as the routed step. **Findings only; never edits,
5	never refactors.**
6
7	## Scope
8
9	The diff or path/glob the caller passes; default the current change vs the
10	default branch. State the scope at the top of the returned table.
11
12	## Checklist (evaluate EVERY item — none is optional; n/a must be stated)
13
14	- ✓ Read the project's brand doc first (e.g. `docs/brand/BRAND.md`) — cite the
15	rule for every finding; n/a all items if the project has none and say so
16	- ✓ Tone of changed copy matches the declared voice (cite the guideline violated)
17	- ✓ Product/domain terms used consistently with the declared glossary (same
18	concept, same word, same capitalization)
19	- ✓ No forbidden/deprecated phrases from the brand doc
20	- ✓ Claims are honest: limits, restrictions, and reductions the code enforces
21	are disclosed in the copy (an undisclosed limitation is a major finding —
22	repo hard rule)
23	- ✓ Error/empty-state copy is actionable (says what happened and what to do),
24	not blame-y
25	- ✓ Consistency across the changed surface and its siblings (same action
26	labeled the same way everywhere)
27	- ✓ Placeholder/lorem text absent from the diff
28
29	## Return exactly
30
31	```
32	REVIEW BRAND — scope: <scope>
33
34	\| # \| Finding \| Sev \| Evidence \| Suggested fix \|
35	\|---\|---------\|-----\|----------\|---------------\|
36	\| 1 \| <what> \| critical\|major\|minor \| <file:line> \| <smallest action> \|
37
38	Checklist: <n> evaluated, <n> pass, <n> findings, <n> n/a (<which + why>)
39	Summary: <1-2 sentences>
40	Decision: PASS \| FAIL
41	```
42
43	FAIL if any critical or major finding is open; PASS otherwise. Minor findings
44	never block — they route to the caller's triage step.
45
46	## Done when
47
48	- Every checklist item was evaluated with evidence (file:line or command output)
49	or explicitly marked n/a with the reason.
50	- The fixed-format block above is returned — nothing more, nothing less — and
51	no code was changed.

People who liked this also viewed

6 picks

Type

review-brand

32installs2forks

View on GitHub

How to install review-brand?

gtrabanco/agentic-workflow/review-brand

$npx -y skills add gtrabanco/agentic-workflow --skill review-brand

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Review Brand & Copy (internal)
2
3	Composed by `review-change` / `product-audit` within their conversation — on any
4	agent, follow this file inline as the routed step. **Findings only; never edits,
5	never refactors.**
6
7	## Scope
8
9	The diff or path/glob the caller passes; default the current change vs the
10	default branch. State the scope at the top of the returned table.
11
12	## Checklist (evaluate EVERY item — none is optional; n/a must be stated)
13
14	- ✓ Read the project's brand doc first (e.g. `docs/brand/BRAND.md`) — cite the
15	rule for every finding; n/a all items if the project has none and say so
16	- ✓ Tone of changed copy matches the declared voice (cite the guideline violated)
17	- ✓ Product/domain terms used consistently with the declared glossary (same
18	concept, same word, same capitalization)
19	- ✓ No forbidden/deprecated phrases from the brand doc
20	- ✓ Claims are honest: limits, restrictions, and reductions the code enforces
21	are disclosed in the copy (an undisclosed limitation is a major finding —
22	repo hard rule)
23	- ✓ Error/empty-state copy is actionable (says what happened and what to do),
24	not blame-y
25	- ✓ Consistency across the changed surface and its siblings (same action
26	labeled the same way everywhere)
27	- ✓ Placeholder/lorem text absent from the diff
28
29	## Return exactly
30
31	```
32	REVIEW BRAND — scope: <scope>
33
34	\| # \| Finding \| Sev \| Evidence \| Suggested fix \|
35	\|---\|---------\|-----\|----------\|---------------\|
36	\| 1 \| <what> \| critical\|major\|minor \| <file:line> \| <smallest action> \|
37
38	Checklist: <n> evaluated, <n> pass, <n> findings, <n> n/a (<which + why>)
39	Summary: <1-2 sentences>
40	Decision: PASS \| FAIL
41	```
42
43	FAIL if any critical or major finding is open; PASS otherwise. Minor findings
44	never block — they route to the caller's triage step.
45
46	## Done when
47
48	- Every checklist item was evaluated with evidence (file:line or command output)
49	or explicitly marked n/a with the reason.
50	- The fixed-format block above is returned — nothing more, nothing less — and
51	no code was changed.

People who liked this also viewed

6 picks

Type