@cliangdev/conductor 0.41.0 → 0.42.0

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.
Files changed (52) hide show
  1. package/assets/claude/agents/conductor-coder.md +278 -7
  2. package/assets/claude/agents/{conductor-content-art-director.md → conductor-marketing-art-director.md} +2 -2
  3. package/assets/claude/agents/{conductor-content-creative-director.md → conductor-marketing-creative-director.md} +2 -2
  4. package/assets/claude/agents/{conductor-content-ideator.md → conductor-marketing-ideator.md} +3 -3
  5. package/assets/claude/agents/{conductor-content-scriptwriter.md → conductor-marketing-scriptwriter.md} +2 -2
  6. package/assets/claude/agents/{conductor-content-strategist.md → conductor-marketing-strategist.md} +2 -2
  7. package/assets/claude/commands/conductor/implement.md +1 -1
  8. package/assets/claude/commands/conductor/marketing.md +26 -0
  9. package/assets/claude/skills/conductor-marketing-create/SKILL.md +85 -0
  10. package/assets/claude/skills/{conductor-creative → conductor-marketing-create}/references/brand-kit-setup.md +2 -3
  11. package/assets/claude/skills/{conductor-content-studio → conductor-marketing-create}/references/design-critique.md +0 -1
  12. package/assets/claude/skills/{conductor-creative/SKILL.md → conductor-marketing-create/references/direct.md} +48 -59
  13. package/assets/claude/skills/{conductor-creative → conductor-marketing-create}/references/hooks.md +1 -1
  14. package/assets/claude/skills/{conductor-creative → conductor-marketing-create}/references/layout-guide.md +0 -1
  15. package/assets/claude/skills/{conductor-creative → conductor-marketing-create}/references/realism-check.md +0 -1
  16. package/assets/claude/skills/{conductor-content-studio → conductor-marketing-create}/references/rubric.md +1 -1
  17. package/assets/claude/skills/{conductor-creative → conductor-marketing-create}/references/slideshow-formats.md +0 -1
  18. package/assets/claude/skills/{conductor-content-studio/SKILL.md → conductor-marketing-create/references/team-run.md} +18 -25
  19. package/assets/claude/skills/{conductor-publisher → conductor-marketing-publish}/SKILL.md +5 -5
  20. package/assets/claude/skills/{conductor-marketing-analyst → conductor-marketing-report}/SKILL.md +11 -4
  21. package/assets/cli-manifest.json +17 -37
  22. package/dist/creative/assertions.js +4 -6
  23. package/dist/creative/frame.css +2 -2
  24. package/dist/creative/job/server.mjs +1 -2
  25. package/dist/creative/layouts/bleed/layout.css +1 -1
  26. package/dist/creative/render.js +1 -1
  27. package/dist/creative/styles.css +3 -3
  28. package/dist/lib/creative-browser.d.ts +1 -2
  29. package/dist/lib/creative-browser.d.ts.map +1 -1
  30. package/dist/lib/creative-browser.js.map +1 -1
  31. package/dist/lib/plugin-assets.d.ts.map +1 -1
  32. package/dist/lib/plugin-assets.js +97 -42
  33. package/dist/lib/plugin-assets.js.map +1 -1
  34. package/package.json +1 -1
  35. package/assets/claude/commands/conductor/content.md +0 -66
  36. package/assets/claude/commands/conductor/creative.md +0 -108
  37. package/assets/claude/commands/conductor/marketing-report.md +0 -38
  38. package/assets/claude/skills/conductor-coder/SKILL.md +0 -282
  39. package/assets/claude/skills/conductor-content-studio/references/layout-guide.md +0 -73
  40. package/assets/claude/skills/conductor-content-studio/references/realism-check.md +0 -95
  41. package/assets/claude/skills/conductor-content-studio/references/slideshow-formats.md +0 -135
  42. package/assets/claude/skills/conductor-creative/references/design-critique.md +0 -52
  43. package/assets/claude/skills/conductor-ux-ui-design/SKILL.md +0 -346
  44. package/assets/claude/skills/conductor-ux-ui-design/references/design-tokens.md +0 -359
  45. /package/assets/claude/skills/{conductor-content-studio → conductor-marketing-create}/references/capabilities.md +0 -0
  46. /package/assets/claude/skills/{conductor-content-studio → conductor-marketing-create}/references/compliance-checklist.md +0 -0
  47. /package/assets/claude/skills/{conductor-content-studio → conductor-marketing-create}/references/idea-template.md +0 -0
  48. /package/assets/claude/skills/{conductor-content-studio → conductor-marketing-create}/references/platform-specs.md +0 -0
  49. /package/assets/claude/skills/{conductor-content-studio → conductor-marketing-create}/references/publish-pack-template.md +0 -0
  50. /package/assets/claude/skills/{conductor-content-studio → conductor-marketing-create}/references/script-template.md +0 -0
  51. /package/assets/claude/skills/{conductor-content-studio → conductor-marketing-create}/references/shotlist-template.md +0 -0
  52. /package/assets/claude/skills/{conductor-marketing-analyst → conductor-marketing-report}/references/html-layout.md +0 -0
@@ -1,282 +0,0 @@
1
- ---
2
- name: conductor-coder
3
- description: Conductor-native coding agent that implements tasks TDD-style. Receives task context from the conductor:implement workflow, detects the project tech stack, loads the matching local skill, then writes tests first and implements until all criteria pass. Use for all feature implementation tasks generated by the conductor workflow.
4
- user-invocable: false
5
- ---
6
-
7
- # Conductor-Coder Skill
8
-
9
- Implementation agent for conductor tasks. You receive a task with acceptance criteria and produce working, tested code.
10
-
11
- ## Step 1: Receive and Parse Context
12
-
13
- You will be given:
14
- - **Task ID and title** — e.g., `T3.2: Add review submission endpoint`
15
- - **Task description** — what to build
16
- - **Acceptance criteria** — tagged `[auto]` (must have automated test) or `[manual]` (document verification steps)
17
- - **Epic context** — background and goals
18
- - **PRD path** — for deeper context if needed
19
-
20
- Read all of it before writing any code.
21
-
22
- ---
23
-
24
- ## Step 1.5: Validate task contract
25
-
26
- Before doing anything else, verify the dispatched task carries a complete v2 contract. The task object MUST contain all five of the following fields with non-empty values:
27
-
28
- - `contract.input` (string) — what this task receives as input
29
- - `contract.output` (string) — what this task must produce
30
- - `contract.invariant` (string) — what must remain true after this task
31
- - `test_plan` (array, ≥1 entry) — concrete checks that prove the task is done
32
- - `files_owned` (array, ≥1 entry) — the exhaustive list of file paths this task is allowed to edit
33
-
34
- **Validation rules — no inference, no guessing:**
35
-
36
- - Do NOT infer any of these fields from the task description, title, epic context, or PRD.
37
- - Do NOT proceed to Step 2 if any required field is missing or empty.
38
- - Do NOT silently fill in defaults.
39
-
40
- **On any missing or empty field, immediately emit a BLOCKED report.** The blocker line MUST use this exact wording:
41
-
42
- ```
43
- task contract incomplete: {missing fields}
44
- ```
45
-
46
- where `{missing fields}` is a comma-separated list of the missing field names drawn from the set `{contract.input, contract.output, contract.invariant, test_plan, files_owned}`. For example:
47
-
48
- ```
49
- ## Task Blocked: {task.id}
50
-
51
- Blocker: task contract incomplete: contract.input, files_owned
52
-
53
- Attempted:
54
- - contract validation in Step 1.5
55
-
56
- Needs:
57
- - task to be re-dispatched with the missing contract fields populated
58
- ```
59
-
60
- After emitting BLOCKED, stop. Do not continue to Step 2.
61
-
62
- **v1 task fallback (backward compat):** If the task object has NONE of the v2 contract fields at all (no `contract`, no `test_plan`, no `files_owned`), treat it as a legacy v1 task: skip Step 1.5 entirely and proceed to Step 2 with the existing v1 behavior. The all-or-nothing rule prevents partial-contract tasks from slipping through — a task with `contract.input` but no `files_owned`, for instance, is a malformed v2 task and MUST emit BLOCKED, not fall back to v1.
63
-
64
- ---
65
-
66
- ## Step 2: Detect Tech Stack
67
-
68
- Use Glob to check for stack indicator files in the project root. Check these in order:
69
-
70
- | File Present | Stack |
71
- |---|---|
72
- | `pom.xml` | Spring Boot |
73
- | `next.config.ts` or `next.config.js` | Next.js |
74
- | `package.json` only (no pom.xml, no next.config) | Node.js / generic |
75
-
76
- ```
77
- # Check for Spring Boot
78
- Glob: pom.xml
79
-
80
- # Check for Next.js
81
- Glob: next.config.ts (or next.config.js)
82
-
83
- # Fallback
84
- Glob: package.json
85
- ```
86
-
87
- Use the first match. Do not guess — check the files.
88
-
89
- ---
90
-
91
- ## Step 3: Load Matching Skill
92
-
93
- Based on the detected stack, read the corresponding skill file:
94
-
95
- | Stack | Skill Path |
96
- |---|---|
97
- | Spring Boot | `conductor-tools/assets/claude/skills/springboot/SKILL.md` |
98
- | Next.js | `conductor-tools/assets/claude/skills/nextjs/SKILL.md` |
99
- | Node.js / generic | `conductor-tools/assets/claude/skills/nodejs/SKILL.md` |
100
-
101
- Read the file. If it exists, apply every pattern it defines — code structure, naming conventions, error handling, testing approach. The stack skill is authoritative.
102
-
103
- If the skill file does not exist, output this message and continue with standard best practices for that stack:
104
-
105
- ```
106
- No {stack} skill found at conductor-tools/assets/claude/skills/{stack}/ — using general practices
107
- ```
108
-
109
- Replace `{stack}` with the actual stack name (e.g., `springboot`, `nextjs`, `nodejs`).
110
-
111
- ---
112
-
113
- ## Step 4: Write Tests First (TDD)
114
-
115
- For every `[auto]` acceptance criterion, write a failing test before writing implementation code.
116
-
117
- Name tests to directly reflect the criterion:
118
-
119
- ```typescript
120
- // [auto] API returns 201 on successful creation
121
- it('returns 201 on successful creation', async () => { ... });
122
-
123
- // [auto] Returns 400 when required field is missing
124
- it('returns 400 when required field is missing', async () => { ... });
125
- ```
126
-
127
- Run the tests and confirm they fail before moving on:
128
-
129
- ```bash
130
- # Spring Boot
131
- mvn test -Dtest=YourTestClass
132
-
133
- # Next.js / Node
134
- npx vitest run path/to/test
135
- ```
136
-
137
- Also write tests for:
138
- - Core business logic functions
139
- - Data validation and transformation
140
- - Error paths and edge cases
141
- - Integration points (API handlers, DB calls)
142
-
143
- ---
144
-
145
- ## Step 5: Implement
146
-
147
- Write the minimum code needed to make the tests pass. Follow the loaded stack skill's patterns exactly.
148
-
149
- Run tests after each meaningful change. Do not move on until all `[auto]` tests are green.
150
-
151
- **File-scope rule (v2 contract tasks):** Edit only files listed in the task's `files_owned`. If implementation requires a file not in `files_owned`, emit BLOCKED with reason `out-of-scope file required: {path}` instead of editing it. The coder may not extend `files_owned` mid-task. This applies to both source files and any companion files (configs, fixtures, generated artifacts) discovered during implementation. If an out-of-scope edit is genuinely required, the task must be redispatched with an updated `files_owned`. (v1 tasks that fell through Step 1.5's backward-compat path are exempt from this rule, since they have no `files_owned`.)
152
-
153
- Example BLOCKED report for an out-of-scope file:
154
-
155
- ```
156
- ## Task Blocked: {task.id}
157
-
158
- Blocker: out-of-scope file required: src/lib/utils/parser.ts
159
-
160
- Attempted:
161
- - implementation per files_owned
162
-
163
- Needs:
164
- - task redispatched with src/lib/utils/parser.ts added to files_owned, OR
165
- - a separate task to handle that file
166
- ```
167
-
168
- **Code quality rules (always apply):**
169
- - Small, focused functions — one responsibility each
170
- - Dependencies injected, not hardcoded — enables testing
171
- - Pure functions for business logic where possible
172
- - No global mutable state
173
- - No unnecessary comments — let naming convey intent
174
- - No commented-out code
175
-
176
- ---
177
-
178
- ## Step 6: Handle Manual Criteria
179
-
180
- For each `[manual]` criterion, add a comment in the relevant code or commit body describing how to verify it:
181
-
182
- ```
183
- Manual Verification: {criterion text}
184
- Steps: {what a reviewer should do to confirm this works}
185
- ```
186
-
187
- ---
188
-
189
- ## Step 7: Commit
190
-
191
- After all tests pass, create a single commit:
192
-
193
- ```bash
194
- git add {specific files}
195
- git commit -m "$(cat <<'EOF'
196
- {task.id}: {brief description}
197
-
198
- - {what was added}
199
- - {another change if relevant}
200
-
201
- Acceptance Criteria:
202
- - [x] {auto criterion 1}
203
- - [x] {auto criterion 2}
204
- - [ ] {manual criterion} — manual verification required
205
-
206
- Co-Authored-By: Claude Sonnet <noreply@anthropic.com>
207
- EOF
208
- )"
209
- ```
210
-
211
- Use a feature branch. Never push directly to main.
212
-
213
- ---
214
-
215
- ## Step 8: Report Back
216
-
217
- After committing, report your outcome:
218
-
219
- **If all auto criteria pass:**
220
-
221
- ```
222
- ## Task Complete: {task.id}
223
-
224
- Implemented:
225
- - {what was built}
226
-
227
- Tests:
228
- - {N} tests added, all passing
229
-
230
- Commits:
231
- - {hash}: {message}
232
-
233
- Manual Verification Needed:
234
- - {criterion}: {verification steps}
235
- ```
236
-
237
- **If blocked:**
238
-
239
- ```
240
- ## Task Blocked: {task.id}
241
-
242
- Blocker: {specific description of what's wrong}
243
-
244
- Attempted:
245
- - {what you tried}
246
-
247
- Needs:
248
- - {what is required to unblock}
249
- ```
250
-
251
- ---
252
-
253
- ## Quick Reference
254
-
255
- ### Stack Detection Order
256
-
257
- 1. `pom.xml` present → Spring Boot → load `springboot/SKILL.md`
258
- 2. `next.config.ts` or `next.config.js` present → Next.js → load `nextjs/SKILL.md`
259
- 3. `package.json` only → Node.js → load `nodejs/SKILL.md`
260
- 4. No skill file found → log gap message → use general best practices
261
-
262
- ### Criteria Tags
263
-
264
- - `[auto]` — write a failing test first, implement until it passes
265
- - `[manual]` — document verification steps in commit body or code comment
266
-
267
- ### Contract Validation (v2 tasks)
268
-
269
- - All five fields required: `contract.input`, `contract.output`, `contract.invariant`, `test_plan` (≥1 entry), `files_owned` (≥1 entry)
270
- - Missing → emit `task contract incomplete: {fields}` and STOP
271
- - Out-of-scope file needed → emit `out-of-scope file required: {path}` and STOP
272
- - Never extend `files_owned` mid-task; never infer missing contract fields
273
-
274
- ### Never
275
-
276
- - Commit without running tests
277
- - Push directly to main
278
- - Implement more than the acceptance criteria require
279
- - Skip the stack skill if it exists
280
- - Use `git add -A` or `git add .` — stage specific files by name
281
- - Edit a file outside `files_owned` (v2 tasks) — emit BLOCKED instead
282
- - Guess or infer missing contract fields — emit BLOCKED instead
@@ -1,73 +0,0 @@
1
- <!-- Keep identical to the copy in the other creative skill (conductor-creative / conductor-content-studio references/layout-guide.md). Skills install independently and cannot reference each other. -->
2
- # Layout guide
3
-
4
- Pick the layout on purpose. A Creative has one layout across all its placements (9:16, 4:5, 1:1), so
5
- choose it for the hardest placement, usually 9:16. Never rely on the registry default: it is
6
- `stacked`, which is the wrong pick whenever 9:16 is enabled.
7
-
8
- These notes come from rendering the same photo and headline in every layout with
9
- `preview_creative_draft`.
10
-
11
- ## Default
12
-
13
- - 9:16 enabled: **`bleed`**. Use **`card`** when the photo itself must stay bright and readable.
14
- - Only 4:5 and 1:1: `split` or `card` both work.
15
-
16
- ## The layouts
17
-
18
- - **`bleed`**: full-frame photo with a large headline. It is the only layout that fills 9:16 with a
19
- big headline. Dark theme only (`theme: "light"` is refused). Its scrim darkens most of the photo on
20
- 9:16 and 4:5, so choose a photo with a bright, high-contrast subject. On 4:5 the headline sits at
21
- the top, so a face in the top third of the photo lands under it; on 1:1 the headline is small at the
22
- bottom.
23
- - **`card`**: the photo as a framed card with a large headline beneath. On 9:16 the bottom third is
24
- an empty dark panel. Use it when the photo must stay readable, such as a product screen that
25
- bleed's scrim would hide.
26
- - **`split`**: good on 4:5, with a big headline under the photo. Bad on 9:16: the photo sits in the
27
- top third, a large dark panel is left empty, the headline is small, and it failed the 9:16 bottom
28
- safe-zone check. Don't use it when 9:16 is enabled.
29
- - **`stacked`**: on 9:16 the photo band leaves an empty dark slab and the headline is forced small
30
- (the 430 px bottom safe zone is solid fill). Don't use it when 9:16 is enabled. Fine for 4:5.
31
-
32
- ## 1:1 headline size
33
-
34
- On 1:1 every layout auto-fits the headline small (about 60 px at most). Pin it with `typeOverrides`,
35
- e.g. `{"1x1": [88]}`; 92 passed the checks with an eight-word headline. A pinned size is not shrunk to
36
- fit, so read `checks` again after pinning.
37
-
38
- ## Resolution
39
-
40
- Never upscale a photo. Before rendering, compute each photo's scale per placement and crop: the
41
- full-bleed cover scale is `max(W/w, H/h)` for a placement of W x H and a photo of w x h. Placements
42
- are 9:16 (1080x1920), 4:5 (1080x1350) and 1:1 (1080x1080). For a MOTION also multiply by the video
43
- zoom (up to 1.12).
44
-
45
- - A 1200x1200 photo full-bleed at 9:16 uses 675x1200 source pixels for 1080x1920: 1.6x.
46
- - A 1024x1536 photo at 9:16 is 1.25x. A 1440x2560 one is 0.75x, and 0.84x with the 1.12 zoom.
47
- - `bleed` is full-bleed on every placement. Refuse any full-bleed use above 1.0x, and compute the
48
- scale for the photo's actual crop in `card`, `split` and `stacked` too.
49
-
50
- Fixes, in order:
51
-
52
- 1. Generate at the largest size in that placement's aspect (`aspect: "9:16"` for 9:16;
53
- `placementFit` in the result shows the scale per placement).
54
- 2. Use a different photo.
55
- 3. Use a layout that shows the photo framed at or below native size.
56
-
57
- A photo above 1.0x is fixed before anything is shown, not mentioned.
58
-
59
- ## Logo
60
-
61
- `lockup: "chip"` puts the logo on a white pill. Use it when the photo behind the logo is busy.
62
-
63
- ## Photo and layout together
64
-
65
- `focalOverride` (e.g. `{"4x5": "50% 80%"}`) only moves the subject when the crop leaves spare room:
66
- a photo much taller than the placement's frame, or `card`'s wide strip on 1:1. A photo already close
67
- to the placement's shape (a 4:5-ish photo on 4:5) has nothing to shift, and the override does nothing.
68
- Check the next preview rather than assuming it worked.
69
-
70
- If the subject's face would sit under the headline: try `focalOverride` where there is room, else pick
71
- a photo with the subject lower in the frame, else use `card` (and pin `card`'s 1:1 crop with
72
- `focalOverride` so the face isn't cut off). If two fix rounds still leave a weak frame, the photo is
73
- usually the problem: say so and offer a different one.
@@ -1,95 +0,0 @@
1
- <!-- Keep identical to the copy in the other creative skill (conductor-creative / conductor-content-studio references/realism-check.md). Skills install independently and cannot reference each other. -->
2
- # Make it real, then check it
3
-
4
- This is about image quality, not concealment. The `aiGenerated: true` provenance and the platform's
5
- AI label still apply to every generated photo, however real it looks.
6
-
7
- A realistic photo comes from the prompt first and the check second. Write the prompt with the rules
8
- below, then check the result at the size it will be seen.
9
-
10
- ## Write the prompt
11
-
12
- These rules apply to every `generate_creative_image` call, from the art director and from the
13
- orchestrator.
14
-
15
- - **Shoot it like a home cook's phone photo, not an ad.**
16
- - Light: ordinary kitchen or window light. Normal dynamic range, a slightly off white balance, a
17
- little sensor noise.
18
- - Banned prompt words: cinematic, stunning, perfect, hyper-detailed, 8k, award-winning, golden
19
- hour, dramatic lighting, professional food photography, bokeh, glossy, studio.
20
- - **Every repeated item is different.** When a dish has several of something (stuffed peppers,
21
- tacos, cookies, dumplings, slices), the prompt names how they differ:
22
- - size, shape and lean;
23
- - how each is cut or carved;
24
- - char and blistering on one side only, a split skin on one;
25
- - filling heaped on one and sunk on another;
26
- - cheese melted unevenly, with one spot browner;
27
- - one slightly collapsed.
28
-
29
- Example for jack-o'-lantern stuffed peppers: "four peppers of different sizes and shades of
30
- orange, one leaning against another, each with a differently carved face (one lopsided, one with a
31
- missing tooth, one with small round eyes), the tallest has blistered skin on one side, filling
32
- spilling over the rim of one, cheese melted unevenly."
33
- - **Texture over shine.** Food that is matte in life stays matte. Sauces are a little broken or
34
- dried at the edges. There are crumbs, drips and a smear on the dish rim. No steam wisps, no perfect
35
- cheese pulls, no scattered garnish confetti.
36
- - **A real setting, lightly used.** Choose things a home has:
37
- - a sheet pan or baking dish with scorch marks, or a scratched enamel pot;
38
- - a worn wooden board, a laminate counter, a dish towel, a fork already in it.
39
- - Do not stage it. Something is slightly cut off at the frame edge.
40
- - **Off-center and imperfect framing.** No symmetrical hero composition. A slight tilt, an ordinary
41
- handheld angle (overhead or about 45 degrees, not low and dramatic).
42
- - **Vary across a batch.** Each image in a set gets its own surface, angle and light; only the
43
- realism and the absence of on-image text are shared. One prompt with the dish name swapped in is a
44
- defect.
45
- - **No people's faces, hands only if needed.** No text, logos or packaging brands in the image.
46
-
47
- For a subject that is not food, keep the same spirit: ordinary light, a lived-in setting, every
48
- repeated object different, imperfect framing.
49
-
50
- ## When to check
51
-
52
- Every image from `generate_creative_image`, before it is used as `photoPath`. Photos already in a
53
- library are not exempt: an existing recipe photo gets the same check, whoever made it.
54
-
55
- ## How to look
56
-
57
- Check a 100% crop of the region that will be on screen, at the size and crop of each placement:
58
- 4:5, 9:16 and, for a MOTION, the video zoom (up to 1.12x). Open the full-size file with Read and
59
- crop it. Never judge from a contact sheet: it hides exactly the tells below.
60
-
61
- ## Tells
62
-
63
- - **Light**: golden-hour or HDR glow, halos, dramatic or studio lighting, perfect white balance,
64
- colours too saturated, over-sharpening.
65
- - **Repeated items**: identical copies of the same item, the same garnish or prop twice.
66
- - **Objects and physics**: melted or merged objects, floating items, utensils or handles that do not
67
- connect to anything, impossible reflections, steam or liquid that looks painted, wrong scale.
68
- - **Text**: pseudo-text, garbled labels, invented logos, a fake product or app screen.
69
- - **Texture**: plastic or waxy food, skin or fabric; everything glossy; over-smoothed surfaces;
70
- perfect cheese pulls.
71
- - **Anatomy**: hands and fingers (count, joints), teeth, eyes, hair edges merging into the
72
- background.
73
- - **Detail under zoom**: smeared or mushy detail, repeating textures, a staged stock-photo look.
74
-
75
- ## Verdict
76
-
77
- Write PASS or FAIL for each placement crop, naming the tell on a FAIL. Any tell above that shows in
78
- a crop is a FAIL. A flaw that shows in no placement crop can PASS with a note.
79
-
80
- ## On FAIL
81
-
82
- Regenerate with the failed tells named in the new prompt, for example "four different peppers, no
83
- two alike", "matte sauce, dried at the edges, soft window light", "hands out of frame". At most two
84
- regenerations per image (each uses Codex allowance, or bills the API key on the fallback route, more at
85
- larger sizes). Then stop. Tell the person what still looks generated and offer a
86
- library photo, a reference photo (`referenceImagePaths`), or filming. Never ship a FAIL.
87
-
88
- ## Report
89
-
90
- When showing the draft for approval, give a one-line realism verdict per generated photo:
91
-
92
- - "Realism: passed — natural light, believable clutter"
93
- - "Realism: passed with a note — a smudge at the far edge, outside every placement crop"
94
-
95
- The person's approval remains the final check.
@@ -1,135 +0,0 @@
1
- <!-- Keep identical to the copy in the other creative skill (conductor-creative / conductor-content-studio references/slideshow-formats.md). Skills install independently and cannot reference each other. -->
2
- # Slideshow formats
3
-
4
- For organic posts: a native-looking photo slideshow (TikTok photo post, Instagram carousel) that
5
- promotes an app or product by being worth watching first. Build it with `compose_slideshow`, then
6
- post it as a CAROUSEL Creative. Ads use the brand layouts (STILL) instead; this is not the ad path.
7
-
8
- Branding is light: no logo, badge or offer on the slides. The product appears as the payoff, not the
9
- opener.
10
-
11
- ## Post anatomy
12
-
13
- Aim for 5 to 7 slides. Each slide has one job.
14
-
15
- 1. **Slide 1, the hook.** A human tension or a result people want to keep. Never a feature, the
16
- product name or a price.
17
- 2. **Middle slides, the value.** The part people save or send: the list, the plan, the fix, the story
18
- beat. Saves and sends carry a post beyond followers.
19
- 3. **Slide N-1, the payoff.** The product in use on a real screenshot (a `screen` slide, optionally
20
- with `callouts`) plus one plain mention, such as "I keep mine in <App>".
21
- 4. **Last slide, the ask.** A save or follow ask: "Save this. Link in bio."
22
-
23
- ## Slide types
24
-
25
- Every slide takes `type` (default `photo`), an optional background (`bg` path, `bgColor`, `blur`,
26
- `grade`, `grain`, `dim`) and `texts`. Each text is `{t, y, fs, style}`; the first text of a slide
27
- needs `y`, and later texts without `y` stack under the previous one.
28
-
29
- | Type | For | Key fields | Use when |
30
- |---|---|---|---|
31
- | `photo` | A full-bleed photo with text on it | `bg`, `pos`, `grade`, `grain`, `dim`, `texts` | The default hook, list or story slide |
32
- | `screen` | A real app screenshot in a phone frame | `shot`, `phoneY`, `pw`, `cropH`, `callouts [{x, y, label}]`, `bg`, `blur`, `texts` | The payoff slide (N-1); callouts point at what to notice |
33
- | `notes` | A Notes-app page | `title`, `date`, `items` (strings or `{t, done, strike}`), `paras` | A plan, checklist or "what I do now" |
34
- | `messages` | A chat thread | `bubbles [{from: "me"|"them", t}]` | Doubt or conflict: what someone said to you |
35
- | `grid` | A wall of small photos | `cols`, `gridTop`, `photos [{src, x, badge, cap, restore}]` | "Everything you saved and never used"; one tile `restore`d for the close |
36
- | `stack` | Photos stacked in a column | `photos [{src, label}]` | A before/after with `label`s ("Before", "After") or a short comparison |
37
- | `tier` | A tier list | `rows [{k, c, items}]`, `ts` | Ranking, "what's worth it and what isn't" |
38
- | `week` | A week planner | `days [{d, t, img, icon, fog}]` | A routine or plan across days |
39
- | `receipt` | A till receipt | `head`, `sections [{h, items}]`, `count` | A tally or breakdown; `count` must be a real figure |
40
- | `placard` | A museum-style label over a photo | `bg`, `ex`, `title`, `y`, `lines [{k, v}]` | A deadpan, collectible-feeling item card |
41
-
42
- Text `style`: `box` (white rounded box, TikTok's own text look), `dark` (dark box), `stroke` (white
43
- text, black outline), `sub` (smaller subline).
44
-
45
- ### Example spec
46
-
47
- A five-slide "stop doing X" post. Paths are relative to the spec file or absolute.
48
-
49
- ```json
50
- {
51
- "id": "stop-over-saving",
52
- "slides": [
53
- {"type": "photo", "bg": "photos/desk.jpg", "grade": true, "grain": true,
54
- "texts": [{"t": "Stop saving things you will never open.", "y": 30, "fs": 76}]},
55
- {"type": "messages",
56
- "bubbles": [{"from": "them", "t": "did you ever look at that thing you saved?"},
57
- {"from": "me", "t": "define look"}],
58
- "texts": [{"t": "Be honest.", "y": 20}]},
59
- {"type": "notes", "title": "What I do now", "date": "Today",
60
- "items": ["Save one thing", {"t": "Open it within a day", "done": true}, "Delete the rest"]},
61
- {"type": "screen", "shot": "shots/home.png", "phoneY": 40, "pw": 600,
62
- "callouts": [{"x": 50, "y": 30, "label": "one tap"}],
63
- "texts": [{"t": "I keep mine in <App>.", "y": 18}]},
64
- {"type": "photo", "bg": "photos/desk.jpg", "dim": true,
65
- "texts": [{"t": "Save this.", "y": 32, "fs": 80}, {"t": "Link in bio.", "style": "sub"}]}
66
- ]
67
- }
68
- ```
69
-
70
- ## Hook archetypes
71
-
72
- Pick one per post and name it in the idea. Change one thing per post so results are comparable.
73
-
74
- | Archetype | Slide 1 | Slides |
75
- |---|---|---|
76
- | Saved-but-never-used guilt | "Camera-roll graveyard." | `grid` (one tile `restore`d at the end), `photo`, `screen`, ask |
77
- | Doubt or conflict | What someone said to you (needs a true story) | `messages`, `photo`, `notes`, `screen`, ask |
78
- | Stop doing X | "Stop doing X." | `photo` with the reason per slide, `screen`, ask |
79
- | Numbered list | "5 things worth saving" | `photo` per item, `screen` last, ask |
80
- | Tier list | "Ranking everything I tried" | `tier`, `photo` close-ups, `screen`, ask |
81
- | Notes-app plan | "My plan for the week" | `notes`, `week`, `screen`, ask |
82
- | POV | "POV: you finally did it" | `photo` (hands or a real scene), `screen`, `photo`, ask |
83
- | Before / after | "Week 1 vs week 4" | `stack` with `label`s, `photo`, `screen`, ask |
84
-
85
- ## Text rules
86
-
87
- - Native box text (`box`) or white text with a black stroke (`stroke`); centred, bold, sans.
88
- - At most 8 words a line and 3 lines a box.
89
- - Keep text between about y 16 and y 75 (percent of the 9:16 frame). That survives the 4:5 Instagram
90
- cut and the platform UI (top bar, bottom caption, right button column).
91
- - The first text of every slide needs `y`.
92
- - Read the composer's `checks`; an `error` severity blocks the preview.
93
-
94
- ## Resolution
95
-
96
- Slides are 1080x1920 (and 1080x1350 for Instagram). Never upscale a background photo: the full-bleed
97
- scale is `max(1080/w, 1920/h)` for a photo of w x h (use `max(1080/w, 1350/h)` for the 4:5 cut). A 1200x1200
98
- photo full-bleed at 9:16 uses 675x1200 source pixels, a 1.6x upscale. Check every `bg` and
99
- `photos[].src` before composing and refuse a full-bleed use above 1.0x. The fixes are: generate at
100
- the largest size in that aspect (`aspect: "9:16"`), use a different photo, or use a slide type that
101
- shows the photo framed at or below native size (such as `grid` or `stack`).
102
-
103
- ## Honesty and brand
104
-
105
- - No logo, badge or offer on the slides. The offer, if any, goes in the caption.
106
- - No invented numbers or claims. A placeholder count (a receipt `count`, "312 saved") must be
107
- replaced with a real figure, or the line rewritten without one.
108
- - Real screenshots only for `screen` slides; never mock up the product.
109
- - A generated photo needs the platform's AI label turned on. Turn on the platform's branded-content
110
- or "your brand" setting for a brand's own promotional post.
111
- - A conflict or testimonial story must be true, and anyone shown or quoted must be real and agree.
112
-
113
- ## Getting the download
114
-
115
- Captions on TikTok and Instagram cannot hold clickable links, so do not rely on one:
116
-
117
- - Name the app in the caption and on slide N-1, so it can be searched ("search <App> in the App
118
- Store").
119
- - Pin a comment that says where to find it.
120
- - Keep the link in the profile bio.
121
- - Repost the post to Instagram Stories with a link sticker.
122
-
123
- ## Flow
124
-
125
- 1. Write the spec (`slideshow-spec.json`); call `compose_slideshow({specPath})`.
126
- 2. If `passed` is false, fix every `error` check and compose again. Warnings are advisory.
127
- 3. `preview_creative_draft({kind: "CAROUSEL", slidePaths, caption, slideAltText})` using the
128
- returned `slidePaths` (`9x16` for TikTok, `4x5` for Instagram). Look at the contact sheet and show
129
- it.
130
- With music (`audio: {source: "track", trackId}`, a library track from
131
- `list_creative_media({kind: "AUDIO"})`; a new file is uploaded there first with its source and
132
- licence), the preview also renders the slideshow video and returns `slideshowVideoPath`: watch it
133
- with the person. No platform accepts a chosen track on photos, so a destination sends the video
134
- (`carouselAs: "video"`) or the silent photos.
135
- 4. Only after the person approves, `commit_creative_draft`.
@@ -1,52 +0,0 @@
1
- <!-- Keep identical to the copy in the other creative skill (conductor-creative / conductor-content-studio references/design-critique.md). Skills install independently and cannot reference each other. -->
2
- # Design critique
3
-
4
- Passing checks does not make an ad good. `checks` and `passed` cover text spill, safe zones, contrast
5
- and fonts. This critique covers craft, and it runs before the person sees a draft.
6
-
7
- Look at the preview image at phone size. Vision models miss small typography details, so don't
8
- claim to have judged kerning or hairline spacing; judge what is visible at a glance.
9
-
10
- ## Which criteria apply
11
-
12
- Stills, ads and brand-layout creatives use the six criteria below. An organic slideshow (a
13
- `compose_slideshow` CAROUSEL) uses the five slideshow criteria further down instead, because it is
14
- meant to look native, not like an ad.
15
-
16
- ## Score each criterion 1 to 5 (stills and ads)
17
-
18
- Score each one on its own, against the description, not against another draft.
19
-
20
- 1. **Thumb-stop**: would it stop a scroll? One clear focal point and a hook you get in a second.
21
- 2. **Headline size and position**: readable at thumbnail size, not crammed into a corner or a thin strip.
22
- 3. **Empty space**: no dead slab or empty panel. Space that is there on purpose is fine; a leftover band is not.
23
- 4. **Photo and copy together**: copy is not on the subject's face, and the photo carries the concept rather than decorating it.
24
- 5. **Product shown**: the product, or the result it gives, is visible. A stock pose or an empty scene scores 1 or 2.
25
- 6. **Not a banner ad**: it does not read as logo + badge + tagline stacked on a picture.
26
-
27
- ## Act on the scores
28
-
29
- - Any criterion below 3: fix it (copy, layout, `focalOverride`, `typeOverrides`, the photo) and
30
- render again. At most two fix rounds.
31
- - Still below 3 after that: show the best version with one honest line on what is weak.
32
- - Comparing variants: score each on its own first. Use a side-by-side comparison only to break a
33
- tie, and judge it in both orders (first vs. second, then second vs. first); if the order changes
34
- the winner, call it a tie. Pairwise judging favours whichever is shown first.
35
-
36
- ## Show the scores
37
-
38
- One compact line next to the preview, for example:
39
- `Craft: thumb-stop 4, headline 4, space 3, photo+copy 4, product 3, not-banner 4. Weakest: product is implied, not shown.`
40
-
41
- ## Slideshow criteria (organic slideshows)
42
-
43
- Look at the contact sheet: slide 1 at full size, then the slides in order. Score each 1 to 5.
44
-
45
- 1. **Slide 1 stops the scroll**: a human tension or a result people want, in a line a stranger gets in a second. A feature, the app name or a price scores 1 or 2.
46
- 2. **Each slide earns the next swipe**: every slide has one job and a reason to go on; no filler slide, no slide that repeats the last.
47
- 3. **People would save or send it**: the middle slides hold something to keep or to send to a named person.
48
- 4. **The app is the payoff, not the opener**: it appears on slide N-1 on a real screenshot with one plain mention, never on slide 1 and never as a logo, badge or offer.
49
- 5. **Native look**: text boxes and photos feel like a person's post. Banner-ad signs (a logo lockup, a badge, a tagline stack, a call-to-action button) score 1 or 2.
50
-
51
- Act on the scores as below. Show them in one line, for example:
52
- `Slideshow: scroll-stop 4, next-swipe 3, save/send 4, app-as-payoff 4, native 5. Weakest: slide 3 repeats slide 2.`