Skip to content

JasonColapietro/suede-creator-skills / skills/suede-newsroom

suede-newsroom

Verified

Suede Newsroom Skills. editorial pipeline with six role contracts, an inspectable campaign record, distinct distribution arguments, and performance feedback. Use when asked "build an AI content team" or to repair duplicated, generic, or unsourced agent content. NOT FOR: topics (suede-content-strategy), channel calendars (suede-social), scheduling (suede-marketing-loops), code lanes (suede-agent-teams), or flagship writing (suede-ship-copy).

FileKindSize
CARD.mdmarkdown4.5 KB
SKILL.mdskill md16.1 KB
agents/openai.yamlconfig456 B
evals/evals.jsonconfig7.9 KB
references/campaign-record.mdmarkdown4.9 KB
references/entryways.mdmarkdown5.6 KB
references/founder-content-loop.mdmarkdown18.7 KB
references/role-contracts.mdmarkdown7.9 KB
references/worked-contract.mdmarkdown2.2 KB

references/entryways.md

View on GitHub
# The seven entryways

An entryway is the door a reader walks through into one idea. Seven doors, one
idea, seven reasons to stop scrolling. Each entry gives the requirement, the
surfaces it survives on, the failure mode, and a worked line.

## Contents

- [Proof](#proof)
- [Mechanism](#mechanism)
- [Workflow](#workflow)
- [Risk](#risk)
- [Result](#result)
- [Critique](#critique)
- [Compression](#compression)
- [Surface fit](#surface-fit)
- [Sequencing](#sequencing)
- [When the source is thin](#when-the-source-is-thin)

---

## Proof

**Argues:** this is real, and here is the thing you can check yourself.

**Requires:** an artifact a stranger can inspect without trusting you: a
screenshot, dataset, receipt, before-and-after, or public URL.

**Failure mode:** posting the artifact with a caption that describes it. The
artifact is the argument; the caption says what it settles.

**Worked line:** "Four platform posts from one campaign. Same hook, four times.
Nobody chose that: the pipeline fed the finished draft to the repurposing step."

---

## Mechanism

**Argues:** here is why it works, at the level of cause.

**Requires:** a causal chain. "X happens because Y, which is why Z" passes; "X is
important for Y" does not.

**Failure mode:** restating what the thing is. A mechanism a reader could have
guessed from the name is a definition wearing a lab coat.

**Worked line:** "A finished draft carries exactly one argument. Anything derived
from it inherits that argument. That is why your five platform posts say the same
thing: not prompt quality, not model choice."

---

## Workflow

**Argues:** you can run this today.

**Requires:** ordered steps specific enough to follow without a follow-up
question.

**Failure mode:** steps that are really categories. "Do research" is a category;
"return three to seven claims, each with a URL" is a step.

**Worked line:** the role contract published on its own, actionable with no link.

---

## Risk

**Argues:** here is what breaks, and the conditions that break it.

**Requires:** a named failure mode with its trigger. A generic caution is not a
risk entryway.

**Failure mode:** hedging. "Results may vary" is not a risk; "this degrades the
moment two roles share one memory" is.

**Worked line:** "The failure is not that the agents are bad. It is that six of
them share one memory, so every specialist has read everything and distinguishes
nothing."

---

## Result

**Argues:** here is what it produced, and the conditions that produced it.

**Requires:** an outcome with context: what was measured, over what period,
under what conditions.

**Failure mode:** the naked number. A result with no conditions invites the
reader to assume them, and they will assume the flattering ones.

**Worked line:** "Three campaigns, same evidence packet, zero rework on the last
two. The first took four returns to get the claims traced."

---

## Critique

**Argues:** the common approach is worse than it looks, and here is how it fails.

**Requires:** the actual default, what most people do, plus the mechanism of
its failure. Critique without a named default is posturing.

**Failure mode:** attacking a strawman nobody runs, or naming a competitor rather
than an approach.

**Worked line:** "Every asset in the set can be individually good and the
campaign still fails. Quality per asset is not the axis. Distinctness is."

---

## Compression

**Argues:** here is the whole shape, in one line or one image.

**Requires:** the idea reduced far enough to repeat from memory.

**Failure mode:** compressing to a slogan. A compression a reader can repeat but
not unpack is a tagline.

**Worked line:** `idea -> research -> angle -> flagship -> distribution -> review
-> performance -> playbooks`, published as the diagram alone.

---

## Surface fit

An entryway that survives on one surface dies on another. Consumption pattern
decides, not character count.

| Surface | Entryways that carry it | Why |
|---|---|---|
| Short text feed | proof, critique, compression, result | the scroll rewards a single sharp claim |
| Professional feed | workflow, risk, result, mechanism | the operator lesson and the before-and-after |
| Carousel | workflow, compression, mechanism | sequence and structure are clearer shown |
| Video | mechanism, result, risk | tension, demonstration, and outcome speak well |
| Newsletter | mechanism, risk, workflow | room for nuance, conditions, and context |
| Long-form | all of them, combined | the flagship is where they meet |

Where the project's own surface playbook contradicts this table, the project
wins, say which one you followed.

## Sequencing

Two rules. **Lead with the largest outcome**, result or proof opens, compression
closes, and a reader arriving at any point can work backward to the flagship.
**Space the demanding entryways**, mechanism and risk ask more of a reader than
proof or compression, so alternate rather than stacking them.

A full set in order: result, mechanism, proof, workflow, critique, risk,
compression. Critique and risk sit late because both ask the reader to
reconsider something, which lands better once the week has shown the thing works.

In a short set, drop critique and risk first: they depend on context the set has
not built yet.

## When the source is thin

Not every idea supports seven doors. An idea with no proof object does not get a
proof asset, and inventing one is fabrication.

| Inventory rows filled | Realistic set size |
|---|---|
| 2–3 | two assets, take the strongest, skip the rest |
| 4–5 | three to four assets |
| 6–8 | up to seven |

Report the unused entryways and why each is unavailable. That list is often more
useful than the set: it names exactly what the next round of research must find.
writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deploymentStars: 323kUpdated Claude CodeCodexVerifiedInstall
xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release.Stars: 118kUpdated Claude CodeCodexVerifiedInstall