JasonColapietro/suede-creator-skills / skills/suede-ship-copy
suede-ship-copy
VerifiedProduce one high-stakes public draft with parallel research, agent-claim audits, message ownership, adversarial review, publish readiness, and an evidence record. Use when asked to "research and draft this launch page" or rigorously develop one landing page, email, post, README, ad, or store listing. Preserves requester-supplied facts and writes drafts only. NOT FOR: routine or bulk copy (use suede-copy), code changes (use suede-graph-flo-xr), or cleaning existing prose (use suede-deslop).
| File | Kind | Size |
|---|---|---|
| CARD.md | markdown | 5.5 KB |
| SKILL.md | skill md | 15.8 KB |
| agents/openai.yaml | config | 728 B |
| references/claim-origin-policy.md | markdown | 3.3 KB |
| references/phase-and-threshold-reference.md | markdown | 5.9 KB |
| references/worked-handoff.md | markdown | 1.9 KB |
| workflows/suede-ship-copy.js | script | 82.4 KB |
references/phase-and-threshold-reference.md
View on GitHub# Suede Ship Copy Skills: Phases and Thresholds
## The graph
Twelve phases, parallel wherever the edges are not real. This is the logical DAG;
the script's twelve `phase()` labels fold **Claim audit** into `Gaps` and **Collision
check** into `Outline`, and split **Review and refute** and **Gate and handoff** into
two each. When narrating live progress use the script's labels: there is no phase
called "Claim audit" in `/workflows`.
1. **Intake**: sources, the requester's own statements transcribed into the
permitted set untouched, the currently published text captured verbatim, voice
references drawn from shipped copy, protected strings, the surface's hard
limits, hazards. Manifest only.
2. **Research**: five blind lenses: product truth, audience, market, voice,
surface law. Each searches a different way because one angle never finds
everything. Every fact carries a `file:line`, URL, sha, or timestamp.
3. **Gaps**: a completeness critic names what went unread, then one bounded fill
round (first 2 gaps; the rest ride to the handoff as unread).
4. **Claim audit**: the load-bearing skeptic, pointed only at agent output. Every
agent-generated fact is opened against its source and returns `holds`,
`overstated`, `unsourceable`, or `stale`. Dropped claims leave the set;
overstated ones are narrowed to what the source supports. The requester's
givens are not in this list and a verdict returned against one is discarded
unread. **Nothing downstream may assert a claim outside the permitted set:
surviving agent claims plus every given.**
5. **Angles**: three postures generated blind to each other: problem-first,
outcome-first, wedge. Each declares whether a competitor could publish its
headline verbatim, which is a failing grade rather than a formatting field.
6. **Outline**: the planner judges the three angles, grafts the best of the
runners-up, and writes a section map: one message per section, citations drawn
only from the surviving claims, an observable acceptance question per section.
High effort by design. Then a red team. One revision round follows **only** if the
red team returned a fatal objection or two serious ones; otherwise the map stands
and the objections ride to the handoff. Do not narrate a revision that did not run.
7. **Collision check**: a pure function, no agent. Duplicate message ownership,
a citation outside the claim set, a protected string assigned zero or twice, or
budgets over the ceiling all halt the run.
8. **Draft**: one writer per section, in parallel. Each sees its neighbours' jobs
so transitions are possible, and never their text. A fact outside its citation
list becomes `[AUTHOR: supply X]`, never an invention.
9. **Assemble**: a barrier. Transitions written, repetition cut, one voice,
budget enforced, placeholders and protected strings preserved byte-exact.
10. **Review and refute**: four lenses on the whole piece (cold read, assertion
audit, conversion, slop). Findings aimed at a given are dropped by a pure
function first, then two independent verifiers take each surviving blocker or
major, refute by default. **Both must fail to refute** for a finding to
survive; unanimity, not majority, because rewriting a line that was fine has a
real cost in a short piece.
11. **Polish**: one reviser for confirmed blockers (prose has no file-level
disjointness, so parallel editors of one string produce a conflict with no
merge tool), then Suede Slop Stop scored out of 50, then the graphic spec and
the channel package in parallel.
12. **Gate and handoff**: deterministic checks (open placeholders, missing
protected strings, house-style dash violations, word count, fields over limit) run in the script
where no agent can argue with them, then a read-only publish-readiness verifier
for drift, truth at the source, rights, and reversibility. Drift and truth-at-the-source
are scoped to agent-generated claims; the rights check is scoped to third-party material,
so a customer result you supplied cannot come back as a permissions risk wearing a
rights label. Then the evidence record.
## Thresholds
Every gate in this workflow resolves to a number or a command:
| Check | Threshold |
|---|---|
| Requester's own claims audited | Never. 0 reach the audit. They reach the refute and gate prompts only as named out-of-scope context, never as a target |
| Claim may be asserted | Present in the permitted set (surviving agent claims + every given). Anything else is `[AUTHOR: supply X]` |
| Finding survives review | 2 of 2 verifiers fail to refute it |
| Findings refuted per run | First 4 blockers/majors; the remainder are logged, never silently dropped |
| Gap fills | First 2; the rest are reported as unread |
| Sections | 3-5 preferred, 7 ceiling |
| Slop Stop score | 35/50 or the piece is `REVISE`; advisory score only |
| Channel field | `chars <= limit` per field, counted and reported individually |
| Word count | `<= wordBudget × 1.1` when a budget was supplied; unenforced when it was not |
| Em-dash violations | 0 in newly written prose when `houseStyle.emDashes` is `avoid`; permitted when `allow`. Protected strings and givens are exempt |
| Open placeholders | 0, or Status is "ready for author", never "reviewed" |
| Placeholders vanished since draft | 0. A placeholder the assembler or deslop pass resolved away is a fabrication |
| Stalled sections | 0. A writer returning `blocked`, `needs-context`, or nothing leaves a hole in the piece |
The six rows from Channel field through Stalled sections are **hard gates**:
any one fails and `hardMechanical` forces `copyVerdict: hold`.
Two more hard gates have no row because they are
liveness rather than quality: a channel-package agent or a deslop agent that
returned nothing also forces `hold`.
The preceding rows describe claim scope, review, and planning constraints.
The Slop Stop score alone only moves the verdict to `ship-with-caveats`, never to
`hold`. Do not report a 22/50 score as a hold.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |