Skip to content

mikeparcewski/wicked-garden / skills/draft

wicked-garden-draft

Verified

The quality floor for DOCUMENT deliverables drafted from a repo — brochures, one-pagers, flyers, pages, decks, memos — guidance plus a self-check before "done". Three floors: (1) READABLE — every text/background pair ≥ 4.5:1 (WCAG AA; 3:1 for large text) on COMPOSITED colours, print text ≥ 7pt; (2) SIZED TO THE BRIEF — the RENDERED page count honours the brief's page budget; (3) GROUNDED — every number, URL and claim cites a repo path, mocks visibly labelled, no placeholder ships. Use when: "draft a brochure / one-pager / page / deck / memo about <repo>", "print-ready A4 / Letter", "make it two pages", "is this brochure readable / grounded", before declaring a wicked-interactive draft/edit/revision done, or as the skill a governed drafting run (wicked-crew `interactive-*`) follows. A brief's `Kind:` line (narrative, status update, message, …) adds that kind's ref. NOT for code documentation (the engineering documentarian) or a running app's accessibility audit (the product or qe a11y skills).

FileKindSize
SKILL.mdskill md14.0 KB
refs/claims.mdmarkdown4.7 KB
refs/demo-script.mdmarkdown1.9 KB
refs/design-floor.mdmarkdown4.8 KB
refs/meeting-prep.mdmarkdown1.9 KB
refs/message.mdmarkdown1.6 KB
refs/narrative.mdmarkdown1.9 KB
refs/operating-model.mdmarkdown2.1 KB
refs/respond.mdmarkdown3.9 KB
refs/rework.mdmarkdown4.1 KB
refs/self-check.mdmarkdown7.0 KB
refs/status-update.mdmarkdown1.7 KB

refs/operating-model.md

View on GitHub
# Kind: operating model

Who does what: the roles, their responsibilities, who decides what, and the cadences that keep the
work moving, as a document a team can adopt. The brief's `Kind: operating model.` line selects this
ref (the **Roles and operating model** card). The skill's three floors still apply.

## Shape

1. **Scope:** the team or programme, and the work this model covers.
2. **Roles:** each role with its purpose and three to six responsibilities. Roles, not people:
   name a person only when a source names them in that role.
3. **Responsibility matrix** (RACI): one row per key activity or decision, one column per role,
   each cell R (does it), A (accountable), A/R (accountable and does it), C (consulted), I
   (informed) or empty.
4. **Decision rights:** which decisions each role makes alone, which need agreement, and how a
   disagreement is escalated, and to whom.
5. **Cadences:** each recurring meeting or ritual with its purpose, frequency, owner, inputs and
   outputs. A cadence with no output is cut.
6. **Interfaces:** how the team takes in work and hands it on (the intake channel, the hand-over
   artefact, who signs off).
7. **Open questions:** what the sources leave undecided.

## Rules

- **Exactly one A per row** (an `A/R` counts as it), and at least one R or `A/R`. A row with two accountable roles is the
  disagreement the model exists to settle: name it under open questions.
- **Observed or proposed, labelled.** What the sources show the team does today (a CODEOWNERS file,
  a process document, a recurring meeting) is cited as current. What you propose is labelled
  "proposed", so a reader can tell the two apart.
- **Fit the team's size.** A five-person team does not get twelve roles or a weekly steering
  committee; keep only what the sources' scale supports.
- **Sized:** two pages unless the brief names a budget (self-check `--pages 2`). The matrix may be
  its own page.

## Never

- assign a named person a role, a responsibility or an authority the sources do not give them;
- present a proposed model as the team's current practice;
- leave a decision with no accountable role.
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: 472kUpdated Claude CodeCodexVerifiedInstall
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: 472kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.Stars: 194kUpdated Claude CodeCodexVerifiedInstall