JasonColapietro/suede-creator-skills / skills/suede-parity-contract
suede-parity-contract
VerifiedSuede Parity Contract Skills. cross-surface parity contracts generated from live reference constants and asserted through follower behavior. Use when asked "these app and web thresholds disagree" or when rules are copied across web, mobile, docs, or services. NOT FOR: choosing the correct shipped value, diff review (suede-code), merge-gate setup (suede-ci-gate), or search audits (suede-seo-audit).
| File | Kind | Size |
|---|---|---|
| CARD.md | markdown | 4.3 KB |
| SKILL.md | skill md | 7.8 KB |
| agents/openai.yaml | config | 1.1 KB |
| references/worked-contract.md | markdown | 2.3 KB |
agents/openai.yaml
View on GitHubinterface:
display_name: "Suede Parity Contract Skills"
short_description: "Cross-surface constants held by a generated contract"
default_prompt: "Use $suede-parity-contract when the same rule, threshold, ladder or scoring table is implemented on more than one surface and the values are being kept in step by hand. Name exactly one reference surface, build a contract that imports its live constants rather than retyping them, add a staleness test so the committed file cannot drift from the code, vendor a byte-identical copy to every follower, and make each follower assert through public behaviour rather than by reimplementing the reference formula. Record every divergence you find under knownDivergences with the value on each surface and a reason, and guard that the divergence list is exactly the expected set. Prove non-vacuity on both sides in the same run: change a constant, watch the named test fail, restore it. Never decide which surface is correct and never change a shipped constant as a side effect: halt, name the divergence, offer the options, and wait."
policy:
allow_implicit_invocation: true
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: 196k | Updated | Claude CodeCodex | Verified | Install |