CtrlK
BlogDocsLog inGet started
Tessl Logo

gitweb-rs

github.com/igouss/gitweb-rs

SkillAddedReview
adr-discipline

.claude/skills/adr-discipline/SKILL.md

Use before proposing any architectural, modelling, or dependency decision; after making one; or when tempted to restructure existing code whose shape seems wrong. ADRs are the memory that stops agents from relitigating settled decisions across sessions.

62

golden-parity

.claude/skills/golden-parity/SKILL.md

Use when building or extending a golden-master/differential conformance harness against a reference implementation — ports, rewrites, legacy capture. Defines the two-tier oracle, determinism engineering at capture time, the divergence-fencing pattern, and the golden ratchet. testing-strategy says WHERE goldens belong; this skill says HOW to build a harness that never flickers and never lies.

71

handoff

.claude/skills/handoff/SKILL.md

Compact the current conversation into a handoff document for another agent to pick up.

61

memory-discipline

.claude/skills/memory-discipline/SKILL.md

Use when deciding whether something learned this session is worth persisting to agent memory, when writing or updating a memory file, and when a saved memory turns out to be wrong. Defines the four memory genres, the selection bar, the evidence-anchor rule, and correction discipline. The repo carries specs/ADRs/beads; memory carries what none of those can.

69

quality-gates

.claude/skills/quality-gates/SKILL.md

Use when designing, wiring, debugging, or being blocked by quality-gate infrastructure — git hooks, lint matrices, exception files, complexity gates, Stop hooks. Defines the three-tier latency topology, the vacuous-green problem (gates must prove they FIRED), exception-file hygiene, and gate failure UX. verification-ratchet defines WHAT the checks are; this skill defines how the machinery that runs them stays honest.

64

refactoring-campaign

.claude/skills/refactoring-campaign/SKILL.md

—

Invalid
rust-determinism-engineering

.claude/skills/rust-determinism-engineering/SKILL.md

Use when writing deterministic tests, golden/snapshot suites, or any Rust whose output must be byte-stable across runs, machines, and parallel test execution — or when a test is flaky. In greenfield there is no reference oracle, so your own goldens ARE the spec and a flaky golden is a spec that lies. Covers the single-entropy-fixture funnel, stable hashing/ordering, golden checksum-gating, the four flaky-test causes, seeded randomness, and cross-architecture drift. testing-strategy says WHERE determinism is injected; this is the Rust-deep HOW.

66

rust-fail-closed-hardening

.claude/skills/rust-fail-closed-hardening/SKILL.md

Use when constructing a domain type with invariants, validating untrusted or numeric input, building subprocess argv, sharing state behind a lock, writing a predicate that gates a release/admission decision, or auditing safe Rust for the silent ways it produces and propagates a wrong value. Greenfield has no reference oracle to catch a wrong-but-non-crashing result — so the wrong value must be made un-constructable, rejected at the boundary, and never allowed to poison state. Fail closed.

68

session-lifecycle

.claude/skills/session-lifecycle/SKILL.md

Use at the START of every working session, at the END of every working session, and immediately after any context compaction/summarization. Defines the orientation protocol (first steps), the handoff protocol (last steps), and how to exploit the fact that agent sessions start from a clean state.

70

slice-workflow

.claude/skills/slice-workflow/SKILL.md

Use when a requirement spans a full vertical capability slice across multiple hexagonal zones — domain entity, port, adapter(s), use case, render/web — plus port conformance. Defines the double-loop TDD protocol, the sanctioned WIP-acceptance-test mechanism, the layer implementation order, and the slice definition of done.

72

spec-authoring

.claude/skills/spec-authoring/SKILL.md

Use when writing a new requirement, defining a new feature, or when asked to implement behavior that has no requirement in specs/. Produces an EARS requirement with an FDD-style feature name, anchor Gherkin scenarios, and a stable REQ ID. Also use when an existing requirement must change.

72

tdd-cycle

.claude/skills/tdd-cycle/SKILL.md

Use during the implementation step of any requirement — after the spec exists and before declaring done. Defines the red/green/refactor loop, the Three Laws adapted for agents, the mandatory refactor step with its quality gates (Four Rules of Simple Design, CRAP threshold), and the backtracking protocol for when you get stuck.

62

testing-strategy

.claude/skills/testing-strategy/SKILL.md

Use when deciding WHAT kind of test a piece of code needs — before writing tests for a new module, when unsure whether something deserves a property test, an example test, a contract test, or an integration test, or when scoping where cargo-mutants should run. Maps test types onto hexagonal zones. The verification-ratchet skill defines HOW to write each kind; this skill defines WHERE each kind belongs.

68

traceability

.claude/skills/traceability/SKILL.md

Use when auditing the link between requirements and tests, before changing or deleting a requirement, when deciding whether a test is allowed to exist, or when asked "what verifies X" / "why does this test exist". Convention-based; the audit script is Babashka, ad-hoc searches use ripgrep.

67

tracker-discipline

.claude/skills/tracker-discipline/SKILL.md

Use when creating, decomposing, claiming, closing, or blocking on a work item (bead) — and whenever the words "deferred", "out of scope", or "follow-up" are about to leave your mouth. Defines bead anatomy for agent consumers, the standing meta-beads, follow-up capture, dependency hygiene, and the tracker as an inter-session message bus.

64

verification-ratchet

.claude/skills/verification-ratchet/SKILL.md

Use when implementing a requirement, writing tests, deriving property tests from a spec's candidate laws, running and triaging cargo-mutants results, or checking the CRAP complexity gate. Defines what counts as real verification and the only legal responses to failing checks, surviving mutants, and CRAPpy functions.

70