CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

slice-workflow

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.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

88%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An excellent instruction-type skill body: a precisely sequenced 9-step workflow with mechanical validation gates, exact marker syntax, and concrete handoff templates, all written for a competent reader with near-zero padding. The only structural note is that everything lives inline in one file — several sections (port heuristics, migration slices) are natural candidates for reference files if the bundle grows.

DimensionReasoningScore

Conciseness

The body is dense and assumes full competence — it never explains hexagonal architecture, TDD basics, or what a port is, and every section carries kit-specific rules. Minor instances of padding ("Days may pass in between. That is its job.", the extended field-incident anecdote in step 8) keep it at the 'efficient; minor instances of over-explanation' anchor rather than the fully lean anchor 5.

4 / 5

Actionability

Guidance is fully concrete and executable in-domain: the exact WIP marker grammar `WIP(REQ-<AREA>-<NNN>)` with a runnable Rust snippet, a 9-step layer order naming specific gates (hex-lint, trace-audit, check-guard, mutants + CRAP), prescribed commit-subject prefixes, and a copy-paste layer-map template for handoffs. This matches the anchor where specific examples cover the common cases; it is well above the 'minor gaps' anchor 4.

5 / 5

Workflow Clarity

Steps 1–9 are explicitly sequenced with validation at each stage — contract suites certify the fake before upstream use (step 4), the definition of done in step 8 is mechanically checkable, and step 9 runs the full gate list (mutants + CRAP scoped to changed zones, trace-audit, check-guard). Feedback loops are explicit (STALE WIP fails the audit, untagged crates are a hard error), matching the anchor requiring clear sequence, explicit validation, and error-recovery loops.

5 / 5

Progressive Disclosure

No bundle files exist; the skill is a single ~205-line file with clear section headers and cross-skill pointers (refactoring-campaign, tracker-discipline, session-lifecycle) acting as references, though these are name-drops rather than links. Structure is good and nothing is buried, but content like the ~35-line port-design heuristics section could arguably live in a reference file, and there are no well-signaled one-level-deep file references, so it fits anchor 4 rather than 5.

4 / 5

Total

18

/

20

Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: it explicitly states both what the skill defines and when to use it, in third person, with a highly distinctive trigger condition tied to the kit's architecture vocabulary. Its main limitation is jargon density — trigger terms are precise for insiders but offer no natural synonyms or variations that would broaden matching.

Suggestions

Add one or two natural-language trigger variations (e.g. 'implementing one behavior end-to-end', 'new feature slice') so users who don't use the exact kit vocabulary still match.

Soften the jargon in the what-clause slightly (e.g. 'layer-by-layer implementation order with tests-first at each layer') so the defined artifacts are understandable without knowing the kit's terms.

DimensionReasoningScore

Specificity

The description lists several concrete artifacts it defines — "the double-loop TDD protocol, the sanctioned WIP-acceptance-test mechanism, the layer implementation order, and the slice definition of done" — but phrasing is jargon-heavy and contents-oriented rather than a comprehensive set of concrete actions, fitting the 'several specific actions; minor gaps' anchor rather than the comprehensive anchor 5.

4 / 5

Completeness

It explicitly answers both questions: "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" gives a concrete when, and the "Defines ..." sentence gives a clear what. This matches the anchor for explicitly answering both what and when with concrete trigger phrases; it is clearly above the anchor 4 where the 'when' is only loosely specified.

5 / 5

Trigger Term Quality

Terms like "vertical capability slice", "hexagonal zones", "port", "adapter", "use case", and "TDD" match what a user of this architecture kit would naturally say, giving good keyword coverage, but there are no synonyms or common variations of these phrases, so it falls short of the comprehensive anchor 5.

4 / 5

Distinctiveness Conflict Risk

The vertical-slice-across-hexagonal-zones framing with port conformance and WIP acceptance tests carves out a clear niche with distinct triggers; only marginal overlap with closely related kit skills (tdd-cycle, refactoring-campaign), matching the 'clear niche with distinct triggers; minimal conflict risk' anchor.

5 / 5

Total

18

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

igouss/gitweb-rs

Path

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

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.