CtrlK
BlogDocsLog inGet started
Tessl Logo

implement-slice

Implements a single slice with Signal validation and unit tests. Agent-first — invoked by the slice-implementer subagent (under implement-mainspec). No human-in-the-loop; signal validation iterates up to a bounded `max_signal_iterations` (default 3) before reporting FAILURE.

60

Quality

69%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/sdd/implement-slice/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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.

The body is a clear, actionable instruction skill with a well-sequenced workflow and an explicit bounded feedback loop for signal validation. Its chief weakness is redundancy — the signal workflow and git/iteration prohibitions are stated in multiple places — which mildly hurts conciseness and organization.

Suggestions

Consolidate the signal workflow into one section; have the Workflow step reference 'Signal Processing' rather than restating it.

Add an explicit fix-and-retry loop for the unit-test step so its validation checkpoint matches the signal loop's rigor.

Dedupe the git/iteration-bound prohibitions between the Invocation Contract and Guidelines DON'Ts.

DimensionReasoningScore

Conciseness

Mostly efficient with clear TODO and workflow structure, but the Signal workflow is restated twice (Workflow step 4 and the 'Signal Processing' section) and the Guidelines DON'Ts repeat the workflow's bounds and git prohibitions, which could be tightened.

3 / 5

Actionability

Provides concrete, actionable guidance — explicit inputs/outputs, specific result reasons (signal_failure, test_failure, implementation_blocked), a copy-paste TODO structure, and exact invocation syntax ('skill: "[signal-name]"') — with only minor gaps since no executable code is shown.

4 / 5

Workflow Clarity

A clearly sequenced six-step workflow with an explicit signal validation feedback loop (fix, re-invoke, track iterations, cap, report FAILURE), but the unit-test step lacks an explicit fix-and-retry loop on failure, leaving a minor validation gap.

4 / 5

Progressive Disclosure

Well-organized into clear sections (Invocation Contract, Workflow, Signal Processing, TODO Structure, Guidelines) with no external references needed, though the redundancy between Workflow and Signal Processing is a minor organization gap keeping it just below 5.

4 / 5

Total

15

/

20

Passed

Description

71%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 specific, well-scoped description that clearly conveys its agent-first invocation context and concrete actions. Its main weakness is reliance on internal orchestration jargon over natural user trigger phrases, and the absence of an explicit 'Use when...' clause.

Suggestions

Add an explicit 'Use when...' trigger clause so the invocation condition is unambiguous.

Soften internal jargon (e.g. 'slice-implementer subagent', 'implement-mainspec') or pair it with a plainer framing so natural trigger terms are present.

Include common synonyms or phrasings a user would actually say when this skill is needed.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions ('Implements a single slice', 'Signal validation', 'unit tests', 'iterates up to a bounded max_signal_iterations', 'reporting FAILURE') with only minor coverage gaps, fitting the 'lists several specific actions' anchor.

4 / 5

Completeness

Clearly states what ('Implements a single slice with Signal validation and unit tests') and when ('invoked by the slice-implementer subagent under implement-mainspec'), though the 'when' is an invocation contract rather than an explicit 'Use when...' trigger phrase, so it sits just below a 5.

4 / 5

Trigger Term Quality

Relevant domain terms ('slice', 'Signal validation', 'unit tests') appear, but heavy internal jargon ('slice-implementer subagent', 'implement-mainspec', 'max_signal_iterations') crowds out the natural phrases a user would say, matching 'some relevant keywords but missing common variations'.

3 / 5

Distinctiveness Conflict Risk

Occupies a clear, narrowly-scoped niche (single-slice implementation under a specific orchestrator with Signal validation) with distinct triggers and minimal overlap risk with other skills.

5 / 5

Total

16

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
tdg-ninja/context-specs-factory-ai
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.