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.

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

73%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 provides a clear, well-sequenced workflow with strong validation semantics and bounded feedback loops, and it is highly actionable for an instruction-only skill. Its main weakness is redundancy — the Signal workflow and several rules are stated multiple times — which inflates token cost without adding information.

Suggestions

Merge the 'Signal Processing' section into Workflow step 4 to eliminate the duplicated signal workflow and repeated iteration-cap text.

State the cap and default for `max_signal_iterations` once (in the Invocation Contract inputs) and reference it elsewhere instead of repeating it.

Specify how to run unit tests (command or framework) so the final workflow step is fully executable.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient but contains real duplication: the Signal workflow appears twice (Workflow step 4 and the entire 'Signal Processing' section), the `max_signal_iterations` default of 3 is repeated three times, and the no-git/no-PR rule appears twice. It is noticeably below anchor 4 because a whole section is redundant.	3 / 5
Actionability	Guidance is concrete for an instruction-only skill: exact TODO strings, enumerated failure reasons (`signal_failure`, `test_failure`, `implementation_blocked`), explicit inputs/outputs, and a DO/DON'T list. Not a 5 because 'invoke `skill: "[signal-name]"`' is not an executable command and no test command/framework is specified.	4 / 5
Workflow Clarity	The six-step numbered workflow has an explicit validation checkpoint (Signal validation), a bounded fix→retry feedback loop with an iteration cap, and explicit failure reporting with enumerated reasons — matching the anchor for clear sequence with validation steps and error-recovery feedback loops.	5 / 5
Progressive Disclosure	A single-file skill (~90 lines) with clean, well-signaled sections (Invocation Contract, Workflow, TODO Structure, Guidelines) and no external references needed. Not a 5 because the internal duplication could be consolidated for easier navigation.	4 / 5
	Total	16 / 20 Passed

Description

62%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-bounded description that clearly states what the skill does and its failure semantics, but it lacks a natural 'Use when...' trigger clause and leans on internal jargon (slice, Signal, subagent names) rather than terms a caller would naturally use. Distinctiveness is good thanks to the named invocation context.

Suggestions

Add an explicit trigger clause (e.g., 'Use when the slice-implementer subagent is asked to implement one slice from a mainspec') to lift completeness.

Include natural-language synonyms or variations of the key terms (e.g., 'implement a slice', 'signal check', 'slice unit tests') so the description surfaces in skill matching.

Briefly state what Signal validation consists of so the 'what' is fully concrete.

Dimension	Reasoning	Score
Specificity	The description lists several concrete actions — "Implements a single slice with Signal validation and unit tests" and bounded iteration "up to a bounded `max_signal_iterations` (default 3) before reporting FAILURE" — with only minor gaps in coverage. It falls short of a 5 because the scope of Signal validation itself is not elaborated.	4 / 5
Completeness	The "what" is clear (implement a slice with Signal validation and unit tests), and the "when" is only stated as invocation mechanics ("invoked by the slice-implementer subagent (under implement-mainspec)"). There is no 'Use when...' clause or equivalent user-facing trigger guidance, which caps completeness at 3.	3 / 5
Trigger Term Quality	Relevant keywords exist ("slice", "Signal validation", "unit tests", "slice-implementer") but they are domain jargon; common natural variations a user or dispatcher would say are missing. Not a 4 because the natural trigger phrases are largely absent.	3 / 5
Distinctiveness Conflict Risk	Terms like "single slice", "Signal validation", `max_signal_iterations`, and the named subagent context carve a mostly distinct niche with minimal overlap risk. Not a 5 because "Implements a single slice" could still overlap with generic implementation skills in a larger skill ecosystem.	4 / 5
	Total	14 / 20 Passed

Validation

100%

Warnings & errors only

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: tdg-ninja/context-specs-factory-ai
Path: skills/sdd/implement-slice/SKILL.md
Commit: 3a7a725

Reviewed: 2 hours ago

Table of Contents

Discovery Implementation Validation

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.