CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

sy-slice-spec

Create one selected trace or tracker slice spec with acceptance criteria, constraints, validation, and exit conditions. Use when exactly one slice has been selected and needs a buildable contract before implementation planning.

Quality

78%

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 ./Plugins/synaipse-harness/skills/sy-slice-spec/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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.

A well-structured, lean lifecycle-stage skill with explicit validation gates, error-recovery routing, and exemplary progressive disclosure through verified one-level references. Its weakest area is actionability: the procedure stays abstract and never names the concrete commands or artifact schema it delegates to the reference files.

Suggestions

Name the actual plugin validation and SDK proof commands (or at least one concrete example invocation) in the Validation section instead of the generic 'run plugin validation and SDK proof commands from the repository wrapper'.

Replace the self-referential 'Perform only the work owned by slice-spec' with a concrete enumeration of what this stage produces (e.g., the spec's required fields or a pointer to the contract.yaml output schema).

Remove the 'When to use' section duplicating the frontmatter description verbatim, or merge its content into Required inputs to save tokens.

DimensionReasoningScore

Conciseness

The ~55-line body is lean with no explanations of concepts Claude already knows, but 'When to use' duplicates the frontmatter description verbatim and 'Handoff' largely restates Procedure step 5, so a few tokens could be trimmed.

4 / 5

Actionability

Procedure steps and classification labels ("pass, fail, blocked, or not_checked") are concrete, but no actual commands are given — "run plugin validation and SDK proof commands from the repository wrapper" never names them, and "Perform only the work owned by slice-spec" is self-referential, deferring key details to contract.yaml.

3 / 5

Workflow Clarity

A clear 5-step sequence with an explicit fail-fast validation gate ("stop at the first failed required gate... do not proceed to downstream stages") and a Failure modes section giving recovery routing; the gap is that the validation checks themselves are described only vaguely ("the smallest relevant local check").

4 / 5

Progressive Disclosure

The body is a concise overview with four clearly labeled, one-level-deep references (contract.yaml, evals.yaml, task-profile.json, source-context.yaml), all of which exist as real, substantive files in references/; content is appropriately split with easy navigation.

5 / 5

Total

16

/

20

Passed

Description

76%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 with an explicit and well-bounded 'Use when' clause and a concrete enumeration of deliverables. Its main weaknesses are jargon-heavy trigger terms without natural synonyms and a single-action framing that limits specificity at the top of the scale.

Suggestions

Add one or two natural-language trigger phrases or synonyms (e.g., 'write the slice contract', 'define the slice for build') alongside the stage jargon so the description matches how the request might actually be phrased.

Name the sibling stages it must be distinguished from in the description (e.g., 'after slice selection, before execution-plan') to further reduce overlap risk with adjacent lifecycle skills.

DimensionReasoningScore

Specificity

The description names the domain ("trace or tracker slice spec") and enumerates four concrete deliverable components ("acceptance criteria, constraints, validation, and exit conditions"), but describes a single create action rather than multiple distinct actions, leaving minor coverage gaps.

4 / 5

Completeness

It clearly answers both what ("Create one selected trace or tracker slice spec with acceptance criteria, constraints, validation, and exit conditions") and when ("Use when exactly one slice has been selected and needs a buildable contract before implementation planning") with an explicit, concrete trigger condition.

5 / 5

Trigger Term Quality

Terms like "slice spec", "trace or tracker", "buildable contract", and "implementation planning" are domain-precise for the orchestrator context but jargon-heavy, with no synonyms or natural phrasing variations a user would spontaneously say.

3 / 5

Distinctiveness Conflict Risk

The slice-spec stage is a distinct niche bounded by "exactly one slice" and "before implementation planning", though adjacent lifecycle stages (e.g., execution-plan or reframe, named in the body) could plausibly compete for similar triggers.

4 / 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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

jscraik/Agent-Skills

Path

Plugins/synaipse-harness/skills/sy-slice-spec/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.