kiro-steering-custom

Create custom steering documents for specialized project contexts

Quality

55%

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 ./tools/cc-sdd/templates/agents/antigravity-skills/skills/kiro-steering-custom/SKILL.md

Quality

Content

57%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 well-sectioned, mostly actionable instruction skill with concrete paths, tools, and an output template, but it is held back by redundant inlined principles, a missing referenced bundle file, a confusing dual Step/Workflow numbering, and only implicit validation for a file-creating workflow. It is functional but not tightly engineered.

Suggestions

Add an explicit validation checkpoint inside the workflow (e.g., after generating, verify the file does not duplicate core steering content and stays within 100-200 lines, with a fix-and-retry loop) to lift workflow_clarity above 3.

Reconcile the dual structure: merge "Step 1: Gather Context" into the single numbered Workflow so the sequence is linear and unambiguous.

Either create the referenced rules/steering-principles.md and inline only a one-line pointer to it, or drop the dangling reference and keep the principles inline without claiming a separate file — and move the 7-template catalog to a reference file with a one-line summary in SKILL.md.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient but carries redundancy: the Steering Principles are inlined as a list while also being referenced from rules/steering-principles.md, and the Notes section restates earlier points ("Templates are starting points", "Follow same granularity principles"), fitting 'mostly efficient but could be tightened' rather than the lean anchor 4.	3 / 5
Actionability	Guidance is concrete and executable for an instruction-only skill: specific file paths ({{KIRO_DIR}}/steering/{name}.md), named tools (Glob/Grep/Read), a 100-200 line target, and a copy-paste output template, with only the minor gap of no full example of a generated steering document, fitting 'mostly executable guidance; minor gaps'.	4 / 5
Workflow Clarity	Five numbered steps are sequenced, but validation is implicit (mentioned only in a separate Safety & Fallback section as "Ensure doesn't duplicate core steering content") rather than an integrated checkpoint, and a confusing dual structure (### Step 1 followed by a separate ## Workflow 1-5) muddies the sequence; per the guidelines, missing validation for a file-writing operation caps this at 3.	3 / 5
Progressive Disclosure	Section headers organize the content reasonably, but the body references rules/steering-principles.md which does not exist in the bundle, and the principles plus the 7-template list are inlined rather than split into reference files, fitting 'some structure but content that should be separate is inline' rather than the well-split anchor 4.	3 / 5
	Total	13 / 20 Passed

Description

53%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.

The description states a clear, third-person "what" with a recognizable niche, but it omits any "when to use" trigger guidance and offers only a single concrete action, leaving it middling across all dimensions. It reads as competent but incomplete rather than vague.

Suggestions

Add a "Use when..." clause naming natural trigger phrases (e.g., "Use when the user needs domain-specific steering like API standards, testing, or security guidelines beyond the core steering files").

Broaden the action list beyond a single verb to reflect the skill's real capabilities (e.g., "Create and customize steering documents... load templates, analyze codebase patterns, and generate...").

Include user-natural synonyms/extensions (e.g., "project memory", "domain steering", "specialized guidelines") to improve trigger term coverage and distinctiveness.

Dimension	Reasoning	Score
Specificity	"Create custom steering documents for specialized project contexts" names a concrete action (create) and a specific domain artifact (steering documents), but lists only one action with no breadth of capabilities, matching the '1-2 concrete actions, not comprehensive' anchor rather than the multi-action anchor 4.	3 / 5
Completeness	It clearly answers the "what" (create custom steering documents) but provides no "when"/trigger guidance at all, which per the judging guidelines caps completeness at 3; this is not anchor 2 because the "what" is clear rather than vague.	3 / 5
Trigger Term Quality	Terms like "custom steering documents" and "specialized project contexts" are relevant but domain-internal (Kiro jargon) with no "Use when..." phrasing or natural synonyms, fitting 'some relevant keywords but missing common variations' rather than the generic-only anchor 2 or the well-covered anchor 4.	3 / 5
Distinctiveness Conflict Risk	"Custom steering documents for specialized project contexts" carves a clear niche (specialized/custom steering) distinct from a presumed core-steering skill with only minor overlap risk, fitting 'mostly distinct; minor overlap risk' rather than the fully-distinct anchor 5 which would require explicit distinct triggers.	4 / 5
	Total	13 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: gotalab/cc-sdd
Path: tools/cc-sdd/templates/agents/antigravity-skills/skills/kiro-steering-custom/SKILL.md
Commit: e2a0c67

Reviewed: 5 days 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.