skill-designer

Design new Claude skills from structured idea specifications. Use when the skill auto-generation pipeline needs to produce a Claude CLI prompt that creates a complete skill directory (SKILL.md, references, scripts, tests) following repository conventions.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/skill-designer/SKILL.md

Quality

Content

86%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 content is highly actionable with copy-paste-ready commands, a clear sequenced workflow with validation, and excellent progressive disclosure pointing to real reference files. The only meaningful gap is minor redundancy and the absence of an explicit retry-on-validation-failure feedback loop.

Suggestions

Add an explicit error-recovery loop in Step 4 (e.g., 'If validation fails or the score is below threshold, revise the generated skill and re-run validation before proceeding').

De-duplicate the build_design_prompt.py invocation between Step 2 and Step 3 by showing the full pipeline command once and referencing it.

Tighten the Overview so it does not restate the frontmatter description verbatim, trimming tokens that do not add new information.

Dimension	Reasoning	Score
Conciseness	The body is well-organized and mostly lean, with only minor trimmable redundancy such as the Overview restating the frontmatter purpose and the full command appearing in both Step 2 and Step 3, fitting anchor 4 rather than the fully lean anchor 5.	4 / 5
Actionability	It provides copy-paste-ready, fully executable commands with exact CLI invocations ('python3 skills/skill-designer/scripts/build_design_prompt.py --idea-json ... \| claude -p --allowedTools ...') plus explicit exit codes, matching the anchor 5 for fully executable guidance covering the common cases.	5 / 5
Workflow Clarity	The four steps are clearly sequenced and Step 4 includes explicit validation (verify SKILL.md exists, directory structure, score meets threshold), but there is no explicit error-recovery feedback loop if validation fails, placing it at anchor 4 rather than anchor 5.	4 / 5
Progressive Disclosure	The body is a concise overview with well-signaled, one-level-deep references in the Resources section (skill-structure-guide.md, quality-checklist.md, skill-template.md, build_design_prompt.py), all of which are real bundle files, matching the anchor 5 for clear navigation and appropriate content splitting.	5 / 5
	Total	18 / 20 Passed

Description

67%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 clearly answers both what the skill does and when to use it, with concrete actions and a distinct niche. Its main weakness is trigger-term quality: the 'when' relies on pipeline-internal jargon rather than the natural language a user would actually say.

Suggestions

Rewrite the 'Use when' clause in natural user-facing terms (e.g., 'Use when designing or bootstrapping a new Claude skill, or when the skill-generation pipeline needs a design prompt').

Add common synonyms users might say such as 'create a skill', 'scaffold a skill', or 'generate a skill' to broaden trigger coverage.

Consider listing the concrete deliverables more comprehensively (e.g., 'with test scaffolding and quality scoring') to push specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Phrases like 'Design new Claude skills from structured idea specifications' and 'produce a Claude CLI prompt that creates a complete skill directory (SKILL.md, references, scripts, tests)' list several concrete actions with only minor coverage gaps, fitting the anchor 4 rather than 5 which requires fully comprehensive coverage.	4 / 5
Completeness	It states both the 'what' (design skills / produce a CLI prompt that builds a skill directory) and an explicit 'when' clause ('Use when the skill auto-generation pipeline needs to produce a Claude CLI prompt'), but the 'when' is narrow and technical rather than broadly concrete, so it lands at anchor 4 instead of 5.	4 / 5
Trigger Term Quality	The trigger 'Use when the skill auto-generation pipeline needs to produce a Claude CLI prompt' relies on pipeline-specific jargon rather than the natural phrases a user would say ('design a skill', 'generate a skill'), and lacks synonyms or common variations, matching anchor 3.	3 / 5
Distinctiveness Conflict Risk	The skill occupies a clear niche (skill auto-generation / design prompt builder) with distinct triggers and minimal overlap risk, but the trigger phrasing is narrow enough that it sits at anchor 4 rather than the fully distinct anchor 5.	4 / 5
	Total	15 / 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: tradermonty/claude-trading-skills
Path: skills/skill-designer/SKILL.md
Commit: 51c7907

Reviewed: ~6 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.