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

78%

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

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, actionable skill body with strong progressive disclosure and copy-paste-ready commands. The main gaps are mild conciseness redundancy and a workflow that lists validation checks but does not spell out the fix-and-retry recovery loop.

Suggestions

Remove the duplicated bash command between Step 2 and Step 3 — show the command once, then show only the '… | claude -p --allowedTools …' pipeline addition in Step 3.

Drop or compress the 'The script: 1. Loads the idea JSON …' enumeration in Step 2; Claude can read the script, so a one-line summary of its role is enough.

Add an explicit recovery branch to Step 4, e.g. 'If any check fails, re-run the prompt builder or edit the generated files and re-score until the dual-axis-skill-reviewer threshold is met.'

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient but includes tighten-able redundancy: the Overview rephrases the frontmatter description, Step 2 restates the script's internals ('Loads the idea JSON / Reads all three reference files / Lists existing skills / Outputs a prompt') that Claude could learn by reading the script, and Steps 2–3 repeat the same bash command. This fits the level-2 'mostly efficient but could be tightened' anchor rather than the every-token-earns-its-place level-3.	2 / 3
Actionability	Steps 2 and 3 give concrete, copy-paste-ready bash commands with full paths and flags ('python3 skills/skill-designer/scripts/build_design_prompt.py --idea-json … --skill-name … --project-root . \| claude -p --allowedTools …'), matching the level-3 'fully executable code/commands; copy-paste ready' anchor rather than the pseudocode/missing-details level-2.	3 / 3
Workflow Clarity	The four steps are clearly sequenced and Step 4 provides a validation checklist with a scoring-threshold gate, but there is no explicit error-recovery feedback loop ('if verification fails, fix and re-run') — the recovery is only implicit. This lands on the level-2 'validation gaps / checkpoints implicit' anchor rather than the level-3 anchor that requires feedback loops for error recovery.	2 / 3
Progressive Disclosure	The SKILL.md is a concise overview whose Resources section points to three verified reference files (skill-structure-guide.md, quality-checklist.md, skill-template.md) and one script (build_design_prompt.py), each with a one-line description; the references are one level deep with no chaining, matching the level-3 'clear overview with well-signaled one-level-deep references' anchor.	3 / 3
	Total	10 / 12 Passed

Description

85%

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, third-person description that answers both what the skill does and when to use it, with a distinct niche and low conflict risk. Its only weakness is trigger-term naturalness — the 'Use when' clause is framed around the internal pipeline mechanism rather than user-facing language.

Suggestions

Rewrite the 'Use when…' trigger to lead with natural user intent, e.g. 'Use when creating a new Claude skill from a structured idea spec, or when bootstrapping a skill directory from an idea JSON file.'

Add common natural phrasings users would actually say ('create a skill', 'generate a skill', 'bootstrap a new skill') alongside the pipeline framing.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — '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)' — matching the 'lists multiple specific concrete actions' anchor rather than the single-domain score-2 anchor.	3 / 3
Completeness	It clearly answers both 'what' (design skills / produce a CLI prompt that builds the skill directory) and 'when' via an explicit 'Use when…' clause, satisfying the level-3 anchor and avoiding the level-2 cap that applies when trigger guidance is only implied.	3 / 3
Trigger Term Quality	The trigger clause 'Use when the skill auto-generation pipeline needs to produce a Claude CLI prompt' leans on internal-pipeline jargon rather than phrases a user would naturally say (e.g., 'create a new skill', 'generate a skill'), so it has some relevant keywords but misses common natural variations — not the level-3 'good coverage of natural terms'.	2 / 3
Distinctiveness Conflict Risk	It carves a clear niche (auto-generation pipeline producing skill design prompts) with triggers unlikely to fire for other skills, matching the level-3 'clear niche with distinct triggers' rather than the overlapping level-2 anchor.	3 / 3
	Total	11 / 12 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: 62a1635

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.