workshop

Workshop coach for the Research Desk (SEC agents) workshop. Use when the user types /workshop, asks for a workshop act or module ("act 2", "next act", "where am I"), wants a TODO(workshop-N) implemented or explained, or asks for help following WORKSHOP.md.

Quality

91%

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

Quality

Content

88%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 high-quality, highly actionable workshop-coach body with exact code, explicit validation checkpoints, and clear sequencing. The main weakness is that it is a single large monolithic file where some act-by-act detail could be split into referenced materials.

Suggestions

Move the per-act detailed stub specifications into a referenced file (e.g. references/acts.md) and keep SKILL.md as the overview, to improve progressive disclosure.

Tighten the 'Teach:' paragraphs to the single platform concept each act demonstrates, trimming restated context.

Add an explicit pointer at the top to WORKSHOP.md as the canonical detailed reference so the overview-vs-detail split is signaled immediately.

Dimension	Reasoning	Score
Conciseness	The body is dense and actionable with little generic padding, and the platform-API specifics it explains (sessions.events.send, custom_tool_result, define_outcome) are not things Claude reliably knows, so the explanation earns its place; a few 'Teach:' paragraphs could still be trimmed.	4 / 5
Actionability	Each TODO stub gives copy-paste-ready code with exact method calls and arguments, plus concrete commands (npm run dev, npm run typecheck, rg -l "TODO(workshop-") — fully executable and covering the common cases.	5 / 5
Workflow Clarity	Acts 0–6 are clearly sequenced with explicit validation checkpoints (typecheck, restart dev server, read-only status checks) and feedback loops (rule 9: read the error together, fix forward); the one destructive op ('reset progress') requires confirmation.	5 / 5
Progressive Disclosure	Well organized with clear sections and one-level-deep, clearly signaled references to repo files (WORKSHOP.md, prompts/*.md, skills/edgartools/SKILL.md), but the ~110-line body is monolithic with no bundle files offloading the act-by-act detail.	4 / 5
	Total	18 / 20 Passed

Description

95%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, third-person description that clearly states both what the skill does and when to use it, with concrete natural-language triggers and synonyms. The only minor gap is that the 'what' is a single phrase rather than an enumerated action list.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('asks for a workshop act or module', 'wants a TODO(workshop-N) implemented or explained', 'asks for help following WORKSHOP.md') tied to a named domain, but the 'what' is stated once as 'Workshop coach' rather than enumerated comprehensively.	4 / 5
Completeness	Explicitly answers both: 'Workshop coach for the Research Desk (SEC agents) workshop' (what) and 'Use when the user types /workshop, asks for...' (when) with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Natural phrases a participant would actually say are covered with synonyms — '/workshop', 'act 2', 'next act', 'where am I', 'act or module', 'TODO(workshop-N)' — matching the comprehensive-synonym anchor.	5 / 5
Distinctiveness Conflict Risk	A very specific niche (Research Desk SEC-agents workshop, WORKSHOP.md, TODO(workshop-N) markers) with distinct triggers means minimal risk of firing for an unrelated skill.	5 / 5
	Total	19 / 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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: anthropics/cwc-workshops
Path: research-desk/.claude/skills/workshop/SKILL.md
Commit: 068b84b

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.