agent-supply-chain-newsletter
Generate the Agent Supply Chain newsletter by researching team activity on GitHub and Confluence, then creating a Confluence draft and Gmail draft
83
80%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/agent-supply-chain-newsletter/SKILL.mdQuality
Discovery
82%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong, specific description for a niche workflow skill. It clearly names the concrete actions and tools involved, and the unique product name makes it highly distinctive. The main weakness is the lack of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill.
Suggestions
Add a 'Use when...' clause, e.g., 'Use when the user asks to generate, create, or draft the Agent Supply Chain newsletter or requests a team activity summary for the newsletter.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: researching team activity on GitHub and Confluence, creating a Confluence draft, and creating a Gmail draft. These are clear, actionable steps. | 3 / 3 |
Completeness | Clearly answers 'what' (research team activity, create Confluence and Gmail drafts), but lacks an explicit 'Use when...' clause. The when is only implied by the nature of the task. Per rubric guidelines, missing 'Use when' caps completeness at 2. | 2 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'Agent Supply Chain newsletter', 'GitHub', 'Confluence', 'Gmail draft', 'newsletter'. A user asking about this specific newsletter would naturally use these terms. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific product name 'Agent Supply Chain newsletter' and the unique combination of GitHub research, Confluence drafting, and Gmail drafting. Very unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, highly actionable skill that provides a clear end-to-end workflow for generating a team newsletter. Its greatest strengths are the concrete tool invocations with exact parameters and the well-sequenced multi-step process with validation reminders. Minor weaknesses include some redundancy in the format description (reading past newsletters AND specifying the format inline) and the lack of bundle files to offload reference material.
Suggestions
Consider extracting the newsletter format specification (Step 2 bullet list) into a separate reference file like NEWSLETTER_FORMAT.md to reduce inline verbosity, since you're already instructing Claude to read past newsletters for format reference.
Remove the inline newsletter format description in Step 2 if the intent is truly to match the most recent newsletter's style—having both creates potential conflicts if the format evolves.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient and avoids explaining concepts Claude already knows, but some sections could be tightened—e.g., the newsletter format description in Step 2 is somewhat redundant given that it also instructs Claude to read past newsletters for format reference. The step-by-step structure is appropriate for the complexity but has minor verbosity. | 2 / 3 |
Actionability | The skill provides fully concrete, executable commands (gh CLI calls, specific MCP tool names with parameters, exact CQL queries, specific space IDs, email addresses, and content types). Every step has copy-paste-ready instructions with specific parameter values. | 3 / 3 |
Workflow Clarity | The 7-step workflow is clearly sequenced with logical dependencies (gather members → read format → research GitHub → research Confluence → synthesize → create outputs → present). Step 7 includes explicit validation checkpoints (review for accuracy, send to self first, get review before publishing). The parallelization strategy in Step 3 is well-specified. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and sub-steps, but it's a monolithic file with no bundle files to offload detail into. The newsletter format specification in Step 2 and the detailed research instructions could potentially be split into reference files. However, for a skill of this length (~100 lines), inline content is borderline acceptable. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- DataDog/datadog-agent
- Commit
0f36ad4
- 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.