bls-query

Queries U.S. Bureau of Labor Statistics data using the BLS MCP server. Use when user asks about CPI, inflation, unemployment, employment, wages, jobs, labor statistics, producer prices, or any economic indicator tracked by BLS. Maps natural language to correct series IDs and tools. Copied from https://github.com/larasrinath/bls_mcp

Quality

93%

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

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 body is a well-structured, token-efficient workflow that maps natural language to BLS series IDs and tools, with a clear decision table and an explicit error-recovery loop. It appropriately offloads the series catalog to a one-level-deep reference that exists on disk.

Suggestions

Add one or two concrete MCP tool-call examples (e.g. the exact arguments for get_latest_series) to lift actionability from strong to fully copy-paste ready.

Tighten the unknowns feedback loop into hard validation gates (e.g. 'Confirm the series ID with the user before fetching') to reach a 5 on workflow_clarity.

Note explicitly when the calculations field requires an API key versus when Claude should compute percent change itself, to remove ambiguity in Step 3.

Dimension	Reasoning	Score
Conciseness	Lean and efficient throughout: no preamble explaining what BLS or CPI is; every section (topic mapping, tool table, interpretation, error handling) earns its place and assumes Claude's competence.	5 / 5
Actionability	Concrete, executable guidance: explicit series IDs, a decision table mapping intent to named tools, and exact fallback steps; minor gaps are that no literal MCP tool call syntax/examples are shown and percent-change calculation is left implied.	4 / 5
Workflow Clarity	Four clearly sequenced steps with an explicit 'Handle unknowns' feedback loop (call get_all_surveys -> get_popular_series -> ask user) and the guard 'Do NOT guess a series ID'; slightly below 5 because validation checkpoints are advisory rather than enforced as hard gates.	4 / 5
Progressive Disclosure	Overview SKILL.md points to a single one-level-deep reference, references/series-catalog.md, which exists and is clearly signaled at the points where it is needed; bulk catalog content is correctly offloaded to the reference file.	5 / 5
	Total	18 / 20 Passed

Description

100%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 is exemplary: it states the capability concisely, uses third person, lists concrete actions, and provides comprehensive natural-language triggers with an explicit 'Use when' clause. It occupies a clear niche with minimal conflict risk.

Dimension	Reasoning	Score
Specificity	Names the domain (BLS data) and multiple concrete actions: 'Queries', 'Maps natural language to correct series IDs and tools', with explicit enumeration of CPI, inflation, unemployment, wages, PPI, JOLTS.	5 / 5
Completeness	Explicitly answers both 'what' ('Queries U.S. Bureau of Labor Statistics data using the BLS MCP server') and 'when' ('Use when user asks about...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger coverage including synonyms and acronyms: 'CPI, inflation, unemployment, employment, wages, jobs, labor statistics, producer prices' plus the catch-all 'any economic indicator tracked by BLS'.	5 / 5
Distinctiveness Conflict Risk	Clear niche (BLS-specific economic data via MCP) with distinct triggers unlikely to fire for unrelated skills; minimal conflict risk.	5 / 5
	Total	20 / 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: dathere/qsv
Path: .claude/skills/skills/bls-query/SKILL.md
Commit: a46782a

Reviewed: about 3 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.