CtrlK
BlogDocsLog inGet started
Tessl Logo

apitally-cli

Retrieve and investigate API metrics and request log data from Apitally. Fetches aggregated metrics, request logs, consumers, and app metadata via the Apitally CLI, stores data in a local DuckDB database, and runs SQL queries to investigate issues or answer questions. Use when the user mentions Apitally, the Apitally CLI, API metrics, API request logs, or API consumers.

94

1.10x
Quality

Does it follow best practices?

Impact

92%

1.10x

Average score across 3 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

87%

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 dense, actionable reference with executable commands, DuckDB-specific SQL patterns, and a well-structured progressive-disclosure layout pointing to real reference files. The only meaningful gap is the absence of an explicit verification step after batch data fetches into the persistent database.

Suggestions

Add an explicit verification checkpoint after each batch fetch (e.g. run `sql "SELECT count(*) FROM request_logs WHERE app_id = <id> AND timestamp >= '<since>'"` to confirm rows loaded and match the intended scope) before proceeding to analysis.

In the Investigation Workflow, turn the 'Iterate if needed' step into a concrete feedback loop: if a query returns zero rows or unexpected data, list the specific corrective actions (widen/fix the time range, check filters against the endpoints/consumers lookup, re-run the fetch).

For destructive operations like `reset-db`, add a one-line validation/guard note (e.g. confirm the target db path and that no other in-progress investigation depends on the existing tables) before the command is run.

DimensionReasoningScore

Conciseness

The body is lean and every section earns its place: the Key Concepts define Apitally-specific terms (consumer_id vs identifier, path vs url) Claude would not know, and the SQL patterns cover non-obvious DuckDB syntax (list comprehensions over STRUCT arrays, AT TIME ZONE for TIMESTAMPTZ, JSON path operators) rather than padding with general knowledge.

3 / 3

Actionability

It provides fully executable, copy-paste-ready `npx @apitally/cli ...` commands and complete SQL examples with real field names and filter JSON, satisfying the level-3 'fully executable code/commands; copy-paste ready' anchor rather than pseudocode.

3 / 3

Workflow Clarity

The 6-step Investigation Workflow is clearly sequenced and includes an auth-error feedback loop and a CRITICAL scope-filtering guard, but the batch/database operations (fetching up to 1,000,000 rows into a persistent DuckDB) lack an explicit post-fetch verification checkpoint, which the rubric's judging guideline says caps this dimension at 2.

2 / 3

Progressive Disclosure

The body is a clear overview that points to three well-signaled, one-level-deep references (commands.md, duckdb_tables.md, duckdb_json_functions.md), all of which exist in references/; detailed flags/schemas are appropriately split out rather than inlined, matching the level-3 anchor.

3 / 3

Total

11

/

12

Passed

Description

100%

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 third-person, concise, and follows the ideal what-plus-when pattern with concrete capabilities and natural trigger terms. It matches the rubric's good_overall_examples closely and has no over-claims or fluff.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Fetches aggregated metrics, request logs, consumers, and app metadata', 'stores data in a local DuckDB database', and 'runs SQL queries to investigate issues' — matching the level-3 anchor rather than the single-action level-2 example.

3 / 3

Completeness

It explicitly answers both what ('Retrieve and investigate API metrics and request log data…') and when (an explicit 'Use when…' clause with concrete triggers), which is the level-3 anchor; it is not the level-2 case where 'when' is only implied.

3 / 3

Trigger Term Quality

The 'Use when the user mentions Apitally, the Apitally CLI, API metrics, API request logs, or API consumers' clause gives natural phrasings a user would actually say, with good coverage and no jargon-only terms.

3 / 3

Distinctiveness Conflict Risk

Apitally is a specific product niche with distinct triggers ('Apitally', 'the Apitally CLI'), making it unlikely to fire for unrelated skills, satisfying the level-3 'clear niche with distinct triggers' anchor.

3 / 3

Total

12

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
apitally/cli
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.