CtrlK
BlogDocsLog inGet started
Tessl Logo

amplitude-automation

Automate Amplitude tasks via Rube MCP (Composio): events, user activity, cohorts, user identification. Always search tools first for current schemas.

70

1.25x
Quality

65%

Does it follow best practices?

Impact

68%

1.25x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/amplitude-automation/SKILL.md

The canonical home for this skill is amplitude-automation in sickn33/agentic-awesome-skills

SKILL.md
Quality
Evals
Security

Quality

Content

68%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, actionable reference for Amplitude MCP automation with concrete tool sequences, parameter specs, and a worked JSON example. Its main gaps are missing verification steps for batch event and IDENTIFY operations (capping workflow clarity) and minor duplication across the pitfalls sections.

Suggestions

Add a verification step for batch event ingestion (e.g. re-query or check processing status) and for IDENTIFY to confirm property changes landed, since these are batch/eventually-consistent operations.

De-duplicate the per-workflow 'Pitfalls' blocks and the consolidated 'Known Pitfalls' section — keep one canonical location and cross-reference it to save tokens.

Provide one full end-to-end worked example (find user -> get activity -> identify) to push actionability from concrete fragments to a complete copy-paste-ready flow.

DimensionReasoningScore

Conciseness

The body is largely efficient, listing tool sequences and parameters without explaining concepts Claude already knows; the main trim opportunity is duplication between each workflow's 'Pitfalls' block and the consolidated 'Known Pitfalls' section, plus a Quick Reference table that re-lists tool slugs — matching 'efficient; minor instances that could be trimmed'.

4 / 5

Actionability

Guidance is concrete and actionable — exact tool slugs, parameter objects, and a copy-paste-ready JSON example for $set/$add operations — fitting 'mostly executable guidance; concrete code or commands with minor gaps'; not a 5 because there is no full end-to-end worked example combining the steps.

4 / 5

Workflow Clarity

Multi-step processes are clearly sequenced with some checkpoints (connection ACTIVE verification, cohort async status retry loop), but batch event ingestion and IDENTIFY operations lack verification steps, and the batch/destructive-without-validation cap holds at 3 — so it does not reach the 'most checkpoints present' level.

3 / 5

Progressive Disclosure

Single-file skill with no bundle files present; structure is good — clear prerequisites, five labeled workflows, Common Patterns, Known Pitfalls, and a Quick Reference table giving easy navigation — matching 'good structure; most content appropriately placed; minor organization gaps'.

4 / 5

Total

15

/

20

Passed

Description

62%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 specific and distinctive, clearly scoping a niche (Amplitude via Rube MCP) with multiple concrete capability areas. Its main weakness is the missing explicit 'Use when...' trigger guidance and tool-centric phrasing that limits natural-trigger coverage.

Suggestions

Add an explicit trigger clause, e.g. 'Use when automating Amplitude product analytics — sending events, looking up user activity, managing cohorts, or setting user properties.'

Soften jargon in the lead (lead with 'Amplitude product analytics' before the Rube MCP/Composio mechanism) so the description opens with a phrase a user would naturally say.

Include common synonyms/variations such as 'user properties', 'cohorts', 'event tracking' to broaden natural keyword coverage.

DimensionReasoningScore

Specificity

The description names the domain (Amplitude via Rube MCP) and lists several concrete action areas ('events, user activity, cohorts, user identification'), matching the 'lists several specific actions; minor gaps' anchor; not a 5 because the actions are terse labels rather than fully elaborated concrete operations.

4 / 5

Completeness

The 'what' is clear ('Automate Amplitude tasks... events, user activity, cohorts, user identification') but there is no 'Use when...' trigger clause — the trailing 'Always search tools first for current schemas' is an instruction, not usage guidance, so per the missing-trigger cap completeness stays at 3.

3 / 5

Trigger Term Quality

Relevant domain keywords ('Amplitude', 'events', 'user activity', 'cohorts') are present, but the phrasing is tool-centric and includes jargon ('Rube MCP (Composio)'), missing natural user-need phrasings and synonyms — fitting 'some relevant keywords but missing common variations'.

3 / 5

Distinctiveness Conflict Risk

'Amplitude' paired with 'Rube MCP (Composio)' carves a clear, specific niche with minimal overlap risk against other skills, matching the 'clear niche with distinct triggers; minimal conflict risk' anchor.

5 / 5

Total

15

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.