CtrlK
BlogDocsLog inGet started
Tessl Logo

instrument-pr

Instruments a pull request with Amplitude analytics that conform to the project's existing taxonomy. Reads the tracking plan via the Amplitude MCP server (events, properties, naming conventions), analyzes the PR diff to find the few user actions genuinely worth tracking, detects the codebase's SDK and tracking patterns, and adds instrumentation that matches both. Optionally (opt-in) stages new events and properties on an Amplitude tracking-plan branch for data-governance review. Use when asked to "instrument this PR", "add analytics to this change", "add tracking", "add Amplitude events", "instrument this feature", or "what should I track here".

76

Quality

95%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

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.

The body is a well-engineered, highly actionable seven-phase workflow with explicit validation and error-recovery loops, naming exact MCP tools and parameters. Its main weaknesses are minor verbosity in the principles rationale and the absence of any progressive disclosure into reference files for a skill of this length.

Suggestions

Tighten the Core Principles and Troubleshooting prose to the essential rule plus one concrete example, trimming rationale that does not change behavior.

Consider extracting the detailed convention-inference bullets (Phase 2 step 4) or the Troubleshooting section into a references/ file, keeping SKILL.md a concise overview with a one-level-deep pointer.

DimensionReasoningScore

Conciseness

Dense with skill-specific actionable specifics and avoids explaining generic concepts Claude already knows, but the Core Principles section and a few troubleshooting entries carry rationale prose that could be trimmed. It sits above the 'mostly efficient' anchor (3) but short of fully lean (5).

4 / 5

Actionability

Names exact MCP tools and parameters (get_amplitude_context, get_events paginated at 500/page, get_properties with propertyType, create_branch/create_events/create_properties, approvalWF: "Required"), a git diff command, a spec-table template, and explicit judgment criteria — fully actionable for an instruction-only skill.

5 / 5

Workflow Clarity

Seven clearly sequenced phases with explicit validation checkpoints (stop if no user-facing change, stop if no SDK, run typecheck/lint/tests and fix), error-recovery feedback loops (403 → report-only fallback), and a spec-table checklist for a complex process. Validation is present, so the destructive/batch cap does not apply.

5 / 5

Progressive Disclosure

Well-organized into Core Principles, seven phase sections, and Troubleshooting with clear headers, but it is a single ~118-line file with no bundle files or one-level-deep references; the over-50-line simple-skill exception does not apply and anchor 5 requires well-signaled external references.

4 / 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 concrete capabilities, the mechanism (Amplitude MCP server, diff analysis, SDK detection), and explicit opt-in write-back, then closes with a rich set of natural trigger phrases. It is concise, third-person, and clearly distinguishes the skill from related ones.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Reads the tracking plan via the Amplitude MCP server', 'analyzes the PR diff', 'detects the codebase's SDK and tracking patterns', 'adds instrumentation', and 'stages new events and properties' — giving comprehensive concrete coverage of capabilities.

5 / 5

Completeness

Explicitly answers both 'what' (instruments a PR with Amplitude analytics conforming to the existing taxonomy, reading the tracking plan, analyzing the diff, detecting the SDK, and optionally staging events) and 'when' (a 'Use when...' clause with concrete trigger phrases).

5 / 5

Trigger Term Quality

Includes comprehensive natural trigger phrases users would actually say — 'instrument this PR', 'add analytics to this change', 'add tracking', 'add Amplitude events', 'instrument this feature', and 'what should I track here'.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche — Amplitude analytics instrumentation on pull requests — with distinct, specific triggers and minimal overlap risk with other skills. Voice is third person throughout ('Instruments', 'Reads', 'analyzes'), so no specificity penalty applies.

5 / 5

Total

20

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
amplitude/builder-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.