CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

metrics-expert

Growth Studio metrics pipeline expert. Use when: adding channels, metrics, stages, or groups to the analytics module; modifying the progressive loading architecture; changing channel-to-group mappings; debugging missing channels in the dashboard. Triggers: 'nuevo canal', 'nueva metrica', 'agregar metrica', 'canal no aparece', 'growth studio metrics', 'stage service', 'channel registry', 'group mapping'.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

81%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.

A high-quality operational skill body: lean, table-driven, with copy-paste-ready snippets for the common changes (channel, metric, group, stage) and a genuinely enforced validation step plus an ordered debugging checklist. The main improvements are tightening a couple of confusing example comments and adding code to the prose-only frontend steps.

Suggestions

Fix the step-3 group-mapping example in the channel SOP: it shows an ATTRACTION_GROUP_MAP entry commented "already maps" — show an actual new channel_type→group addition, or drop the code block and state the rule in one line.

Add concrete snippets for the frontend steps in the stage-group SOP (the group filter in AttractionCaptureDetail.tsx and the LazyChannelGroup usage), matching the specificity of the backend steps.

Trim inline comments that restate the adjacent prose (e.g., "# ← new group", "# ← new optional group") and merge the extraction-contract file table with the rules-file pointer into one navigation block.

DimensionReasoningScore

Conciseness

The body is dense and lean — tables, minimal code snippets, ordered checklists — with no re-explanation of concepts Claude already knows. Minor slack keeps it below anchor 5: the step-3 group-mapping example presents an entry commented "already maps" (a non-change shown as an edit), and a few inline comments state the obvious.

4 / 5

Actionability

Nearly everything is executable: copy-paste-ready registry/DTO/frontend snippets, exact commands (make extraction-contract, the pytest path, redis-cli DEL "metrics:{tenant_id}:{stage}:last_30_days"), and exact file paths. Minor gaps — the frontend steps in the stage-group SOP ("Add group filter in AttractionCaptureDetail.tsx", "Add LazyChannelGroup") are prose-only — hold it at anchor 4 rather than 5.

4 / 5

Workflow Clarity

All three SOPs are numbered and sequenced; the "Mandatory final step of any change" gives an explicit validation command pair with "Both must pass" and a same-commit rule; and the debugging section is an ordered error-recovery checklist including a cache-clear feedback step. This matches anchor 5 (explicit validation, feedback loops, checklists).

5 / 5

Progressive Disclosure

All three advertised reference files (references/etl-extraction-contract.md, references/analytics-metrics.md, references/data-reliability.md) exist, are one level deep, and are clearly signaled with one-line summaries in a "Project invariants (read on demand)" section. The 209-line body appropriately keeps SOPs inline as the operational core, but the top-level extraction-contract table plus the rules-file pointer slightly duplicate navigation, fitting anchor 4 rather than 5.

4 / 5

Total

17

/

20

Passed

Description

78%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.

A strong, distinctive description with an explicit use-when clause and unusually good bilingual trigger coverage for a domain-specific analytics pipeline. Its main weakness is that the capability statement is a role claim ("expert") rather than a concrete action list.

Suggestions

Replace the role claim "Growth Studio metrics pipeline expert" with concrete verbs, e.g., "Add channels, metrics, stages, and groups to the Growth Studio analytics pipeline; update channel-to-group mappings; debug missing channels."

Add trigger variants for stages and groups (e.g., "nueva etapa", "nuevo grupo", "agregar canal", "stage missing") to round out the bilingual coverage.

DimensionReasoningScore

Specificity

"Use when: adding channels, metrics, stages, or groups to the analytics module; modifying the progressive loading architecture; changing channel-to-group mappings; debugging missing channels in the dashboard" lists several concrete actions with only minor coverage gaps, but the "what" ("Growth Studio metrics pipeline expert") is a role claim rather than an enumerated capability list, so it fits anchor 4 rather than 5.

4 / 5

Completeness

The "when" is exemplary — an explicit "Use when:" clause plus a separate "Triggers:" list of concrete phrases — but the "what" is stated as a role ("Growth Studio metrics pipeline expert") without concrete verbs describing what it does, matching anchor 4 ("both present; one could be more specific") rather than anchor 5.

4 / 5

Trigger Term Quality

Bilingual natural phrases users would actually say ("nuevo canal", "nueva metrica", "canal no aparece", "growth studio metrics", "stage service", "channel registry", "group mapping") give good keyword coverage, but a few natural variants are missing (e.g., "nueva etapa"/"nuevo grupo" for stages and groups, "agregar canal"), which fits anchor 4 rather than comprehensive anchor 5.

4 / 5

Distinctiveness Conflict Risk

Terms like "Growth Studio", "stage service", "channel registry", and "group mapping" carve out a clear niche with distinct triggers and minimal risk of firing for unrelated skills — anchor 5.

5 / 5

Total

17

/

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

alpacapurpura/ap_sales_agent

Path

.claude/skills/metrics-expert/SKILL.md

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.