CtrlK
BlogDocsLog inGet started
Tessl Logo

review-rep-call-trends

Use when the user wants to understand how a sales or customer-facing rep's call behavior is changing over time. Produce an evidence-backed trend readout with improvements, regressions, stable patterns, coaching actions, and calls to re-listen.

72

Quality

88%

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.

A highly actionable, well-sequenced workflow skill: concrete parameters throughout, a complete output template, validation and failure-handling loops, and appropriately split reference files. Remaining issues are minor: some redundancy in the ambiguity-resolution step and malformed cross-skill links pointing outside the bundle.

Suggestions

Consolidate the overlapping ambiguity bullets in '1. Resolve the rep and comparison basis' (both the bare-invocation and 'my call trends' bullets dictate offering the same explicit choices) into a single rule to trim redundancy.

Fix the malformed external link 'plugins/sales/skills/index/SKILL.md## Cross-Skill Best Practices' — the space breaks the heading anchor; use a proper path plus '#cross-skill-best-practices' and verify the target file exists.

Verify or inline the '{Follow the instructions...}' placeholders that point to ../index/SKILL.md#limitations-and-improvements and #4-next-steps, since unresolved external anchors make the output format depend on files outside this skill's bundle.

DimensionReasoningScore

Conciseness

The body is dense and procedural, assuming Claude's competence (e.g. "Convert every relative window to concrete absolute dates before searching") with no padding or explanation of known concepts. However, step 1 repeats ambiguity-handling guidance across overlapping bullets (two bullets both dictate offering the same explicit choices), which could be tightened. Not 5: some redundancy in the resolve-rep step; not 3: only minor trimming is needed.

4 / 5

Actionability

Fully concrete for an instruction-only skill: exact search parameters ("score_threshold=0", "limit of about 25 per slice"), concrete sample targets ("30-60 deduplicated calls", trailing 90 days in three slices), a copy-paste output format template, a literal citation example ("2026-03-24, ExampleCorp, Pilot & Pricing [1](https://example.com/call/123)"), and example prompts. Matches the 5 anchor.

5 / 5

Workflow Clarity

A clear five-step sequence with explicit validation and recovery loops: zero-result retry with grounded name variations, sparse-slice expansion, a dedicated small validation-fetch step, a Failure Handling section, and a fallback Limited Trend Readout mode. Matches the 5 anchor including error-recovery feedback loops.

5 / 5

Progressive Disclosure

References are well signaled and one level deep, both real files (references/request-schema.yaml, references/rubric.md), loaded conditionally with stated purpose ("Load references only when their extra detail matters"). Not 5: external links are malformed or unverifiable — "plugins/sales/skills/index/SKILL.md## Cross-Skill Best Practices" (space inside a heading-anchor link, outside the bundle) and "../index/SKILL.md#limitations-and-improvements" — which slightly impairs navigation.

4 / 5

Total

18

/

20

Passed

Description

88%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 description: third-person, concise, with an explicit 'Use when' trigger and a specific, comprehensive list of deliverables. Its only weaknesses are a few missing natural trigger synonyms and minor overlap risk with closely related call-review skills.

DimensionReasoningScore

Specificity

"Produce an evidence-backed trend readout with improvements, regressions, stable patterns, coaching actions, and calls to re-listen" enumerates multiple specific, concrete deliverables, comprehensively covering the skill's output. Not 4: there are no coverage gaps in the action list.

5 / 5

Completeness

Explicitly answers both: "Use when the user wants to understand how a sales or customer-facing rep's call behavior is changing over time" (when) and "Produce an evidence-backed trend readout with improvements, regressions, stable patterns, coaching actions, and calls to re-listen" (what). Matches the 5 anchor with concrete trigger phrasing; not 4 because the when-clause is explicit and specific.

5 / 5

Trigger Term Quality

Natural phrases like "rep's call behavior is changing over time", "trend", and "sales" are present, but common variations a user would naturally say (e.g. "coaching review", "call analysis", "how are my calls going") are missing. Not 5: synonym coverage is good but not comprehensive.

4 / 5

Distinctiveness Conflict Risk

The time-comparison framing ("changing over time", "trend") carves a distinct niche versus single-call review skills, but phrasings like "review a rep's calls" could overlap with sibling call-review or coaching-note skills. Not 5: minor overlap risk with closely related sales skills remains.

4 / 5

Total

18

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 2 suspicious

Warning

Total

15

/

16

Passed

Repository
XiaomiMiMo/MiMo-Code
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.