sales-call-prep

Pre-sales-call intelligence composite. Deep dives on the person AND their company before a sales call, then maps findings to your product to generate talking points, objection prep, and a call strategy. Goes beyond generic attendee research — this is sales-specific intelligence that helps SDRs, AEs, and founders walk into calls with a plan. Tool-agnostic — works with any CRM, research source, and calendar.

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/sales/composites/sales-call-prep/SKILL.md

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is a highly actionable, well-sequenced workflow with concrete data contracts and templates throughout. Its main weaknesses are verbosity from rationale prose Claude doesn't need and a monolithic structure that would benefit from progressive disclosure into separate reference files.

Suggestions

Split the large report structure template (the Step 5 block) and the per-dimension research tables into reference files (e.g. REPORT_TEMPLATE.md, COMPANY_RESEARCH.md) and link to them one level deep from SKILL.md.

Trim 'Why It Matters' rationale and concept explanations that restate sales knowledge Claude already has (e.g. budget/authority basics) to reduce token load.

Add a brief verification checkpoint after Step 1's interaction-timeline compilation (e.g. confirm has_prior_contact is set before proceeding) to harden the workflow's feedback structure.

Dimension	Reasoning	Score
Conciseness	The body is structurally efficient (tables and typed input/output contracts carry dense information), but at ~830 lines it includes explanatory prose about sales concepts Claude already knows ('Walking into a meeting without knowing... is a credibility killer', 'Lost deals = you know their objections. Won deals = upsell conversation.') and 'Why It Matters' rationale that could be tightened, so it is 'mostly efficient but includes some unnecessary explanation'.	2 / 3
Actionability	Guidance is concrete and copy-paste ready: explicit input/output data contracts per step, exact tables of what to check and where, a full report structure template, sample opening lines, and pre-built objection handles — fully actionable for an instruction-only skill.	3 / 3
Workflow Clarity	The process is a clearly sequenced Step 0→5 pipeline where each step states its Purpose, Input Contract, Process, and Output Contract, with explicit ordering constraints ('do this before any web research'); this is not a destructive/batch operation so the absence of a validate→retry loop does not cap the score.	3 / 3
Progressive Disclosure	The body is monolithic (~830 lines, no references/, scripts/, or assets/ bundle files exist) with the long report template and per-dimension research tables all inline; sections are well-organized, but content that would benefit from being split into one-level-deep reference files is not separated or signaled.	2 / 3
	Total	10 / 12 Passed

Description

57%

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 well-differentiated, clearly staking out a sales-call-prep niche and listing concrete capabilities. It loses points for missing an explicit 'Use when...' trigger clause, forgoing common natural trigger phrasings, and using second-person voice where third person is required.

Suggestions

Add an explicit trigger clause, e.g. 'Use when prepping for a sales call, demo, or discovery meeting with a prospect.'

Rewrite in third person ('Generates talking points, objection prep, and a call strategy...') to avoid the second-person specificity penalty and to match the rubric's voice requirement.

Surface the natural trigger phrasings users actually say ('call prep', 'prep me for my sales call', 'demo prep') in the description so trigger-term coverage reaches full breadth.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('deep dives on the person AND their company', 'maps findings to your product to generate talking points, objection prep, and a call strategy'), which would anchor at 3, but the description uses second-person voice ('your product', 'walk into calls') and the rubric mandates a 1-point specificity reduction for non-third-person voice, capping it at 2.	2 / 3
Completeness	The 'what' is clearly and thoroughly specified, but there is no explicit 'Use when...' clause or equivalent trigger guidance in the description; the rubric explicitly caps completeness at 2 when such a clause is missing.	2 / 3
Trigger Term Quality	It includes relevant natural terms ('sales call', 'SDRs, AEs, and founders', 'CRM') but omits the common variations a user would actually say ('call prep', 'prep me for my call', 'demo prep'), so it lands at 'some relevant keywords but missing common variations' rather than full coverage.	2 / 3
Distinctiveness Conflict Risk	It carves out a clear niche ('Pre-sales-call intelligence composite', 'sales-specific intelligence', 'Goes beyond generic attendee research') with distinct triggers unlikely to collide with generic meeting/research skills.	3 / 3
	Total	9 / 12 Passed

Validation

87%

Warnings & errors only

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

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (832 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: gooseworks-ai/goose-skills
Path: skills/sales/composites/sales-call-prep/SKILL.md
Commit: 8866b2a

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.