pipeline-review

Pipeline analysis composite. Pulls deal/meeting data from any CRM or tracking system, analyzes the pipeline over a user-defined period (weekly, fortnightly, monthly, quarterly), and produces both an executive summary and a detailed diagnostic report. Covers volume, qualification rates, source effectiveness, stage velocity, stuck deals, and actionable recommendations. Tool-agnostic — works with any CRM (Salesforce, HubSpot, Pipedrive, Close, Supabase, CSV).

Quality

72%

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/pipeline-review/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.

A thorough, highly actionable composite with a clear sequenced workflow and explicit validation checkpoints, but it is a large monolithic SKILL.md with no progressive disclosure and some unnecessary prose padding. Splitting reference material into separate files and trimming rhetorical sections would improve both conciseness and progressive disclosure.

Suggestions

Move the bulky per-analysis input/output contracts, field-mapping tables, and report-format templates into one-level-deep reference files (e.g., references/analysis-contracts.md, references/report-templates.md) and link them from SKILL.md to improve progressive_disclosure.

Trim non-essential prose (e.g., "What a founder reads over morning coffee", the Cadence Guide, and the Tips section) or relocate them to a reference file to tighten conciseness while preserving the actionable core.

Add an explicit error-recovery note for the data-pull step (what to do when fields are missing or the human checkpoint fails) to make the existing validation gate a full validate→fix→retry loop.

Dimension	Reasoning	Score
Conciseness	The ~750-line body is mostly concrete specification rather than explanations of concepts Claude already knows, but it is padded with rhetorical framing ("What a founder reads over morning coffee") and redundant Tips/Cadence sections, so it is not lean enough for a top score.	2 / 3
Actionability	Provides highly actionable, specific guidance — input/output contracts, exact metric formulas, field-mapping tables, numeric thresholds (e.g. ">60% from one source", "coverage <2x"), report templates, and a recommendations logic table — giving copy-ready, concrete instruction.	3 / 3
Workflow Clarity	Clearly sequences Step 0 (config) through Step 4 (export) with explicit human validation checkpoints ("Data looks correct? (Y/n)", executive-summary review) and an Execution Summary table; the data-pull checkpoint serves as a verification gate before analysis proceeds.	3 / 3
Progressive Disclosure	The skill is well-organized into labeled sections but is a single ~750-line monolith with no bundle files or external references; the per-analysis contracts, config tables, and report templates are content that could be split into one-level-deep reference files.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 specific, capability-rich description that clearly conveys what the skill does and carves out a distinct niche, but it lacks an explicit "Use when" trigger clause and the most natural user-facing trigger phrases. Adding a trigger sentence would lift completeness and trigger-term quality.

Suggestions

Append an explicit "Use when..." clause (e.g., "Use when reviewing a sales pipeline, preparing a 1:1 or board review, or asking about pipeline health, conversion rates, or stuck deals.") to satisfy the completeness dimension.

Add the natural trigger phrases users would actually say ("pipeline review", "review my pipeline", "deal review", "how's our pipeline looking") to the description rather than relying on the body's auto-load list.

Replace the jargon term "composite" with plainer phrasing so the description reads as a natural capability statement.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Pulls deal/meeting data", "analyzes the pipeline", "produces both an executive summary and a detailed diagnostic report" — and enumerates specific coverage areas (volume, qualification rates, source effectiveness, stage velocity, stuck deals, recommendations).	3 / 3
Completeness	Clearly answers "what" with specific actions and coverage, but there is no "Use when..." clause or equivalent explicit trigger guidance in the description, which caps completeness at 2 per the judging guidelines.	2 / 3
Trigger Term Quality	Contains relevant sales/CRM terms ("CRM", "deal/meeting data", "executive summary", "diagnostic report", named CRMs), but the most natural user phrases ("pipeline review", "review my pipeline", "deal review") are absent and "Pipeline analysis composite" leans toward jargon.	2 / 3
Distinctiveness Conflict Risk	Targets a distinct sales-pipeline analysis niche with named CRMs and specific analyses, making it unlikely to trigger for unrelated skills.	3 / 3
	Total	10 / 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 (766 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/pipeline-review/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.