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

65%

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

60%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 skill is thorough and well-sequenced with strong contracts and checkpoints, but it is a monolithic single-file document with no progressive disclosure into reference files, and it carries sections (Tips, Cadence, Adapting) that pad the context window. Splitting analyses/templates into reference files and trimming inferred commentary would materially improve both conciseness and progressive disclosure.

Suggestions

Split each of the seven analyses (and/or the report templates) into files under references/ and link to them from SKILL.md, turning the body into an overview — this is the biggest progressive_disclosure lever.

Trim or relocate the Tips and Cadence Guide sections; much of that guidance (consistency compounds, watch vanity metrics) is inferable and competes with context-window budget.

Add an explicit validate→fix→retry loop at the Step 1 human checkpoint (re-pull or remap fields on 'n') to convert the checkpoint into a true feedback loop and lift workflow_clarity to 5.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient input/output contracts and metric tables, but at ~750 lines it is long and the Tips/Cadence/Adapting sections add commentary Claude could largely infer; it could be tightened without losing actionability.	3 / 5
Actionability	Concrete input/output contracts, per-CRM pull tables, explicit metric formulas, and rendered report templates give mostly executable guidance, though the analysis step is largely computation described rather than runnable code.	4 / 5
Workflow Clarity	Steps 0–4 are clearly sequenced with explicit human checkpoints (data-pulled verification, executive-summary review) and error-adaptation tables, missing only a validate→fix→retry loop for the data-pull/checkpoint failures it describes.	4 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are absent) and the entire spec — all seven analyses, full report templates, cadence and tips — is inlined into SKILL.md as a near-monolithic wall, which the rubric penalizes as content that belongs in separate files.	2 / 5
	Total	13 / 20 Passed

Description

71%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 specific and tool-agnostic with strong coverage of analysis dimensions, but it omits an explicit 'Use when...' trigger clause, capping completeness. Adding natural trigger phrases ('pipeline review', 'deal review', '1:1 prep') would lift both completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' trigger clause naming natural phrases users say, e.g. 'Use when the user asks for a pipeline review, deal review, 1:1 prep, or board meeting prep.'

Mirror the body's trigger phrasing ('pipeline report', 'how's our pipeline looking') into the description to raise trigger-term coverage from good to comprehensive.

Keep the named-CRM list but consider trimming it slightly to avoid verbosity while retaining the tool-agnostic signal.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions (pulls deal/meeting data, analyzes pipeline, produces executive summary and detailed diagnostic) plus specific coverage areas (volume, qualification rates, source effectiveness, stage velocity, stuck deals), matching the comprehensive multi-action anchor.	5 / 5
Completeness	It clearly answers 'what' (pull, analyze, produce reports across dimensions) but provides no 'Use when...' trigger clause in the description itself — the explicit 'when' guidance lives only in the body, so completeness caps at 3 per the rubric.	3 / 5
Trigger Term Quality	Includes natural terms like 'pipeline', 'deal', 'CRM', 'executive summary', and named CRM tools, but misses common user phrasings like 'pipeline report', 'deal review', or 'pipeline review' that the body's own trigger list surfaces.	4 / 5
Distinctiveness Conflict Risk	The pipeline-analysis niche with named CRM integrations and dual report outputs is mostly distinct from other skills, with only minor overlap risk against generic reporting or meeting-review skills.	4 / 5
	Total	16 / 20 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: 2523432

Reviewed: 5 days 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.