customer-story-builder

Take raw customer inputs — interview transcripts, survey responses, Slack quotes, support tickets, review excerpts — and generate a structured case study draft with problem/solution/result narrative, pull-quotes, metric callouts, and multi-format outputs (full case study, one-pager, social proof snippet, sales deck slide). Pure reasoning skill. Use when a product marketing team has customer signal but no time to write the story.

Quality

87%

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

Quality

Content

82%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 instruction skill whose output templates, intake checklist, and quality gate leave Claude with no ambiguity about what to produce. Weaker spots are minor: some redundant sections cost tokens, the quality checklist lacks an explicit fix-and-recheck loop, and the inlined templates make the body longer than an ideal overview.

Suggestions

Remove or merge the redundant sections — 'Cost', 'Tools Required', and 'Trigger Phrases' (which duplicates 'When to Use') — to tighten token usage.

Add an explicit feedback loop after the Phase 3 checklist, e.g., 'If any check fails, revise the affected output and re-run the checklist before finalizing.'

Move the five output templates to a single references/ file (e.g., templates.md) with clearly signaled links from SKILL.md to keep the main body a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is dominated by templates, checklists, and structural guidance that assume Claude's competence, but there is trimmable padding: the "Core principle" prose, the "Cost" table, "Tools Required: None", and a "Trigger Phrases" section that duplicates "When to Use". Not a 5 because these sections spend tokens without adding actionable guidance; not a 3 because the padding is minor rather than explanatory filler.	4 / 5
Actionability	Five copy-paste-ready output templates with word counts ("800-1200 words"), a numbered intake questionnaire, a four-type quote taxonomy, a quality checklist with concrete comparisons ("'3x pipeline' > 'improved results'"), and explicit output file paths. For an instruction-only skill this is fully executable guidance; a 4 would require missing key details, and none are evident.	5 / 5
Workflow Clarity	Phases 0-4 give a clear, well-sequenced process (intake, extract, generate, quality check, output) and Phase 3 provides an explicit verification checklist covering specificity, credibility, permission, and freshness. Not a 5 because there is no feedback loop instructing Claude to revise and re-check when a Phase 3 item fails; not a 3 because validation checkpoints are present, not merely implied.	4 / 5
Progressive Disclosure	The ~230-line body is well-sectioned with clear headers, and no bundle files exist, so everything lives appropriately in SKILL.md. Not a 5 because the five detailed output templates are all inlined and would support splitting into one-level-deep reference files (e.g., templates.md) to keep the overview leaner; not a 3 because structure is good and navigation is easy.	4 / 5
	Total	17 / 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 that fully specifies what the skill does and when to use it, with concrete inputs, outputs, and an explicit use-when clause in third-person imperative voice. The only gaps are a few missing natural synonyms (testimonial, customer story) and minor overlap risk with general copywriting skills.

Dimension	Reasoning	Score
Specificity	The description enumerates concrete inputs ("interview transcripts, survey responses, Slack quotes, support tickets, review excerpts") and concrete deliverables ("problem/solution/result narrative, pull-quotes, metric callouts" plus "full case study, one-pager, social proof snippet, sales deck slide"), matching the comprehensive multi-action anchor. It is not a 4 because no meaningful capability gap remains for this domain.	5 / 5
Completeness	It explicitly answers both questions: the "what" is the full input-to-multi-format-output pipeline, and the "when" is stated verbatim ("Use when a product marketing team has customer signal but no time to write the story"). This matches the anchor for clearly and explicitly answering both; a 4 would require the when-clause to be less specific than it is.	5 / 5
Trigger Term Quality	Strong natural phrases users would say — "case study", "interview transcripts", "Slack quotes", "social proof", "sales deck slide", "product marketing" — but common synonyms such as "testimonial", "customer story", or "customer win" are missing. Not a 5 because synonym coverage is incomplete; not a 3 because coverage goes well beyond a couple of generic keywords.	4 / 5
Distinctiveness Conflict Risk	The case-study/social-proof niche has distinct triggers (specific input types and output formats) that are unlikely to fire for unrelated skills, but it slightly overlaps with generic marketing-copywriting skills. Not a 5 because "write marketing content" style requests could ambiguously match; not a 3 because the input/output specificity carves out a real niche.	4 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: gooseworks-ai/goose-skills
Path: skills/content/composites/customer-story-builder/SKILL.md
Commit: cc3e518

Reviewed: 7 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.