battlecard-generator

Research a specific competitor across their website, reviews, ads, social presence, and pricing — then produce a structured sales battlecard with positioning traps, objection handlers, landmine questions, and win/loss themes. Chains web research, review mining, and ad intelligence. Use when sales needs competitive ammo or when entering a new market with established incumbents.

Quality

84%

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

78%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 research workflow with copy-paste search commands and a complete output template — its strongest qualities. Its weaknesses are the absence of any bundle structure (everything, including a very long output template, is inlined in SKILL.md) and minor duplication between the usage-trigger sections.

Suggestions

Move the ~135-line battlecard output template to a one-level-deep reference file (e.g., references/battlecard-template.md) and link to it from Phase 3, keeping SKILL.md as a lean overview.

Merge the 'When to Use' and 'Trigger Phrases' sections, which repeat the same example phrases, into a single section.

Add an explicit validation checkpoint between Phase 1 and Phase 3, e.g., 'Before writing the card, confirm every claimed strength/weakness cites a source (review quote, pricing page, or ad) — downgrade unsourced claims in the Confidence field.'

Dimension	Reasoning	Score
Conciseness	The body is largely efficient — search-query blocks, a strengths/weaknesses matrix, and the output template all earn their tokens, and it never explains concepts Claude already knows. Not a 5 because the 'When to Use' and 'Trigger Phrases' sections duplicate the same example phrases, and the ~135-line inline template could be tightened.	4 / 5
Actionability	Fully copy-paste-ready guidance: literal search strings ('Search: "[competitor]" site:g2.com OR site:capterra.com'), explicit fetch targets per phase, a complete fill-in battlecard template, and a concrete save path ('clients/<client-name>/product-marketing/battlecards/vs-[competitor-slug]-[YYYY-MM-DD].md'). Covers the common cases end-to-end.	5 / 5
Workflow Clarity	The Phase 0 → 1A-1E → 2 → 3 sequence is explicit and well-decomposed, and the skill is neither destructive nor batch so no hard cap applies. Not a 5 because verification is only implicit (a 'Confidence: High/Medium' output field) — there is no explicit checkpoint to validate that research findings are sourced before generating the card.	4 / 5
Progressive Disclosure	Sections are well-organized with clear headers, but the skill is a single ~280-line monolith with zero external references: the ~135-line battlecard output template and the research query blocks are content that could live in one-level-deep reference files. Matches the 3 anchor ('some structure... content that should be separate is inline').	3 / 5
	Total	16 / 20 Passed

Description

83%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: it states concrete capabilities comprehensively and includes an explicit 'Use when' clause for a well-defined niche. The only weakness is that trigger coverage leans on situational phrasing rather than the natural phrases a user would utter verbatim.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions with comprehensive coverage: 'Research a specific competitor across their website, reviews, ads, social presence, and pricing — then produce a structured sales battlecard with positioning traps, objection handlers, landmine questions, and win/loss themes. Chains web research, review mining, and ad intelligence.' There are no generic or padded phrases, so it matches the 5 anchor rather than the 4 anchor's 'minor gaps in coverage'.	5 / 5
Completeness	Both 'what' (research + produce a structured battlecard) and 'when' ('Use when sales needs competitive ammo or when entering a new market with established incumbents') are explicit. Falls short of the 5 anchor because the 'when' clause is situational rather than concrete user trigger phrases (e.g., 'when the user asks for a battlecard against a competitor').	4 / 5
Trigger Term Quality	Good natural keyword coverage ('battlecard', 'competitor', 'competitive', 'sales', 'win/loss') but misses common variations users would say such as 'competitor analysis', 'competitive intelligence', or 'losing deals to [competitor]'. Better than the 3 anchor's partial keyword set, short of the 5 anchor's synonym-complete coverage.	4 / 5
Distinctiveness Conflict Risk	Clear niche — sales battlecards against a specific named competitor — with distinct triggers ('battlecard', 'competitive ammo', 'positioning traps'). Minimal overlap risk with generic research or marketing skills, matching the 5 anchor.	5 / 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/competitive-intel/composites/battlecard-generator/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.