Name: rfp-responder
Rating: 69.6 (1 reviews)
Author: alirezarezvani

rfp-responder

Use when an RFP, RFI, RFQ, security questionnaire, vendor questionnaire, or proposal request arrives and the team needs a structured response — parsing multi-section buyer-dictated requirements (MANDATORY vs WEIGHTED vs NICE-TO-HAVE), building a Shipley-method proof-point matrix mapping each requirement to a verifiable proof point, articulating 3-5 win-themes that ladder up across requirements, and producing a Shipley-derived winrate estimate that informs a bid / no-bid / partner-bid recommendation. For Bid Managers, Proposal Leads, Directors of Sales, and Sales Engineers at the response-strategy moment. Surfaces GAP requirements explicitly — never invents claims. NOT free-form proposal narrative authoring, NOT contract redline, NOT marketing collateral.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

The canonical home for this skill is rfp-responder in alirezarezvani/claude-skills

Quality

Content

71%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 well-structured, action-oriented skill body with a clear pipeline and strong domain-specific guidance (Shipley canon, incumbent/late-entry base rates) that Claude would not already know. Its main weaknesses are missing bundle files undermining the references, undocumented intermediate input formats, and some redundancy across Purpose/Workflow/Distinct-from sections.

Suggestions

Ship the referenced bundle — create scripts/rfp_parser.py, scripts/response_drafter.py, scripts/winrate_predictor.py, assets/rfp_intake_template.md, and the three references/*.md files, since every workflow command and citation currently points to a non-existent file.

Document the JSON schemas for draft_input.json and deal_context.json (or point to a sample produced by --sample) so the response_drafter and winrate_predictor commands are actually runnable end-to-end.

Tighten redundancy: the Purpose 'five questions', the Workflow steps, and the 'Distinct from' / 'Do not use for' lists restate each other — collapse the overlap, or move the forcing-question library and anti-patterns into references/ to deepen progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Largely efficient and assumes domain competence, but the Purpose 'five questions', the Workflow steps, and the 'Distinct from' section overlap with each other and with the 'Do not use for' list, leaving minor trimmable redundancy.	4 / 5
Actionability	Concrete, flag-specific commands are given for all three scripts (e.g. 'python scripts/winrate_predictor.py --input deal_context.json --profile enterprise-software --output markdown'), but input file formats for draft_input.json and deal_context.json are undocumented and the referenced scripts/assets do not exist, leaving minor execution gaps.	4 / 5
Workflow Clarity	A clearly sequenced 5-step pipeline (Parse → Score fit → Win-theme → Winrate → Decide) with checkpoints (GAP audit, <20% no-bid threshold, forcing-question gate), but it lacks explicit error-recovery feedback loops for when a script's output is malformed or a gate fails.	4 / 5
Progressive Disclosure	Section structure and a Scripts/References index are present and signaled, but the referenced bundle files (3 scripts, 3 references, 1 asset template) do not exist, and large blocks (the 7-question forcing-question library with canon citations, the anti-patterns list) are inlined rather than split into the reference files they point to.	3 / 5
	Total	15 / 20 Passed

Description

100%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.

An exemplary description: third-person voice, concrete capabilities, explicit 'Use when' trigger with natural synonyms (RFP/RFI/RFQ), and explicit negative-scope boundaries that distinguish it from neighboring skills. Every dimension lands at the top anchor.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'parsing multi-section buyer-dictated requirements (MANDATORY vs WEIGHTED vs NICE-TO-HAVE)', 'building a Shipley-method proof-point matrix', 'articulating 3-5 win-themes', 'producing a Shipley-derived winrate estimate' — giving comprehensive coverage of capabilities.	5 / 5
Completeness	Explicitly answers both: what it does (parse, matrix, themes, winrate→recommendation) and when to use it ('Use when an RFP... arrives and the team needs a structured response'), with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural-term coverage including synonyms users actually say — 'RFP, RFI, RFQ, security questionnaire, vendor questionnaire, proposal request' — plus 'bid / no-bid / partner-bid recommendation'.	5 / 5
Distinctiveness Conflict Risk	Clear niche with explicit negative boundaries — 'NOT free-form proposal narrative authoring, NOT contract redline, NOT marketing collateral' — minimizing conflict risk with adjacent skills.	5 / 5
	Total	20 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 14 missing	Warning

	Total	14 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: .gemini/skills/rfp-responder/SKILL.md
Commit: 19392f7

Reviewed: ~12 hours 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.