Name: partnerships-architect
Rating: 70.39999999999999 (1 reviews)
Author: alirezarezvani

partnerships-architect

Use when a startup is approached by a prospective partner and someone has to decide should we sign this partner, at what partner tier (referral / reseller / OEM / SI-consulting / strategic alliance), with what joint GTM commitment, and at what revshare. Classifies partner tier from independent-demand evidence vs. preferential-terms hunting, designs a 90-day joint GTM plan, models revshare against direct-sale margin, and surfaces kill criteria for unwinding under-performing partnerships. For Head of Partnerships, Head of BD, and Founder-CEOs doing reseller agreement, OEM deal, or strategic alliance review — not technical sale enablement, not channel cost economics, not M&A.

Quality

87%

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 partnerships-architect in alirezarezvani/claude-skills

Quality

Content

75%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, highly actionable multi-step skill with clear sequencing, deterministic validation rules, and strong progressive-disclosure design — its main weaknesses are a somewhat verbose forcing-question library and bundle files that are referenced but not present.

Suggestions

Ship the referenced bundle files (references/*.md, scripts/*.py, assets/partnership_intake_template.md) — the SKILL.md points to them but none exist, so a user following the workflow hits broken paths.

Add a short example of the intake.json / gtm.json / revshare.json input shape (or point to the template) so the script commands are runnable without guessing the schema.

Add an explicit validate→fix→re-run loop (e.g., if tier validation rejects a planned motion, revise the GTM input and re-run joint_gtm_planner.py) to close the workflow_clarity gap.

Dimension	Reasoning	Score
Conciseness	Dense and assumes Claude's competence (no 'what is revshare/GTM' primers), but the 7-question forcing-question library with per-question recommended answers and canon name-lists is somewhat verbose and could be tightened without losing substance.	4 / 5
Actionability	Concrete copy-paste CLI invocations with flags ('partner_tier_classifier.py --input intake.json --profile saas --output markdown') and a runnable '--sample' example, plus deterministic floors (STRATEGIC requires named_accounts ≥ 5); minor gap is that the intake/gtm/revshare JSON input shapes are not specified inline.	4 / 5
Workflow Clarity	Five clearly sequenced steps with a time estimate, explicit validation (Step 1 stop condition, Step 3 tier-motion rules, Step 5 mandatory kill criteria) and a depth-first forcing-question ordering rule; just short of a 5 because there is no explicit validate→fix→re-run feedback loop for error recovery.	4 / 5
Progressive Disclosure	Well-signaled one-level-deep references to scripts/, assets/, and references/ with per-file descriptions and clean section navigation, but the referenced bundle directories do not actually exist, so the split is designed but not realized — a minor organization/integrity gap that caps a 5.	4 / 5
	Total	16 / 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: concrete third-person actions, a clear 'Use when' trigger with specific decision criteria, comprehensive natural trigger terms, and explicit distinctiveness boundaries that prevent wrong-skill activation.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions in third person — 'Classifies partner tier', 'designs a 90-day joint GTM plan', 'models revshare against direct-sale margin', 'surfaces kill criteria' — with comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both what (classify tier / design GTM / model revshare / surface kill criteria) and when via a concrete 'Use when a startup is approached by a prospective partner and someone has to decide...' trigger clause, plus audience and exclusions.	5 / 5
Trigger Term Quality	Comprehensive natural-term coverage including synonyms and audience phrases a user would actually say: 'prospective partner', 'reseller agreement', 'OEM deal', 'strategic alliance review', 'revshare', 'joint GTM', 'Head of Partnerships'.	5 / 5
Distinctiveness Conflict Risk	Clear niche (partner tier / GTM / revshare design) with explicit negative boundaries — 'not technical sale enablement, not channel cost economics, not M&A' — minimizing overlap with sibling 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: 11 missing	Warning

	Total	14 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: .gemini/skills/partnerships-architect/SKILL.md
Commit: 19392f7

Reviewed: ~11 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.