assimovt-productskills
Skill32 starsChanged 6 months agoMITView on GitHub
Focused product-management skills spanning the full lifecycle: discovery (user interviews, problem validation, JTBD, research synthesis), strategy (competitor analysis, positioning, strategy docs), prioritization (RICE, Shape Up scope-cutting and bet-sizing), evidence-first PRDs, plus launch plans, North Star metrics frameworks, A/B experiment design, and Now/Next/Later roadmaps.
In this repository170 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- accessibility-agentsSkill
- accessibility-catalogueSkill
- addyosmani-qualitySkill
- ai-graphic-design-skillSkill
- algorithmic-artSkill
- anatomySkill
- animate-css-skillSkill
- animate-skillSkill
- anthropics-skillsSkill
- antvis-chart-skillsSkill
- apple-hig-skillsSkill
- awesome-design-skillsSkill
- baseline-uiSkill
- bencium-ux-designerSkill
- brand-design-mdSkill
- building-componentsSkill
- callstack-agent-skillsSkill
- cc-slidevSkill
- chadboyda-gtmSkill
- claud3Skill
- claude2figmaSkill
- claudedesignskillsSkill
- claude-pm-skillsSkill
- claude-wireframe-skillSkill
- cloudai-threejsSkill
- cloudflare-web-perfSkill
- color-expertSkill
- composio-artifactsSkill
- content-catalogueSkill
- content-strategySkill
- copywriting-skillSkill
- coreyhaines-marketingSkill
- creative-directorSkill
- css-animation-skillSkill
- d3js-skillSkill
- dark-pattern-auditSkill
- data-analysis-skillSkill
- data-viz-agentSkill
- deanpeters-pm-skillsSkill
- design-auditorSkill
- design-briefSkill
- design-catalogueSkill
- design-consultationSkill
- design-debt-auditSkill
- design-engineering-catalogueSkill
- designer-skillsSkill
- design-for-aiSkill
- design-htmlSkill
- design-impact-reportingSkill
- design-labSkill
- design-motion-principlesSkill
- design-negotiationSkill
- design-review-garrytanSkill
- design-sprintSkill
- design-system-governanceSkill
- design-tokens-skillSkill
- design-with-claudeSkill
- digidai-pmSkill
- dimensional-drawingSkill
- The first 60 shown.
The file
Files
assimovt-productskills
Catalogue stub — full package: assimovt/productskills
<!-- das:install:start — generated from stub.yaml by `npm run generate`; edit stub.yaml, not this block -->Decision tree
- Is the full skill already installed?
This package installs 16 skills (
user-interview,problem-validation,jtbd-analysis,research-synthesis,opportunity-mapping,competitor-analysis,product-positioning,strategy-doc,feature-prioritization,scope-cutting,bet-sizing,prd-writing,launch-plan,metrics-framework,experiment-design,roadmap-planning); checking the first.- Global:
f=~/.agents/skills/user-interview/SKILL.md; [ -f "$f" ] && ! grep -q "^das:" "$f" && echo "installed" || echo "pointer" - Project:
f=.agents/skills/user-interview/SKILL.md; [ -f "$f" ] && ! grep -q "^das:" "$f" && echo "installed" || echo "pointer" installed→ the skill is installed asuser-interview, invoke it and proceedpointer→ go to step 2
- Global:
Detect scope, then install:
[ -e ~/.agents/skills/assimovt-productskills ] && echo "global" || echo "project"Global:
npx skills add assimovt/productskills --skill user-interview problem-validation jtbd-analysis research-synthesis opportunity-mapping competitor-analysis product-positioning strategy-doc feature-prioritization scope-cutting bet-sizing prd-writing launch-plan metrics-framework experiment-design roadmap-planning -g -yProject:
npx skills add assimovt/productskills --skill user-interview problem-validation jtbd-analysis research-synthesis opportunity-mapping competitor-analysis product-positioning strategy-doc feature-prioritization scope-cutting bet-sizing prd-writing launch-plan metrics-framework experiment-design roadmap-planning -yClaude Code: send a command as a chat message starting with
!to run it without leaving the conversation.
Claude Code plugin route:
/plugin marketplace add assimovt/productskills
/plugin install product-skills@productskillsHeads-up
- License: MIT
- Name collision:
competitor-analysisis also written byphuryn-pm-skills(its install or its catalogue pointer); installing both overwrites the earlier one. - Name collision:
experiment-designis also written byclaude-pm-skills(its install or its catalogue pointer); installing both overwrites the earlier one.
<!-- das:install:end -->Invoke after install
- Skill names:
user-interview,problem-validation,jtbd-analysis,research-synthesis,opportunity-mapping,competitor-analysis,product-positioning,strategy-doc,feature-prioritization,scope-cutting,bet-sizing,prd-writing,launch-plan,metrics-framework,experiment-design,roadmap-planning - Trigger phrases: "roadmap planning", "metrics framework", "North Star metric", "experiment design", "competitor analysis", "Shape Up", "bet sizing"
What it does
Evidence-first PM skills, each shipped with a worked example. Strongest on the areas the other catalogue PM packages don't cover deeply — roadmaps, metrics, experimentation, competitive analysis, strategy, and Shape Up scoping.
| Sub-skill | Best for |
user-interview | Mom Test + YC's Five Questions — unbiased user interviews |
problem-validation | Score problems on frequency × intensity × willingness-to-pay |
jtbd-analysis | Jobs-to-be-Done + Forces of Progress |
research-synthesis | Turn interview notes into atomic insights and patterns |
opportunity-mapping | Opportunity Solution Trees (Teresa Torres) |
competitor-analysis | Feature matrix, positioning map, strategic gaps |
product-positioning | April Dunford's Obviously Awesome framework |
strategy-doc | Playing to Win + Rumelt's Strategy Kernel |
feature-prioritization | RICE scoring with enablers vs blockers lens |
scope-cutting | Shape Up appetite — fixed time, variable scope |
bet-sizing | Shape Up pitch format + Type 1/2 decision framework |
prd-writing | Evidence-first, concise, measurable PRDs |
launch-plan | Launch tiers (silent / soft / big-bang) with checklists |
metrics-framework | North Star + input/output tree + counter-metrics |
experiment-design | Hypothesis-driven A/B tests with a sample-size plan |
roadmap-planning | Now/Next/Later roadmaps — outcomes, not features |
To install only some of them, run the install command with just those names after --skill.
When NOT to use
- Customer journey maps / user story mapping → use
deanpeters-pm-skills - Triple Diamond / Design Sprint facilitation → use
pm-skills - Broad PM marketplace (GTM, data analytics) → use
phuryn-pm-skills - Behavioral product design, growth loops → use
lenny-skills - Go-to-market and sales motion → use
chadboyda-gtm
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

