pm-exploration
Skill0 starsChanged 6 months agoNo licenceView on GitHub
Source code exploration for PM requirements — the second stage in the PM pipeline (pm-brainstorming → pm-exploration → pm-prd). Use this skill when a PM has a direction document (01-direction.md) from brainstorming and needs to validate the requirement against the actual codebase. Triggers on phrases like 'explore this requirement', 'check feasibility', 'analyze impact', 'source code exploration', 'validate in codebase', 'what does the code look like for this', 'is this doable', '探索需求', '源码分析', '需求可行性', '代码影响分析', or any request to assess a product requirement's technical feasibility by examining source code. Also trigger when the user mentions requirement exploration, code impact analysis, or wants to bridge the gap between a product idea and technical reality before writing a PRD.
In this repository43 other files it gives its agents.
- agent-browser-playwright-codegenSkill
- agent-browser-playwright-explorationSkill
- agent-browser-playwright-recordingSkill
- agent-browserSkill
- apollo-configSkill
- auto-test-uiSkill
- batch-tasks-generatorSkill
- claude-searchSkill
- commitSkill
- digital-supermanSkill
- dissSkill
- excel-case-parserSkill
- fast-nexus-analyzeSkill
- fast-nexus-cypherSkill
- fast-nexus-nl2cypherSkill
- fast-nexus-serveSkill
- find-skillsSkill
- gen-imageSkill
- interviewSkill
- midea-doc-scraperSkill
- mysql-querySkill
- patent-architectSkill
- pm-brainstormingSkill
- pmd-clarifySkill
- pmd-prdSkill
- pm-prdSkill
- prd-reviewSkill
- sdd-archiveSkill
- sdd-brainstormingSkill
- sdd-executing-plansSkill
- sdd-global-changeSkill
- sdd-global-initSkill
- sdd-global-readSkill
- sdd-plan-human-verifySkill
- sdd-start-human-verifySkill
- sdd-writing-plansSkill
- skill-creatorSkill
- test-case-sdd-brainstormingSkill
- test-case-sdd-executing-planSkill
- test-case-sdd-global-initSkill
- test-case-sdd-regressionSkill
- test-case-sdd-writing-planSkill
- web-fetchSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
30 rules. About 0 are common, 20 are distinctive, and 10 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈20
Distinctive · estimate
This author's own choices. Worth a look.
10
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
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.