specs
Skill224 starsChanged 3 months agoMITView on GitHub
Analyze requirements, create/maintain FSD and use cases. Use for business analysis, requirements documentation, functional specs.
We split this skill into the rules it gives an agent
2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 9
Create and maintain Functional Specification Documents (FSD) and use case documentation through codebase analysis and requirements …
- Very specific: line 13
If invoked without arguments, use AskUserQuestion to present available operations:
“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Business Analysis
Create and maintain Functional Specification Documents (FSD) and use case documentation through codebase analysis and requirements engineering.
Default (No Arguments)
If invoked without arguments, use AskUserQuestion to present available operations:
| Operation | Description |
init | Analyze codebase & create FSD + use cases |
analyze | Analyze new feature requirements |
update | Sync FSD & use cases with codebase |
Present as options via AskUserQuestion with header "Business Analysis", question "What would you like to do?".
Subcommands
| Subcommand | Reference | Purpose |
/specs init | references/init-workflow.md | Analyze codebase and create initial FSD + use cases |
/specs analyze "feature" | references/analyze-workflow.md | Analyze new feature and update FSD + use cases |
/specs update | references/update-workflow.md | Sync FSD + use cases with current codebase state |
Routing
Parse $ARGUMENTS first word:
init→ Loadreferences/init-workflow.mdanalyze→ Loadreferences/analyze-workflow.md, pass remaining args as feature descriptionupdate→ Loadreferences/update-workflow.md- empty/unclear → AskUserQuestion
Shared Context
- Detection script:
.claude/skills/common/detect-project-type.sh - FSD template:
references/templates/fsd-template.md - UC template:
references/templates/use-case-template.md - PRD input:
docs/project-overview-pdr.md - Output FSD:
docs/project-fsd.md - Output UCs:
docs/usecases/{module}/uc-{module}-{nnn}-{slug}.md
Note: This skill was previously named /ba. All references now use /specs.
IMPORTANT: Do not start implementing code. This skill produces documentation only.
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- jackstine/forgectl★ 8same name
- petestewart/claude-skills★ 2same name
- ptonso/parla★ 2same name
- Rosons/claude-skills★ 1same name
- aiqiliu/claude-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository46 other files it gives its agents.
- .claude/skills/react-best-practices/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- ai-multimodalSkill
- askSkill
- backend-developmentSkill
- brainstorm-featuresSkill
- brainstorm-technicalSkill
- chrome-devtoolsSkill
- code-reviewSkill
- context-engineeringSkill
- cookSkill
- databasesSkill
- debugSkill
- design-mockup-createSkill
- design-systemSkill
- devopsSkill
- docs-seekerSkill
- docsSkill
- fixSkill
- frontend-designSkill
- frontend-developmentSkill
- gitSkill
- journalSkill
- markdown-novel-viewerSkill
- mermaidjs-v11Skill
- mobile-developmentSkill
- plans-kanbanSkill
- planSkill
- previewSkill
- problem-solvingSkill
- project-managementSkill
- quality-gatesSkill
- react-best-practicesSkill
- repomixSkill
- researchSkill
- scoutSkill
- sequential-thinkingSkill
- skill-creatorSkill
- teamSkill
- test-casesSkill
- testSkill
- ui-stylingSkill
- ui-ux-pro-maxSkill
- web-design-guidelinesSkill
- web-frameworksSkill
- web-testingSkill
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.

