pipedrive-claude-skills
CLAUDE.md0 starsChanged 29 days agoMITView on GitHub
Rules for AI agents editing this repo. Follow CONTRIBUTING.md. Run claude plugin validate . after changes (one expected warning: this CLAUDE.md is for repo editors, not shipped plugin context). Bump version in both files in .claude-plugin/ and metadata.version in every SKILL.md for a release.
In this repository19 other files it gives its agents.
- pd-accessSkill
- pd-account-healthSkill
- pd-advisorSkill
- pd-askSkill
- pd-coreSkill
- pd-crm-architectSkill
- pd-data-hygieneSkill
- pd-follow-upSkill
- pd-icp-discoverySkill
- pd-industrySkill
- pd-lead-qualifierSkill
- pd-morning-briefSkill
- pd-pipeline-reviewSkill
- pd-playbook-minerSkill
- pd-premortemSkill
- pd-setupSkill
- pd-thread-mapSkill
- pd-win-backSkill
- pd-win-lossSkill
The file
We split this CLAUDE.md into the rules it gives an agent
5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Every skill in skills/ appears in exactly one of those tables, or in the helpers line under them.
- Distinctive: line 17
Keep the disclaimer at the top, word for word.
- Distinctive: line 18
Never invent numbers or results.
- Distinctive: line 19
No em dashes. Use commas, colons or new sentences.
- Very specific: line 23
Follow CONTRIBUTING.md. Run claude plugin validate .
≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md 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.
Files
CLAUDE.md
Rules for AI agents editing this repo.
Layout
skills/<name>/SKILL.md: one folder per skill.references/andscripts/optional..claude-plugin/: Claude Code marketplace and plugin manifests (plugin at repo root,source: "./").- Skill zips for the Claude app ship as GitHub release assets, never committed.
README is the product page
- Written for sales people, not developers. Value first: the prose opening and the Basics / Intelligence tables lead.
- Every skill in
skills/appears in exactly one of those tables, or in the helpers line under them. - Frame Pipedrive positively: these skills build on Pipedrive data. Never write that Pipedrive "can't" or "fails at" something.
- Install commands must work. Test before changing them.
- Keep the disclaimer at the top, word for word.
- Never invent numbers or results.
- No em dashes. Use commas, colons or new sentences.
Skills
Follow CONTRIBUTING.md. Run claude plugin validate . after changes (one expected warning: this CLAUDE.md is for repo editors, not shipped plugin context). Bump version in both files in .claude-plugin/ and metadata.version in every SKILL.md for a release.
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.