developer-case-study skill (samber): write a customer's technical story
Turns a customer's real production deployment into a technical case study, with an evidence ledger and approvals handled.
- Installs
- 12.5K
- on skills.sh
- Stars
- 7
- on GitHub
- Files
- 5
- besides SKILL.md
- Updated
- Nov 2026
- last repo commit
developer-case-study has Claude write someone else's engineering story: what the customer ran in production, what changed and what it cost them. It runs an 11-question interview, checks five qualification gates, builds an evidence ledger before drafting, writes an eight-section draft with a limitations section and opens an approval track. It delivers six parts, from a verdict line to derivative versions.
It triggers on "a customer case study", "a technical case study" or turning a customer interview or migration into published proof. SKILL.md says not to use it for a post about your own system (engineering-blog-post) or your own project's progress (build-in-public). It bundles no scripts and names no API key.
Good for
- Case-study owners at developer-tool companies
- Account teams with several customers who said yes and one slot to fill
- Anyone whose customer's legal team just refused the company name
Install developer-case-study
Claude Code
- 1
Copy this prompt.
Install the developer-case-study skill in Claude Code. Run this command: /plugin marketplace add samber/developer-relations-skills /plugin install developer-relations-skills@developer-relations-skills Then check that it loaded and tell me how to use it.
- 2
Paste it into Claude Code. It shows the change and asks before running it.
The README recommends installing the whole collection because its skills reference each other, and developer-case-study names other skills in the collection to hand work to. The whole-collection routes add all 93 skills in the repo (counted from the git tree); the repo holds no hooks, agents, commands or MCP server files, and 14 of its skills bundle a script. Pick one route per agent.
From the project README. Source.
What's in the skill
When it loads
Turns a customer's real production deployment into a technical case study engineers believe - measured numbers tied to how they were measured, before-and-after architecture, published limitations, and cleared naming and quote approval. Use whenever the user mentions a customer case study, a technical case study, a developer adoption or success story, a reference customer, or wants to turn a user interview, migration or production rollout into published proof - even if they only say "a post about how Acme uses us". Do NOT use for a post about your own system - use samber/developer-relations-skills@engineering-blog-post; for your own project's ongoing progress use samber/developer-relations-skills@build-in-public.
Sections in SKILL.md
- Scope check
- Interview
- Workflow
- Invocation examples
- Story qualification gates
- Which story to chase first
- Number discipline
- The spine
- Limitations are the differentiation
- Approval track
- Humanizer pass
- Publication gate
- Derivative versions
- Failure modes
- Measurement
- References
Key facts
- Skill version
- 1.0.2 (SKILL.md metadata)
- Installs on skills.sh
- 12,459 (Nov 2, 2026)
- Last repo commit
- Nov 1, 2026
- Audits on skills.sh
- Gen Agent Trust Hub: pass, Socket: pass, Snyk: warn
What it includes
Asks 11 questions about the adopter, evidence, approvals and deadline, one at a time.
InterviewChecks five gates before any drafting, starting with production, not pilot.
Checks five gates: production, measured before-state, named human, reusable decision, path to approval.
Story qualification gatesRanks adopter types by published proof per hour and deletes unapprovable candidates.
Ranks adopter types by published proof per hour, and deletes candidates who cannot be approved.
Which story to chase firstLists every claim with its evidence class, instrument and window, before any drafting.
Evidence ledgerDrafts eight sections, including alternatives rejected and what is still unsolved.
Drafts eight sections, including alternatives rejected and what it cost and what is unsolved.
The spineMaps four permissions and uses a five-rung anonymization ladder if naming is refused.
Reads the publicity clause, maps four permissions and uses a five-rung anonymization ladder if naming is refused.
Approval trackRequires seven checks, such as every quote verbatim and one published limitation.
Seven checks, such as every quote verbatim and at least one published limitation.
Publication gateBuilds a docs link, sales one-pager, community post or talk material after approval.
Builds a docs cross-link, a sales one-pager, a community post or talk material, after approval.
Derivative versions
From the official docs
Permissions
Low risk
developer-case-study is interview and writing instructions with no scripts, and it may save notes to devrel-context.md.
What it can do
- Read your data
- Create and change things
- Delete things
- Read-only mode
Watch out for
Customer data you paste can leave the customer's control
SKILL.md has you work from interview transcripts and the customer's metrics. Paste only what you are cleared to share, and get approval before publishing anything drawn from them. github.com
It may save notes to devrel-context.md
SKILL.md tells Claude to keep task and project context in devrel-context.md when memory lives in a file, or in the memory system your tool already uses. Check the file before you commit it. github.com
The whole-set install adds 93 skills, 14 with scripts
The README says to install every skill. The git tree has 93 skill folders, and 14 of them hold .py or .sh files. This skill bundles no scripts, and the tree holds no hooks, agents or MCP config files. github.com
Technical details
| Turning on read-only | SKILL.md describes no read-only mode. |
|---|---|
| Sign-in and keys | SKILL.md names no account, key or token. |
| Scopes |
|
Questions
What does developer-case-study do?
It writes a technical case study about a customer's production use of your product. It checks the story is publishable first, builds an evidence ledger, drafts it with a limitations section and prepares the approval package.
How do I install it?
Use the install box at the top. The README says to install every skill in the repo, because the skills point to each other. The box shows the whole-set route for each app.
Will it make up numbers or quotes?
SKILL.md tells Claude not to. It says never to compute a number the customer did not confirm, and to copy quotes verbatim from the transcript. Every number needs a value before, a value after, an instrument and a window.
What if the customer will not let me name them?
SKILL.md describes a five-rung anonymization ladder, from named company and engineer down to a pattern write-up with no customer. It says to take the highest rung approval allows, and that the last rung is no longer a case study.
Is it safe to install?
The skill bundles no scripts. Customer interview transcripts, metrics and contract details you paste go into your conversation, so share only what you are cleared to. The whole-set install adds 93 skills, 14 of which bundle scripts.
How is it different from engineering-blog-post?
This skill is for a customer's story that needs their numbers and approval. SKILL.md routes a post about your own system to samber/developer-relations-skills@engineering-blog-post.
Information
updated Nov 2, 2026
- Repository
- samber/developer-relations-skills
- Folder
skills/developer-case-study
Sources
Docs, issue trackers and discussions this page is built from.
Show all 3Hide
- README · github.com
- developer-case-study SKILL.md · github.com
- LICENSE · github.com