Case studies
Curated, auditable, benchmark-ready Agent Skills library for Claude Code, Codex, OpenCode, Cursor, and more.
npx -y skills add shinzoxD/knackbox --skill case-studiesAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 29 days oldThe repository was created 29 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Write customer case studies with problem, solution, proof, and quote discipline. Use whenever the user asks for a case study, customer success story, proof point for sales, or customer story for the website.
The file declares its own license as Apache-2.0. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
1.4 KB, 207 tokens by cl100k_base, as published. Nobody here has run it
Case Studies
Case studies are evidence. Structure: challenge → solution → results → quote. If metrics or quotes are missing, mark placeholders — do not fabricate.
Structure
# <Customer> achieves <outcome> with <Product>
## At a glance
- Industry / size
- Use case
- Results (only verified)
## Challenge
## Solution
## Results
## Quote
## About <Customer>
Rules
- Never invent logos, quotes, or percentages.
- Prefer specific metrics user provides; else qualitative outcomes labeled.
- Get approval path noted when legal/customer marketing review required.
- Avoid feature dumps; tie capabilities to the challenge.
- SEO titles only if requested; accuracy first.
- Offer short (1-pager) and long versions when useful.
Edge cases
- Anonymous customer: still need verifiable internal proof.
- Early startup metrics tiny: honesty over hype.
- Multi-product story: one narrative thread.
What ships with it: 1 file
1.3 KB alongside SKILL.md
benchmarks/
- prompts.json1.3 KB
Gives 0 of the 12 instructions most sales audience skills give in 207 tokens
Counted across 401 of the 401 authors here whose files we hold, read 2026-08-07
- Read product marketing context before asking questionsin 21 of 401, across 11 files
- Acknowledge competitor strengths honestlyin 18 of 401, across 7 files
- Start every page with a summaryin 15 of 401, across 4 files
- Use a single, low-friction call to actionin 15 of 401, across 7 files
- Create a single source of truth for each competitorin 14 of 401, across 3 files
- Make each follow-up email add new valuein 11 of 401, across 5 files
- Cut any sentence that does not drive a replyin 10 of 401, across 4 files
- Tie personalization directly to the problemin 10 of 401, across 4 files
- Write paragraph comparisons for each dimensionin 9 of 401, across 3 files
- Link between related competitor pagesin 9 of 401, across 3 files
- Keep subject lines short and lowercasein 9 of 401, across 3 files
- Define ideal customer profile from top customersin 9 of 401, across 3 files
Said here and by no other author read
- use the challenge to results structure
- mark missing metrics or quotes as placeholders
- prefer specific metrics provided by the user
- label qualitative outcomes clearly
- note the approval path when reviews are required
- tie capabilities to the challenge
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.