9k tokens
context cost
the whole folder, loaded on every use
32
files
ships runnable scripts
0
copies elsewhere
how many repositories repackaged it
144
stars on the repo
on the repository, not the skill itself
Install
one command, takes just this skill from the repository
npx skills add https://github.com/naodeng/awesome-qa-skills --skill sprint-testing-workflow
Copy
What comes with it
34 832 bytes besides the instruction
The instruction itself
7 sections, as written by the author
Sprint Testing Workflow
中文版: See the corresponding Chinese skill.
When to Use
Need a sprint cadence: planning → setup → execution → regression → stabilize → review.
Need iteration gates and DoD with handoffs to type skills—not a one-off testing task.
Workflow
Read and follow prompts/sprint-testing-workflow.md (stages, gates, DoD, handoffs).
Add sprint goal, story scope, capacity, and carryover defects that change the plan.
After locating the stage, hand off by skill name per reference.md; no relative-path links to other skill internals.
If input is incomplete, draft a usable sprint test plan and mark assumptions and gaps.
Core Constraints
Own iteration phases and exit evidence; hand full artifacts to type skills.
Gates and DoD must be checkable.
On scope change, re-rank and state gate impact.
No relative-path links to other skill files.
Progressive Disclosure
Before producing output, read and follow prompts/sprint-testing-workflow.md.
For step ↔ handoff mapping: read reference.md.
For stage deep-dives: invoke the matching type skill; do not expand full artifacts here.
Templates: output-templates/.
Pre-delivery Checklist
[ ] Followed the main prompt’s output structure
[ ] Includes stage position, gate board, exit-criteria check, next skill
[ ] High-risk items have priority and Owner
[ ] Did not invent details the user did not provide
[ ] Assumptions, tradeoffs, and carryover are marked
Common Pitfalls
Do not write a day diary with no gates.
Do not dump full case bodies during planning.
Do not claim regression passed while development is still open-ended.
Do not replace exit evidence with “we tested a lot”.