Third degree
Skill ananthanandanan/skills/skills/engineering/third-degree
Interview the user to converge on a shared, concrete understanding of a feature before any planning or implementation — the front of the ank pipeline (third-degree → visualise-plan → review-board). Use whenever the user invokes /ank:third-degree, says they have a "rough idea", asks you to "flush out the requirements", "interview me", "interrogate me", or otherwise signals the spec is fuzzy and needs pinning down before code or a plan is written.From its SKILL.md
npx -y skills add ananthanandanan/skills --skill third-degreeAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 4 stars4 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.
- runs commandsInstructs the agent to run 1 command, including `grep the codebase`.
SKILL.md
1.5 KB, 213 tokens by cl100k_base, as published. Nobody here has run it
Third degree
The user has an idea but hasn't pressure-tested it. Interview them relentlessly — one question at a time — walking down each branch of the decision tree and resolving dependencies between decisions as you go. Before every question, grep the codebase for an existing convention, prior decision, or analogous feature that already answers it; if you find one, state the inferred answer in a single line ("Inferring X from path/to/file — say so if wrong.") and move on without asking. When you must ask, use AskUserQuestion with 2–4 concrete options and put your Recommended pick first with a one-line reason — never an open-ended prompt; structured options converge faster than free text. Keep going until you have genuine shared understanding — no fixed cap, but stop the moment further questions would just be ceremony. End by echoing back a tight bulleted summary of the resolved spec and asking "ready for /ank:visualise-plan?" — do not start planning or coding inside this skill.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 1 of the 12 instructions most plan spec skills give in 213 tokens
Counted across 1,360 of the 2,617 authors here whose files we hold, read 2026-09-06
- Ask one question at a timehere, and in 73 of 1360
- Write the spec using the templatein 22 of 1360
- Ask clarifying questions if neededin 19 of 1360, across 18 files
- Wait for user confirmation before proceedingin 19 of 1360
- Save plans to the plans directoryin 17 of 1360, across 13 files
- Check for product marketing context firstin 16 of 1360, across 5 files
- Read the plan file completelyin 16 of 1360
- Order tasks by dependencyin 16 of 1360
- Gather context from the conversationin 15 of 1360, across 9 files
- Explore the codebase instead of askingin 15 of 1360, across 13 files
- Wait for explicit user approvalin 14 of 1360, across 13 files
- Quiz the user on the breakdownin 13 of 1360, across 7 files
Said here and by no other author read
- Grep the codebase for existing conventions first
- State the inferred answer if found
- Use AskUserQuestion with concrete options
- Put the recommended pick first with a reason
- Echo back a tight bulleted summary of resolved spec
- Ask if ready for visualise plan
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.