From thinking
Decompose a request into Identifiable, Specific, Verifiable Criteria before executing. Use at the start of any non-trivial task to ensure nothing is missed.
npx claudepluginhub hpsgd/turtlestack --plugin thinkingThis skill is limited to using the following tools:
Decompose $ARGUMENTS into ISC (Identifiable, Specific, Verifiable Criteria) before executing.
Provides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.
Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.
Calculates TAM/SAM/SOM using top-down, bottom-up, and value theory methodologies for market sizing, revenue estimation, and startup validation.
Decompose $ARGUMENTS into ISC (Identifiable, Specific, Verifiable Criteria) before executing.
ISC is the foundation of the /algorithm skill's seven-phase methodology. It can also be used standalone for any task that benefits from upfront decomposition.
Most incomplete work comes from latching onto one part of a request and missing the rest. ISC forces you to read the entire request — including negatives and implied requirements — and turn it into a checklist you can verify.
Read everything. Extract five categories:
| Effort | Time budget | ISC range | When |
|---|---|---|---|
| Trivial | <30s | 2-4 | One-liner fix, typo |
| Quick | <1min | 4-8 | Small focused change |
| Standard | <2min | 8-16 | Normal request (default) |
| Extended | <8min | 16-32 | Multi-file quality work |
| Advanced | <16min | 24-48 | Substantial design + implementation |
| Deep | <32min | 40-80 | Complex multi-system work |
| Comprehensive | <120min | 64-150 | Large-scale, no time pressure |
Default to Standard unless the request clearly warrants more.
For each requirement, create a criterion that is:
Apply to EVERY criterion. If any test triggers, split:
Split differently depending on what you're working on:
Count your criteria. If below the effort tier floor, you haven't decomposed enough — go back and re-split.
| Effort | Minimum criteria |
|---|---|
| Trivial | 2 |
| Quick | 4 |
| Standard | 8 |
| Extended | 16 |
| Advanced | 24 |
| Deep | 40 |
| Comprehensive | 64 |
Below floor = re-decompose. You're grouping things that should be separate.
Present criteria as a numbered checklist:
- [ ] ISC-1: [atomic criterion]
- [ ] ISC-2: [atomic criterion]
...
Mark each criterion complete immediately as it passes during execution — don't batch at the end.
After completing the work, verify every criterion with evidence:
No criterion should be marked complete without evidence from a tool (Read, Bash, Grep, etc.). "I believe it's correct" is not verification.
Request: "Update the README, fix the broken links, and remove references to Chris"
Effort: Quick (4-8 ISC)
Criteria:
grep -i chris README.md returns nothing)The output is the ISC checklist produced in Step 5 — each criterion as a checkable item with its verification command. See the example in Step 5 above.
/algorithm — ISC decomposition is Phase 1 of the algorithm. Use the full algorithm for execution after defining criteria./scientific-method — when criteria require investigation or experimentation to verify.