Stella CLI Size Fit Advisor — Development skill for Claude Code
A four-question conversational agent that builds a sizing profile, maintains a live confidence score, and produces a fit recommendation.
How to install Stella CLI Size Fit Advisor
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open ShifaNasarV2001/Stella-CLI-Size-Fit-Advisor and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Stella CLI Size Fit Advisor does
A four-question conversational agent that builds a sizing profile, maintains a live confidence score, and produces a fit recommendation. Every sentence the user reads is generated by Claude; every number is computed by Python.
Alternatives in Development
- Market Sizing — Estimate TAM, SAM, SOM with top-down and bottom-up approaches 7.8k ★
- Obsidian Reconcile — Find and resolve contradictions in the vault — the vault maintains its own truth 277 ★
- Claude Code Auto Memory — Claude Code plugin that automatically maintains CLAUDE.md files 124 ★
README
Stella — CLI Size & Fit Advisor
A four-question conversational agent that builds a sizing profile, maintains a live confidence score, and produces a fit recommendation. Every sentence the user reads is generated by Claude; every number is computed by Python.
What works
- Full four-question interview, model-driven end to end — opening turn included.
- Live confidence score recomputed in Python after every answer, rendered as a 30-block progress bar with a numeric percent and a label.
- Confidence drops are narrated. A contradiction or a skipped question lowers the score, and the model is required to say why.
- One-follow-up rule. A vague answer earns exactly one clarifying question, then the interview advances regardless. Enforced in Python, not left to the model's discretion.
- Contradictions are recorded, not silently overwritten. Both values survive in state, the conflict is surfaced to the model, and the score takes a penalty.
- Declines are distinct from "I don't know". Declining caps the score at 80 permanently; not knowing is recoverable on the follow-up.
- Inspectable state via
/state, which dumps the whole session object plus the active prompt versions and model ID as JSON. - Graceful degradation. Empty input, gibberish, off-topic replies, hostile input, API timeouts, rate limits and schema-validation failures all produce a sensible turn and no traceback. A failed extraction rolls the user's turn back so a retry doesn't duplicate it.
- 52 unit tests covering the scoring arithmetic and state machine, including an exhaustive monotonicity check across all 256 specificity combinations.
- Session persistence —
/save FILEandpython run.py --resume FILE. - Per-call tracing to JSONL (
STELLA_TRACE=1): latency, tokens, prompt size.
Setup
python3 -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\aRelated Skills
Run Work
Propose portfolio batches (scan-only). No-target scan produces a batch recommendation; all target invocations
Case Team
Run a structured case team debate — four advisor voices collide on the investment-critical questions at a give
Helper
Ask my setup advisor which phase this project is in and which of my tools fit it, based on my claude-setup rep
Fit
Fit a job or sbatch script to what it actually used, with the sample size stated.
Hunt Gaps
Caça gaps num escopo, código ou plano - com severidade, evidência por linha e fechamento proposto.
Overclock Skill
Skill de orquestração multi-agente para o Claude Code. O Overclock transforma uma sessão única do Claude num g
Related Agents
Gap Coach
Reads a job description and tells the user what matches, what is missing, and what they can honestly do to clo
Ficc Outliner
FICC outline owner (T1E). The only seat that builds the tree and decides placement, selection, order, headings
Bh Verifier
Adversarial verifier of Black Heron audit. Runs AFTER all four lenses. Job is to CHALLENGE findings, not add t
