Cecicela — Data skill for Claude Code
AI agent skills for coding agents: /ceci plans a goal as a job graph with human-in-the-loop gates, /cela proves every code, data, or ML model change with a tool-run evidence gate, /trouble debugs what.
How to install Cecicela
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open actviteai/cecicela and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Cecicela does
AI agent skills for coding agents: /ceci plans a goal as a job graph with human-in-the-loop gates, /cela proves every code, data, or ML model change with a tool-run evidence gate, /trouble debugs what breaks. Claude Code, Codex, Cursor, Copilot, Grok.
Alternatives in Data
- Agentlas Storm — Run a force-robust Stormbreaker loop — route to real agents, execute a verified pipeline to completion 1.1k ★
- Ralph The Marketer - Autonomous Copywriter Loop — You are starting the Ralph the Marketer autonomous copywriting agent 698 ★
- Deepdive — Deepdive skill for Claude Code — 12-phase research pipeline: plan-review gate, parallel sub-agent search, clai 297 ★
README
ceciCela
[](https://github.com/actviteai/cecicela/actions/workflows/ci.yml) [](https://www.npmjs.com/package/@actvite/cecicela) [](LICENSE)
ceci plans this, cela proves that, trouble fixes what breaks.
▶ **Video:** [ceciCela, explained](https://youtu.be/i5Ge36L_MTk) on the [actVite YouTube channel](https://www.youtube.com/channel/UCPlRHTUre-GPCK__77zI5IQ).
**ceciCela** is three agent skills for coding agents, shipped as one product:
| Skill | What it does | Package (latest on npm) |
|---|---|---|
| `/ceci` | Turns a goal into a job graph, runs ready jobs in dependency order, stops at human gates before contact, posting, payment, or pricing, places GPU jobs, and hands every code, data, or model change to /cela. |
 |
| `/cela` | The evidence gate. A bundled tool runs the checks, scores the oracles, and names the result (COMPLETE, STALLED, BLOCKED, MISSING_TEST), so the model never grades its own work. |
 |
| `/trouble` | A four-roles debug protocol for stuck bugs and incidents: verbatim evidence, Bayesian ranking, and no fix until the roles unanimously agree. Ends with a machine-parseable verdict. | [ ](https://www.npmjs.com/package/@actvite/tr |
Related Skills
AI Sdr OS
Production-grade agentic AI SDR (sales development rep) system: a 7-stage pipeline (Find, Score, Research, Per
Job Search Agent
A human-in-the-loop job search pipeline that pulls live postings from 7+ ATS platforms (Greenhouse, Lever, Ash
Coding Agent Harness
Nodaris AI's harness for coding agents. It plans before it edits, proves its work before it says done, keeps s
Eval Plan
Decide what an LLM eval actually measures, before any code exists - gather the change and its call path from t
Autoresearch Skill Andrej Karpathy
Claude Code skill for autonomous, goal-directed iteration. /autoresearch builds a real-data benchmark harness,
Fanout Loop
Execute ONE iteration of an effort's fan-out loop — pick-up, derive the run, dispatch a tier-laddered pipeline
Related Agents
Asvs Security Reviewer
Security gate for changes, built on OWASP ASVS 5.0.0. Plans security requirements before coding, reviews chang
Act 6 Analyst
Read-only narrative steward for Act VI (slides 22-24) — the Analyst agent demo that proves human-in-the-loop (
Repro Verifier
Evidence-driven verifier that proves or refutes the static quality gate's findings by writing and running repr
