Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add KirKruglov/claude-skills-kit --skill retention-cohort-interpretergit clone --depth 1 https://github.com/KirKruglov/claude-skills-kitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/kirkruglov/claude-skills-kit/retention-cohort-interpreter)<a href="https://agentmods.dev/skills/kirkruglov/claude-skills-kit/retention-cohort-interpreter"><img src="https://agentmods.dev/badge/skills/kirkruglov/claude-skills-kit/retention-cohort-interpreter/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kirkruglov/claude-skills-kit/retention-cohort-interpreter"><img src="https://agentmods.dev/badge/skills/kirkruglov/claude-skills-kit/retention-cohort-interpreter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00103 | $0.01889 |
| Opus 5 | $0.00051 | $0.00945 |
| Sonnet 5 | $0.00021 | $0.00378 |
| Haiku 4.5 | $0.00010 | $0.00189 |
Grade A, and why
retention-cohort-interpreter scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Retention Cohort Interpreter
This skill interprets cohort retention tables for product managers and analysts, translating raw retention data into actionable plain-language diagnostics. Paste any cohort table (CSV or markdown) and receive a structured report: curve health assessment, key drop-off windows, industry benchmark comparison, hypotheses, and prioritized next steps.
Input:
- Cohort retention table (pasted as CSV, markdown table, or space-separated numbers; rows = cohorts, columns = time periods, values = % retained or user counts)
- Optional: product type (mobile app / SaaS / marketplace / consumer), cohort definition, current goal context
Output:
- Structured markdown report with sections: Curve Health, Key Drop-off Points, Benchmark Comparison, Hypotheses, Recommended Next Steps
Language Detection
Detect the user's language from their message:
- If Russian (or contains Cyrillic): respond in Russian
- If English (or other Latin-script language): respond in English
- If ambiguous: respond in the language of the trigger phrase used
Instructions
Step 1: Validate and Parse Input
-
Check that a retention table is provided
- If no table provided (description only, or question without data): stop and report: "Retention table required. Paste your cohort data as a CSV, markdown table, or plain numbers with headers."
-
Identify table structure
- Rows = cohorts (signup week/month, acquisition channel, or similar)
- Columns = time periods (D1, D7, D30 or Week 1, Week 2, etc.)
- Values = retention % (0–100 or 0–1 scale) or absolute user counts
-
Validate structure
- If single row or single column: stop and report: "Table structure not recognized. Expected: rows = cohorts, columns = time periods, values = retention % or user counts."
- If non-numeric cell values (excluding headers): stop with same message
-
Detect value type
- If values > 100 or the table clearly shows descending absolute counts (not percentages): treat as absolute counts; convert each value to % relative to the period-0 (first column) value for that cohort; note conversion in the output
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 173 lines · 103 tokens per session scan A 4c69374d4086
retention-cohort-interpreter is a skill published in the GitHub repository KirKruglov/claude-skills-kit (18 stars, last pushed 1mo ago), licensed MIT. It adds 103 tokens to every session and 1,889 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
spark-video-director
Translate a screenplay (one scene at a time) into a provider-agnostic storyboard fragment for the spark-video pipeline. Wraps Shanyin Super Director Master when available — the upstream Shanyin SKILL is the single source of truth for craft when present.
spark-video-episode
One-shot autopilot orchestrator — runs the full spark-video pipeline (screenwriter ↔ director per-scene parallel → render chain-DAG parallel + per-clip review → stitch). User confirms at 4 gates (+ 1 mode gate at start + 1 BGM gate when bgm/ folder detected). Use when the user wants "make me an episode" in one command.
vox-video-director
Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end with Aliyun Bailian CLI + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all automated. Use this whenever the user wants a "Vox style" video, a paper/torn-paper collage animation, a "motion collage"…
bailian-train-deploy
A workflow for using Alibaba Cloud’s Bailian command-line tool to fine-tune or directly deploy AI models as callable services. It covers text, speech-synthesis, image-generation, and video-generation models.
spark-video-cast
Scaffold and generate reference assets for characters (cast), locations (movie-set / set dressing), and key props — the three pillars of visual consistency in spark-video. Wraps bl image generate / edit for portrait creation. Use when adding new characters/locations/props or when costume/state changes are needed.
spark-video-screenwriter
Turn a user's premise into a structured screenplay (one scene at a time) for the spark-video pipeline. Wraps Shanyin Super Screenwriting Master when available — that upstream Shanyin SKILL is the single source of truth for craft when present.