Open-source repos
Claude Skills (Gleb Kalinin)
Meetings, research, publishing and personal ops
This page provides source information and editorial guidance. Recommendations and trust labels do not mean every skill here was tested. Results for individual skills are on the skill data pages. See skill data · Listing policy
Overview
Gleb Kalinin's skills for Claude Code cover meeting pipelines, research, image generation, TDD, publishing, personal analytics and Claude Code operations, with curated bundles.
SkillFlux sample check
On 2026-10-31, SkillFlux pinned this source at commit 046a4ce, drew a seeded sample of 20 from the 118 entries it contains, and ran static health check 1.0.0 on each. 85% had no failing check, said when to use the skill and carried a license.
- 20/20sampled entries had a SKILL.md we could check
- 1/20fail at least one check
- 2/20do not say when to use the skill
- 0/20have no license we could find
- 14/20bundle scripts the agent may run
- 4/20include scripts that call the network
- 0/20include destructive shell commands
- 1/20exceed the 5,000-token body guideline
See the 20 sampled entries
| Entry | Result | Flags |
|---|---|---|
| glebis/claude-skills/cull-release-recover | 15 pass, 0 warn, 0 fail | — |
| glebis/claude-skills/telegram | 14 pass, 1 warn, 0 fail | Bundles scripts the agent may run |
| glebis/claude-skills/tdd | 13 pass, 2 warn, 0 fail | Bundles scripts the agent may run |
| glebis/claude-skills/github-gist | 15 pass, 0 warn, 0 fail | Bundles scripts the agent may run, Scripts call the network |
| glebis/claude-skills/meeting-prep | 14 pass, 1 warn, 0 fail | Bundles scripts the agent may run |
| glebis/claude-skills/wispr-analytics | 15 pass, 0 warn, 0 fail | Bundles scripts the agent may run |
| glebis/claude-skills/confide/skills/rehydrate | 15 pass, 0 warn, 0 fail | Bundles scripts the agent may run |
| glebis/claude-skills/telegram-telethon | 13 pass, 2 warn, 0 fail | Bundles scripts the agent may run |
| glebis/claude-skills/skills/job-babysitter | 15 pass, 0 warn, 0 fail | Bundles scripts the agent may run |
| glebis/claude-skills/session-anonymizer | 15 pass, 0 warn, 0 fail | Bundles scripts the agent may run, Scripts call the network |
| glebis/claude-skills/confide/skills/audit | 15 pass, 0 warn, 0 fail | Bundles scripts the agent may run |
| glebis/claude-skills/skill-studio | 15 pass, 0 warn, 0 fail | Bundles scripts the agent may run, Scripts call the network |
| glebis/claude-skills/agency-socials | 15 pass, 0 warn, 0 fail | — |
| glebis/claude-skills/tg-responder | 15 pass, 0 warn, 0 fail | Bundles scripts the agent may run |
| glebis/claude-skills/cull-release-check | 15 pass, 0 warn, 0 fail | — |
| glebis/claude-skills/telegram-post | 14 pass, 1 warn, 0 fail | Bundles scripts the agent may run |
| glebis/claude-skills/present | 15 pass, 0 warn, 0 fail | Bundles scripts the agent may run, Scripts call the network |
| glebis/claude-skills/linear | 15 pass, 0 warn, 0 fail | — |
| glebis/claude-skills/thinking-patterns | 9 pass, 0 warn, 3 fail | — |
| glebis/claude-skills/jtbd | 14 pass, 1 warn, 0 fail | — |
The sample reads files only; it does not run any skill and does not describe entries outside the sample. Flags describe what a skill contains; they are not verdicts. Raw data · Method
Best for
- Solo builders automating their own workflows.
Use cases
- Planning & long tasks
- Content & writing
- Research & science
SkillFlux notes
Per-skill setup (API keys, dependencies) is in each SKILL.md; read it first.
Installation and use
Open the original repository and read its README, the selected skill instructions and any linked scripts. Check installation paths, host requirements, dependencies and licenses, then follow the project documentation to verify a small task in a workspace you can restore.
Limitations
- Skills reflect one person's tools and services.
Alternatives
- Auto-Empirical Research Skills (AERS)
Compare Auto-Empirical Research Skills (AERS) — Connect empirical identification, analysis planning and replication delivery.
- OthmanAdi/planning-with-files
Compare OthmanAdi/planning-with-files — File-based task planning.