What exactly is broken in popular skills: references to files that are not bundled, actions taken without human approval, processes with no stopping condition. Everything here is measured from the skill text rather than judged by a model, so every line can be checked.
Generator
Stage files, create a commit, and push in one step. Use when the user asks to "stage commit and push", "add commit and push", "commit and push", or "commit and push my changes".
- Prose only: no discrete steps
- Does not say what the result is
tobihagemann/turbo · —
Analyzer
Run the code and documentation simplification passes together over one scope, launching every review agent concurrently before applying a single round of fixes. Use when the user a
- Prose only: no discrete steps
- Does not say what the result is
tobihagemann/turbo · —
Generator
Stage files and create a commit in one step with a message matching existing commit style. Use when the user asks to "stage and commit", "add and commit", "commit my changes", or "
- Prose only: no discrete steps
- Does not say what the result is
tobihagemann/turbo · —
Analyzer
Run the code and documentation simplification passes together over one scope, launching every review sub-agent concurrently before applying a single round of fixes. Use when the us
- Prose only: no discrete steps
- Does not say what the result is
tobihagemann/turbo · —
Analyzer
Renamed to /model-assessment in v6 (removed in v7).
- Prose only: no discrete steps
- Does not say what the result is
Aperivue/medsci-skills · —
Reference
Renamed to /imaging-data in v6 (removed in v7).
- Prose only: no discrete steps
- Does not say what the result is
Aperivue/medsci-skills · —
Reference
Renamed to /model-selection in v6 (removed in v7).
- Prose only: no discrete steps
- Does not say what the result is
Aperivue/medsci-skills · —
Analyzer
Renamed to /model-assessment in v6 (removed in v7).
- Prose only: no discrete steps
- Does not say what the result is
Aperivue/medsci-skills · —
Analyzer
Renamed to /model-assessment in v6 (removed in v7).
- Prose only: no discrete steps
- Does not say what the result is
Aperivue/medsci-skills · —
Reference
Renamed to /imaging-data in v6 (removed in v7).
- Prose only: no discrete steps
- Does not say what the result is
Aperivue/medsci-skills · —
Analyzer
Renamed to /model-assessment in v6 (removed in v7).
- Prose only: no discrete steps
- Does not say what the result is
Aperivue/medsci-skills · —
Reference
Renamed to /model-selection in v6 (removed in v7).
- Prose only: no discrete steps
- Does not say what the result is
Aperivue/medsci-skills · —
Analyzer
Use this Skill to exercise the Harness review fixture.
- Prose only: no discrete steps
- Does not say what the result is
skilld-dev/skilld · —
GeneratorGitHub
Predict small-molecule binding poses with DiffDock-L (Corso et al. 2023/2024, github.com/gcorso/DiffDock) — blind diffusion docking that places a ligand into a protein pocket witho
- Prose only: no discrete steps
- Does not say what the result is
aipoch/open-science · —
ReferenceGitHub
Structure prediction for protein, nucleic-acid, and small-molecule complexes with the Chai-1 foundation model (Chai Discovery 2024, github.com/chaidiscovery/chai-lab). Reach for th
- Prose only: no discrete steps
- Does not say what the result is
aipoch/open-science · —
Reference
plugin/Skill repair, marketplace, statusline, model profiles/source sync, 1M/[1m] context, usage/quota reset ping, memory→docs, .txt repair, MCP startup context. Routes Claude Code
- Prose only: no discrete steps
- Does not say what the result is
daymade/claude-code-skills · —
Analyzer
Routes finance: Bigdata/RavenPack, US fundamentals/yfinance, A-share news/policy, sector Top N/公告, Gangtise/岗底斯 setup. Reads one bundled specialist. Pharma reporting and general ar
- Prose only: no discrete steps
- Does not say what the result is
daymade/claude-code-skills · —
Analyzer
Drive and verify an Electron or Tauri desktop app from the inside, including the main-process and Rust IPC calls a browser tool cannot see. Use when a desktop app needs testing, wh
- Prose only: no discrete steps
- Does not say what the result is
reticlehq/reticle · —
AnalyzerPlaywright
Turn a user journey you just clicked through into a saved regression check that re-runs deterministically, with no model in the loop and no test code to write. Use when you have dr
- Prose only: no discrete steps
- Does not say what the result is
reticlehq/reticle · —
Analyzer
Find out why something in a running web app does not work, when the console is empty and the code looks correct. Reads the click, the request, the store and the console together an
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- Prose only: no discrete steps
- Does not say what the result is
reticlehq/reticle · —
Generator
Use when writing Python scripts that must run on Windows, Linux, and macOS — especially when Rich or Typer output breaks on Windows, when dealing with Unicode/encoding errors, ANSI
- Prose only: no discrete steps
- Does not say what the result is
Jamie-BitFlight/claude_skills · —
Reference
Use when independently hunting Python code smells, deviations from engineering standards, maintenance hazards, or suspicious design choices in a bounded review surface.
- Prose only: no discrete steps
- Does not say what the result is
Jamie-BitFlight/claude_skills · —
Analyzer
Use when checking skill quality, validating frontmatter before commit, or diagnosing validator warnings. Runs the plugin validator on a skill, agent, or plugin directory — reports
- Prose only: no discrete steps
- Does not say what the result is
Jamie-BitFlight/claude_skills · —
Integration
Deprecated alias. Play work is now part of `deepline-gtm`, and the CLI documents plays itself. Use when a user or script still invokes `/deepline-plays`: immediately load and follo
- Prose only: no discrete steps
- Does not say what the result is
getaero-io/gtm-eng-skills · —
Reference
Helps with stuff.
- 1 test cases, all positive: not one "should refuse" or "should ask first"
- Prose only: no discrete steps
- Does not say what the result is
confluentinc/agent-skills · —