GitHub user
Agent skills by srid
- skills
- 27
- repositories
- 2
Repositories by srid
Skills by srid, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Run an automated codex⇄Claude debate to consensus — no round cap, no deadlock exit. | srid/ | 963 | — | ~8.9k | Automated safety check: Pass | Unknown | 2 mo ago |
| 2 | 2.Forge PR Write engaging PR titles and descriptions for any forge (GitHub today; Bitbucket planned). | srid/ | 240 | — | ~1.2k | Automated safety check: Pass | MIT | 3 days ago |
| 3 | 3.Do Do a task end-to-end — implement, PR, CI loop, ship. An agent skill from srid/emanote. | srid/ | 963 | — | ~12k | Automated safety check: Pass | Unknown | 2 mo ago |
| 4 | Run /be's review gauntlet SERIALLY — /lens-debate (lowy ⇄ hickey), then /codex-debate, then /simplify, then code-police, each editing and committing on the live branch in turn. | srid/ | 963 | — | ~4.2k | Automated safety check: Pass | Unknown | 2 mo ago |
| 5 | 5.CI Reference for the odu runner — how to invoke a full pipeline, a single recipe, or a platform-pinned node, and how to attach to a live run, from a project whose CI odu runs. | srid/ | 963 | — | ~2.4k | Automated safety check: Pass | Unknown | 2 mo ago |
| 6 | 6.Do Do a task end-to-end — implement, PR, CI loop, ship. An agent skill from srid/haskell-flake. | srid/ | 240 | — | ~5.8k | Automated safety check: Pass | MIT | 3 days ago |
| 7 | 7.Forge PR Write engaging PR titles and descriptions for any forge (GitHub today; Bitbucket planned). | srid/ | 963 | — | ~2.6k | Automated safety check: Pass | Unknown | 2 mo ago |
| 8 | 8.Kolu Drive one AI agent from another through kolu's terminals: spawn a Claude Code / Codex / opencode session in a PTY, prompt it, watch the screen for its reply, read it, and prompt again — a… | srid/ | 963 | — | ~2.4k | Automated safety check: Pass | Unknown | 2 mo ago |
| 9 | Run a structural-review debate between two lenses — lowy (volatility-based decomposition) and hickey (structural simplicity) — on the current diff. | srid/ | 963 | — | ~3.7k | Automated safety check: Pass | Unknown | 2 mo ago |
| 10 | 10.Nix For Dev Use this when setting up Nix for a development project (devShell + package build) and you care about nix develop being fast. | srid/ | 963 | — | ~2.1k | Automated safety check: Pass | Unknown | 2 mo ago |
| 11 | Use this when adding Nix-based local runs for an existing Playwright e2e suite. | srid/ | 963 | — | ~557 | Automated safety check: Pass | Unknown | 2 mo ago |
| 12 | 12.Dpella MCP Reference for the dpella/mcp Haskell library — types, handler shape, transports, and the conventions Emanote uses. | srid/ | 963 | — | ~2k | Automated safety check: Pass | Unknown | 2 mo ago |
| 13 | 13.Elegance Iteratively study and apply elegant coding patterns. An agent skill from srid/emanote. | srid/ | 963 | — | ~602 | Automated safety check: Pass | Unknown | 2 mo ago |
| 14 | 14.Pu Provision and drive a pu box — an Incus container used as a clean Linux host for CI, builds, and evidence capture. | srid/ | 963 | — | ~822 | Automated safety check: Warn | Unknown | 2 mo ago |
| 15 | 15.Fact Check Audit code for correctness and rigor — logic errors, silent error swallowing, wishful thinking, and unjustified fallbacks. | srid/ | 963 | — | ~1.1k | Automated safety check: Pass | Unknown | 2 mo ago |
| 16 | Adversarial "perfection" review — hold a change to an ideal bar, not just a correct one, assuming eternal time, unlimited energy, and no ship pressure. | srid/ | 963 | — | ~773 | Automated safety check: Pass | Unknown | 2 mo ago |
| 17 | 17.Ralph Iterative measurement-driven improvement loop. An agent skill from srid/emanote. | srid/ | 963 | — | ~732 | Automated safety check: Pass | Unknown | 2 mo ago |
| 18 | 18.Talk Enter talk mode — conversation and research, no repo changes. | srid/ | 963 | — | ~4.4k | Automated safety check: Pass | Unknown | 2 mo ago |
| 19 | 19.Hickey Evaluate code (especially LLM-generated) for structural simplicity using Rich Hickey's "Simple Made Easy" framework. | srid/ | 963 | — | ~6.8k | Automated safety check: Pass | Unknown | 2 mo ago |
| 20 | 20.Lowy Evaluate architecture and module boundaries for volatility-based decomposition using Juval Lowy's framework (from "Righting Software", building on Parnas 1972). | srid/ | 963 | — | ~6.2k | Automated safety check: Pass | Unknown | 2 mo ago |
| 21 | 21.Nix Haskell Use this when working on a Haskell project with Nix. An agent skill from srid/emanote. | srid/ | 963 | — | ~327 | Automated safety check: Pass | Unknown | 2 mo ago |
| 22 | 22.Code Police Review code for quality, simplicity, and common mistakes before declaring work complete. | srid/ | 963 | — | ~4.1k | Automated safety check: Pass | Unknown | 2 mo ago |
| 23 | 23.Surface How a downstream app consumes the shared @kolu/surface stack (@kolu/surface · surface-app · surface-nix-host · surface-mcp) — declaring a typed reactive surface, serving it, consuming it (SolidJS… | srid/ | 963 | — | ~1.5k | Automated safety check: Pass | Unknown | 2 mo ago |
| 24 | 24.Nix Justfile Conventions for writing justfile recipes in Nix-based projects. | srid/ | 963 | — | ~173 | Automated safety check: Pass | Unknown | 2 mo ago |
| 25 | 25.Odu MCP odu MCP server launcher — drive CI from a coding agent. An agent skill from srid/emanote. | srid/ | 963 | — | ~446 | Automated safety check: Pass | Unknown | 2 mo ago |
| 26 | chrome-devtools-mcp launcher — a single bash script that resolves Playwright's bundled Chrome-for-Testing and Node.js directly through Nix. | srid/ | 963 | — | ~271 | Automated safety check: Pass | Unknown | 2 mo ago |
| 27 | 27.Be Modern, interactive alternative to /do — clarify intent up front, then take a task end-to-end with a serial AI review gauntlet (lens debate (lowy ⇄ hickey) → codex debate → simplify → code-police… | srid/ | 963 | — | ~5.4k | Automated safety check: Warn | Unknown | 2 mo ago |
Questions, answered from the data.
What is the best skill by srid?
Codex Debate from srid/emanote ranks first of the 27 skills by srid listed here, with the highest score: its repository has 963 GitHub stars, its SKILL.md loads about 8.9k tokens and it passes the automated safety check with no findings. Next come Forge PR and Do.
Are srid's skills official?
None yet. All 27 skills by srid listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.