all publishers

srid

@srid source repo

67 published skills

  1. ▌
    CI 4 · srid
    Reference for the `justci` runner — how to invoke a full pipeline, a single recipe, or a platform-pinned node from a project that depends on `juspay/justci`. Trigger when the user asks to "run justci", "run the pipeline", "re-run a check", or names a specific recipe by `<recipe>@<platform>`.
    968 repo stars
  2. ▌
    Do 4 · srid bundle
    Do a task end-to-end — implement, PR, CI loop, ship
    968 repo stars
  3. ▌
    Lowy 4 · srid
    Evaluate architecture and module boundaries for volatility-based decomposition using Juval Lowy's framework (from "Righting Software", building on Parnas 1972). Use when reviewing module splits, service boundaries, new abstractions, or any decomposition decision. Trigger on phrases like "where should this boundary be", "how to split this", "module boundaries", "encapsulate change", "volatility", or references to Lowy, Parnas, or "Righting Software". Complements /hickey (interleaved concerns) with a different lens (change encapsulation).
    968 repo stars
  4. ▌
    Talk 4 · srid
    Enter talk mode — conversation and research, no repo changes
    968 repo stars
  5. ▌
    Hickey 4 · srid bundle
    Evaluate code (especially LLM-generated) for structural simplicity using Rich Hickey's "Simple Made Easy" framework. Use this skill whenever reviewing a PR, diff, or code snippet for accidental complexity — particularly when the code was generated by an AI coding assistant and line-by-line review isn't feasible. Also use when the user asks about complecting, simplicity vs. easiness, structural coupling, or wants architecture fitness functions for a codebase. Trigger on phrases like "is this simple", "does this complect", "review for complexity", "structural analysis", "fitness function", or any reference to Hickey, Simple Made Easy, or grey-box review.
    968 repo stars
  6. ▌
    Code Police 4 · srid
    Review code for quality, simplicity, and common mistakes before declaring work complete.
    968 repo stars
  7. ▌
    Kolu 3 · srid
    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 create→send→snapshot loop run with the `kaval-tui` CLI directly (no MCP). `kaval-tui` writes input, reads scrollback, and provides a hook-free done-signal (`wait --until idle:<ms>` on raw PTY output); `pulam-tui` adds a precise agent-state done-signal when you drive hooked terminals. Triggers on "drive another agent", "send a prompt to a terminal agent", "have one agent prompt another", "agent drives agent", "orchestrate agents in terminals", "make Claude drive Codex", "prompt the agent running in that terminal", or wiring a loop where one coding agent supervises another.
    968 repo stars
  8. ▌
    CI 3 · srid
    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. Trigger when the user asks to "run CI", "run the pipeline", "re-run a check", or names a specific recipe by `<recipe>@<platform>`.
    968 repo stars
  9. ▌
    Be 3 · srid
    Modern, interactive alternative to `/do` — clarify intent up front, then take a task end-to-end with an AI review gauntlet (codex debate → lens debate (lowy ⇄ hickey) → code-police → CI → evidence). ONLY invoke when the user explicitly types `/be` or `$be`; never auto-select from a natural-language request.
    968 repo stars
  10. ▌
    Lens Debate 3 · srid bundle
    Run a structural-review debate between two lenses — lowy (volatility-based decomposition) and hickey (structural simplicity) — on the current diff. Each reviews independently, then they cross-examine every finding until they agree per-finding, and the agreed fixes are applied. Use when the user types `/lens-debate`, or asks to "have lowy and hickey review this", "run the lens debate", "debate this diff structurally", or "argue the structure of this PR until the lenses agree".
    968 repo stars
  11. ▌
    Codex Debate 3 · srid bundle
    Run an automated code-review debate between the codex CLI (reviewer) and a Claude subagent (author) on the current diff, looping until they reach consensus — no round cap, no deadlock exit. Use when the user types `/codex-debate`, or asks to "have codex review this", "run the codex debate", "review this PR with codex", or "argue this with codex until you agree".
    968 repo stars
  12. ▌
    Talk 3 · srid
    Enter talk mode — conversation and research, no repo changes
    968 repo stars
  13. ▌
    Do 3 · srid bundle
    Do a task end-to-end — implement, PR, CI loop, ship
    968 repo stars
  14. ▌
    Lowy 3 · srid
    Evaluate architecture and module boundaries for volatility-based decomposition using Juval Lowy's framework (from "Righting Software", building on Parnas 1972). Use when reviewing module splits, service boundaries, new abstractions, or any decomposition decision. Trigger on phrases like "where should this boundary be", "how to split this", "module boundaries", "encapsulate change", "volatility", or references to Lowy, Parnas, or "Righting Software". Complements /hickey (interleaved concerns) with a different lens (change encapsulation).
    968 repo stars
  15. ▌
    Hickey 3 · srid bundle
    Evaluate code (especially LLM-generated) for structural simplicity using Rich Hickey's "Simple Made Easy" framework. Use this skill whenever reviewing a PR, diff, or code snippet for accidental complexity — particularly when the code was generated by an AI coding assistant and line-by-line review isn't feasible. Also use when the user asks about complecting, simplicity vs. easiness, structural coupling, or concept deduplication. Trigger on phrases like "is this simple", "does this complect", "review for complexity", "structural analysis", or any reference to Hickey, Simple Made Easy, or grey-box review.
    968 repo stars
  16. ▌
    Forge Pr 2 · srid
    Write engaging PR titles and descriptions for any forge (GitHub today; Bitbucket planned). Use when creating or updating PRs. Avoids boring bullet lists; uses narrative paragraphs with bold/italic for emphasis.
    968 repo stars
  17. ▌
    Code Police 3 · srid
    Review code for quality, simplicity, and common mistakes before declaring work complete.
    968 repo stars
  18. ▌
    Debate 2 · srid
    Use when the user wants a structured debate between this agent and one other AI agent running on a Kolu terminal — set the stance and end-state, exchange turns via the kolu skill, and optionally converge on a ratified ledger of agreed facts. With --orchestrate, this agent steps out of the debate and only coordinates N≥2 external agents on N terminals. Triggers on "debate <topic> with the agent on terminal …", "have Codex/opencode debate me", "start a debate", "run an LLM debate", "argue this back and forth with another agent", "orchestrate a debate between terminals …".
    968 repo stars
  19. ▌
    Ralph 2 · srid
    Iterative measurement-driven improvement loop. Measure, profile, mutate, re-measure, commit. Works for performance, bundle size, complexity, test coverage — anything quantifiable. Use when the user wants to systematically improve a metric through repeated cycles of profiling and targeted changes.
    968 repo stars
  20. ▌
    Talk 2 · srid
    Enter talk mode — conversation and research, no repo changes. ONLY invoke when the user explicitly types `/talk` or `$talk`; never auto-select from a natural-language question or design discussion.
    968 repo stars
  21. ▌
    Hickey 2 · srid bundle
    Evaluate code (especially LLM-generated) for structural simplicity using Rich Hickey's "Simple Made Easy" framework. Use this skill whenever reviewing a PR, diff, or code snippet for accidental complexity — particularly when the code was generated by an AI coding assistant and line-by-line review isn't feasible. Also use when the user asks about complecting, simplicity vs. easiness, structural coupling, or concept deduplication. Trigger on phrases like "is this simple", "does this complect", "review for complexity", "structural analysis", or any reference to Hickey, Simple Made Easy, or grey-box review.
    968 repo stars
  22. ▌
    Nix For Dev 2 · srid
    Use this when setting up Nix for a development project (devShell + package build) and you care about `nix develop` being fast. Covers the zero-inputs flake.nix + npins + default.nix/shell.nix layout, sub-flakes for non-user-facing Nix, and language-specific recommendations.
    968 repo stars
  23. ▌
    Nix Chrome Devtools MCP 2 · srid bundle
    chrome-devtools-mcp launcher — a single bash script that resolves Playwright's bundled Chrome-for-Testing and Node.js directly through Nix. See repo README for usage, override mechanisms, and version compatibility.
    968 repo stars
  24. ▌
    Do 2 · srid bundle
    Do a task end-to-end — implement, PR, CI loop, ship. ONLY invoke when the user explicitly types `/do` or `$do`; never auto-select from a natural-language request, even one that sounds like an end-to-end task.
    968 repo stars
  25. ▌
    Pu 2 · srid
    Provision and drive a `pu` box — an Incus container used as a clean Linux host for CI, builds, and evidence capture. Use when you need to run something on a fresh remote box instead of the user's machine: `nix run` a build, run CI against a real host, capture screenshots/video off-machine, or reproduce on a pristine environment. Covers create/connect/scp/destroy, running remote commands, copying artifacts back, and the no-egress failure mode. Triggers on "pu box", "spin up a box", "run this on a box", "ephemeral host", "pu create/connect/destroy".
    968 repo stars
  26. ▌
    Be 2 · srid
    Modern, interactive alternative to `/do` — clarify intent up front, then take a task end-to-end with a serial AI review gauntlet (lens debate (lowy ⇄ hickey) → codex debate → simplify → code-police, each editing the branch in turn) → CI → evidence. ONLY invoke when the user explicitly types `/be` or `$be`; never auto-select from a natural-language request.
    968 repo stars
  27. ▌
    CI 2 · srid
    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. Trigger when the user asks to "run CI", "run the pipeline", "re-run a check", to run named lanes or recipes (e.g. "run fmt and nix", "just the e2e lane", bare selectors like `fmt`/`nix`/`e2e`), or names a recipe by `<recipe>@<platform>`. This skill — not a repo's local `just ci` / `just <recipe>` — is how an odu-run request is served.
    968 repo stars
  28. ▌
    Lowy 2 · srid
    Evaluate architecture and module boundaries for volatility-based decomposition using Juval Lowy's framework (from "Righting Software", building on Parnas 1972). Use when reviewing module splits, service boundaries, new abstractions, or any decomposition decision. Trigger on phrases like "where should this boundary be", "how to split this", "module boundaries", "encapsulate change", "volatility", or references to Lowy, Parnas, or "Righting Software". Complements /hickey (interleaved concerns) with a different lens (change encapsulation).
    968 repo stars
  29. ▌
    Kolu 2 · srid
    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 create→send→snapshot loop run with the `kaval-tui` CLI directly (no MCP). `kaval-tui` writes input and reads scrollback; `pulam-tui` adds a precise agent-state done-signal when you drive hooked terminals. Triggers on "drive another agent", "send a prompt to a terminal agent", "have one agent prompt another", "agent drives agent", "orchestrate agents in terminals", "make Claude drive Codex", "prompt the agent running in that terminal", or wiring a loop where one coding agent supervises another.
    968 repo stars
  30. ▌
    Odu MCP 2 · srid bundle
    odu MCP server launcher — drive CI from a coding agent. `bin/serve` resolves odu via Nix and runs `odu mcp` in the cwd. See the repo README for the tools/resources and override knobs.
    968 repo stars
  31. ▌
    Surface 2 · srid
    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 hooks or a CLI), and mirroring a remote surface over ssh. Grounded in the real consumers: kolu, pulam-web, drishti, odu, and the TUIs. Load when wiring a surface server/client/mirror, or reaching for getHostSession / a link / the `.use()` hooks. CHANGING the framework is gated separately — `.claude/rules/surface.md` (a paired, CI-green drishti PR pinned to final kolu HEAD).
    968 repo stars
  32. ▌
    Be Review 2 · srid
    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. Use from /be §4, or when the user asks to "run the review gauntlet". Requires Claude Code's Skill tool.
    968 repo stars
  33. ▌
    Dpella MCP 2 · srid
    Reference for the dpella/mcp Haskell library — types, handler shape, transports, and the conventions Emanote uses. Load this before adding MCP resources/tools/subscriptions so you don't re-discover the API by WebFetch.
    968 repo stars
  34. ▌
    Code Police 2 · srid
    Review code for quality, simplicity, and common mistakes before declaring work complete.
    968 repo stars
  35. ▌
    Lens Debate 2 · srid bundle
    Run a structural-review debate between two lenses — lowy (volatility-based decomposition) and hickey (structural simplicity) — on the current diff. Each reviews independently, then they cross-examine every finding until they agree per-finding, and the agreed fixes are applied. Use when the user types `/lens-debate`, or asks to "have lowy and hickey review this", "run the lens debate", "debate this diff structurally", or "argue the structure of this PR until the lenses agree".
    968 repo stars
  36. ▌
    Codex Debate 2 · srid bundle
    Run an automated codex⇄Claude debate to consensus — no round cap, no deadlock exit. Two explicit subcommands. `review` (also the bare/back-compat default) — codex (reviewer) critiques the current diff and a Claude subagent (author) fixes/disputes, looping until they agree. `answer` — Claude and codex each answer a freeform prompt in parallel, then cross-check until they agree, and a unified answer is returned. Use when the user types `/codex-debate`, asks to "have codex review this", "run the codex debate", "review this PR with codex", "argue this with codex until you agree", or passes a question to "have Claude and codex debate/answer until they agree".
    968 repo stars
  37. ▌
    Nix Playwright 2 · srid
    Use this when adding Nix-based local runs for an existing Playwright e2e suite. Provides a self-contained `tests/shell.nix` that uses `nixpkgs-latest` for `playwright-driver.browsers`, plus a justfile entry — works on NixOS where `npx playwright install --with-deps` cannot.
    968 repo stars
  38. ▌
    Perfection Review 2 · srid
    Adversarial "perfection" review — hold a change to an *ideal* bar, not just a correct one, assuming eternal time, unlimited energy, and no ship pressure. Use when the user asks to review "for perfection", to make a defect "impossible to express", or to hunt where a defect "relocates" across review rounds. Grounds every claim in the diff, fans out adversarial verifiers via Workflow, and reports residual surfaces with a structural fix for each. ONLY invoke when the user explicitly asks for a perfection / ideal-bar review.
    968 repo stars
  39. ▌
    Debate · srid
    Use when the user wants a structured debate between this agent and one other AI agent running on a Kolu terminal — set the stance and end-state, exchange turns via the kolu skill, and optionally converge on a ratified ledger of agreed facts. With --orchestrate, this agent steps out of the debate and only coordinates N≥2 external agents on N terminals. Triggers on "debate <topic> with the agent on terminal …", "have Codex/opencode debate me", "start a debate", "run an LLM debate", "argue this back and forth with another agent", "orchestrate a debate between terminals …".
    968 repo stars
  40. ▌
    Github Pr · srid
    Write engaging GitHub PR titles and descriptions. Use when creating or updating PRs. Avoids boring bullet lists; uses narrative paragraphs with bold/italic for emphasis.
    968 repo stars
  41. ▌
    Nix Chrome Devtools MCP · srid bundle
    chrome-devtools-mcp launcher — a single bash script that resolves Playwright's bundled Chrome-for-Testing and Node.js directly through Nix. See repo README for usage, override mechanisms, and version compatibility.
    968 repo stars
  42. ▌
    Nix For Dev · srid
    Use this when setting up Nix for a development project (devShell + package build) and you care about `nix develop` being fast. Covers the zero-inputs flake.nix + npins + default.nix/shell.nix layout, sub-flakes for non-user-facing Nix, and language-specific recommendations.
    968 repo stars
  43. ▌
    Nix Justfile · srid
    Conventions for writing justfile recipes in Nix-based projects.
    968 repo stars
  44. ▌
    Odu MCP · srid bundle
    odu MCP server launcher — drive CI from a coding agent. `bin/serve` resolves odu via Nix and runs `odu mcp` in the cwd. See the repo README for the tools/resources and override knobs.
    968 repo stars
  45. ▌
    Nix Oss Cache · srid
    Use this when setting up a GitHub repo to push its Nix builds to Juspay's shared OSS Attic cache (cache.nixos.asia/oss) — adds the substituter to flake.nix, a nix-cache.yml GitHub Actions workflow, and prompts for the ATTIC_TOKEN secret.
    968 repo stars
  46. ▌
    Pu · srid
    Provision and drive a `pu` box — an Incus container used as a clean Linux host for CI, builds, and evidence capture. Use when you need to run something on a fresh remote box instead of the user's machine: `nix run` a build, run CI against a real host, capture screenshots/video off-machine, or reproduce on a pristine environment. Covers create/connect/scp/destroy, running remote commands, copying artifacts back, and the no-egress failure mode. Triggers on "pu box", "spin up a box", "run this on a box", "ephemeral host", "pu create/connect/destroy".
    968 repo stars
  47. ▌
    Evidence · srid
    Produce visual PR evidence — a screenshot or a video — whenever a change has on-screen impact. If exercising the change would make the screen look different (a rendered view, an error/empty/loading/blocked state, a panel, layout, an icon, motion, a live update) a visual artifact is MANDATORY, not optional. A change can be backend by cause and visible by effect: tests are never a substitute for a visual artifact when there is on-screen impact. Capture rides the project's own Cucumber + Playwright e2e harness on an ephemeral pu box (video of a flow, or a still pulled from the clip), or drives a live kolu with the chrome-devtools MCP for a state no scenario reaches. Then transcode (ffmpeg), host on a GitHub release, and post a `## Evidence` comment. Triggers on "post evidence", "screenshot the change", "PR evidence", "record a video of this", "capture the UI", "show it working", "prove it", or finishing any change whose effect is visible on screen.
    968 repo stars
  48. ▌
    Nix Typescript · srid
    pnpm + Nix build conventions. Covers fetchPnpmDeps hash management and dependency workflow.
    968 repo stars
  49. ▌
    Do · srid bundle
    Do a task end-to-end — implement, PR, CI loop, ship. ONLY invoke when the user explicitly types `/do` or `$do`; never auto-select from a natural-language request, even one that sounds like an end-to-end task.
    968 repo stars
  50. ▌
    Lowy · srid
    Evaluate architecture and module boundaries for volatility-based decomposition using Juval Lowy's framework (from "Righting Software", building on Parnas 1972). Use when reviewing module splits, service boundaries, new abstractions, or any decomposition decision. Triggers on "where should this boundary be", "how to split this", "module boundaries", "volatility", or references to Lowy, Parnas, or "Righting Software". Complements /hickey (interleaved concerns) with a change-encapsulation lens.
    968 repo stars
  51. ▌
    Talk · srid
    Enter talk mode — conversation and research, no repo changes. ONLY invoke when the user explicitly types `/talk` or `$talk`; never auto-select from a natural-language question or design discussion.
    968 repo stars
  52. ▌
    Ralph · srid
    Iterative measurement-driven improvement loop. Measure, profile, mutate, re-measure, commit. Works for performance, bundle size, complexity, test coverage — anything quantifiable. Use when the user wants to systematically improve a metric through repeated cycles of profiling and targeted changes.
    968 repo stars
  53. ▌
    Hickey · srid bundle
    Evaluate code (especially LLM-generated) for structural simplicity using Rich Hickey's "Simple Made Easy" framework. Use when reviewing a PR, diff, or snippet for accidental complexity, or when the user asks about complecting, simplicity vs. easiness, structural coupling, or concept deduplication. Triggers on "is this simple", "does this complect", "review for complexity", or any reference to Hickey / Simple Made Easy.
    968 repo stars
  54. ▌
    Elegance · srid
    Iteratively study and apply elegant coding patterns. Each iteration - understand the code, research what simple and elegant code looks like, apply learnings, verify with CI. Use as a standalone refactoring pass or when the user asks to make code more elegant, simple, or idiomatic.
    968 repo stars
  55. ▌
    Forge Pr · srid bundle
    Write engaging PR titles and descriptions for any forge (GitHub today; Bitbucket planned). Use when creating or updating PRs. Leads with narrative paragraphs and reaches for lists, tables, and diagrams when content is genuinely structured.
    968 repo stars
  56. ▌
    Fact Check · srid
    Audit code for correctness and rigor — logic errors, silent error swallowing, wishful thinking, and unjustified fallbacks. This is not a style review; it's a logic review. Use when you want a focused correctness audit separate from the full code-police pass.
    968 repo stars
  57. ▌
    Code Police · srid
    Review code for quality, simplicity, and common mistakes before declaring work complete.
    968 repo stars
  58. ▌
    Be · srid
    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, each editing the branch in turn) → CI → evidence. ONLY invoke when the user explicitly types `/be` or `$be`; never auto-select from a natural-language request.
    968 repo stars
  59. ▌
    CI · srid
    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. Trigger when the user asks to "run CI", "run the pipeline", "re-run a check", to run named lanes or recipes (e.g. "run fmt and nix", "just the e2e lane", bare selectors like `fmt`/`nix`/`e2e`), or names a recipe by `<recipe>@<platform>`. This skill — not a repo's local `just ci` / `just <recipe>` — is how an odu-run request is served.
    968 repo stars
  60. ▌
    Kolu · srid
    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 create→send→snapshot loop run with the `kaval-tui` CLI directly (no MCP). `kaval-tui` writes input and reads scrollback; `pulam-tui` adds a precise agent-state done-signal when you drive hooked terminals. Triggers on "drive another agent", "send a prompt to a terminal agent", "have one agent prompt another", "agent drives agent", "orchestrate agents in terminals", "make Claude drive Codex", "prompt the agent running in that terminal", or wiring a loop where one coding agent supervises another.
    968 repo stars
  61. ▌
    Surface · srid
    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 hooks or a CLI), and mirroring a remote surface over ssh. Grounded in the real consumers: kolu, pulam-web, drishti, odu, and the TUIs. Load when wiring a surface server/client/mirror, or reaching for getHostSession / a link / the `.use()` hooks. CHANGING the framework is gated separately — `.claude/rules/surface.md` (a paired, CI-green drishti PR pinned to final kolu HEAD).
    968 repo stars
  62. ▌
    Dpella MCP · srid
    Reference for the dpella/mcp Haskell library — types, handler shape, transports, and the conventions Emanote uses. Load this before adding MCP resources/tools/subscriptions so you don't re-discover the API by WebFetch.
    968 repo stars
  63. ▌
    Be Review · srid
    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. Use from /be §4, or when the user asks to "run the review gauntlet". Requires Claude Code's Skill tool.
    968 repo stars
  64. ▌
    Lens Debate · srid bundle
    Run a structural-review debate between two lenses — lowy (volatility-based decomposition) and hickey (structural simplicity) — on the current diff. Each reviews independently, then they cross-examine every finding until they agree per-finding, and the agreed fixes are applied. Use when the user types `/lens-debate`, or asks to "have lowy and hickey review this", "run the lens debate", "debate this diff structurally", or "argue the structure of this PR until the lenses agree".
    968 repo stars
  65. ▌
    Codex Debate · srid bundle
    Run an automated codex⇄Claude debate to consensus — no round cap, no deadlock exit. Two explicit subcommands. `review` (also the bare/back-compat default) — codex (reviewer) critiques the current diff and a Claude subagent (author) fixes/disputes, looping until they agree. `answer` — Claude and codex each answer a freeform prompt in parallel, then cross-check until they agree, and a unified answer is returned. Use when the user types `/codex-debate`, asks to "have codex review this", "run the codex debate", "review this PR with codex", "argue this with codex until you agree", or passes a question to "have Claude and codex debate/answer until they agree".
    968 repo stars
  66. ▌
    Nix Playwright · srid
    Use this when adding Nix-based local runs for an existing Playwright e2e suite. Provides a self-contained `tests/shell.nix` that uses `nixpkgs-latest` for `playwright-driver.browsers`, plus a justfile entry — works on NixOS where `npx playwright install --with-deps` cannot.
    968 repo stars
  67. ▌
    Perfection Review · srid
    Adversarial "perfection" review — hold a change to an *ideal* bar, not just a correct one, assuming eternal time, unlimited energy, and no ship pressure. Use when the user asks to review "for perfection", to make a defect "impossible to express", or to hunt where a defect "relocates" across review rounds. Grounds every claim in the diff, fans out adversarial verifiers via Workflow, and reports residual surfaces with a structural fix for each. ONLY invoke when the user explicitly asks for a perfection / ideal-bar review.
    968 repo stars