tk
Software surgery: contract → invariants → creative search → inevitable incision; minimal diff, compositional core, proof signal.
Découvrez les skills Développement, comparez leurs dépôts et consultez leurs instructions.
Software surgery: contract → invariants → creative search → inevitable incision; minimal diff, compositional core, proof signal.
Review+fix protocol with safety guardrails (unsoundness, invariants, footguns, incidental complexity); requires a validation signal.
Unified shipping + TRACE self-review protocol (beads, proof, PR). Explicit-only.
Convert a project plan written in a Markdown file into a complete bd beads graph (tasks, subtasks, dependencies) using only bd for creation and edits, then review and optimize each bead. Use when asked to beadi...
Algebra-Driven Design (ADD): model domains via minimal algebra + laws; encode in types; test laws.
Gauntlet for absolute claims (always/never/guaranteed/optimal); pressure-test, then refine with explicit boundaries.
Finalize work after validation: confirm a signal, capture proof in PR description and bead comment (if beads), and open a PR (no merge). Use when asked to ship, finish, or open a PR.
Spawn Codex CLI sub-agents non-interactively with fixed model/effort and required flags (web search, skills, yolo). Use when dispatching a single agent per bead via codex exec with a positional prompt string an...
Automate Chrome/Chromium via CDP: navigate, click, fill forms, evaluate JS, screenshot, scrape.
Zig runbook: performance (SIMD + threads), build/test, comptime patterns, allocators, build.zig/build.zig.zon, zero-copy parsing, C interop.
PR autopilot: create/manage PRs, enforce CI gates, apply surgical fixes, and squash-merge via `gh`.
Create a new skill that encodes a team’s bead-implementation method and packages it as a .skill. Use only when the user explicitly says "$method".
Create a ghost-library repo from an existing library git repo by extracting a strict SPEC.md, exhaustive tests.yaml, INSTALL.md, README.md, VERIFY.md, and preserving upstream LICENSE files. Use only when a user...
Run validation loops (format/lint/typecheck/build/tests) and report signals. Use when asked to validate, run checks/tests, or repeat verification during work.
Iterate a markdown list of prompts in order, repeating passes until an explicit stop condition is met. Use when asked to loop over prompts or skills to drive work to completion.
Finalize GitHub PRs: update the branch/PR, monitor CI until green, squash-merge, and clean up local/remote state. Use for requests like finish/land/close a PR, monitor checks, squash and cleanup.
Editing mode for clarity and semantic density; use for prompts, docs, specs, emails, and naming.
Law-driven abstraction protocol: evidence first, seam test, minimal algebra, executable law check.
BMad Method v6: workflow-driven agile delivery (track selection, PRD/spec, UX, architecture, epics/stories).
Implement the Ralph Wiggum iterative AI loop for Codex/Claude Code: create /ralph-loop and /cancel-ralph commands, wire a stop hook or wrapper loop, persist a fixed prompt, track iterations, and detect a comple...
Finish the in-progress bead; validate via $close-the-loop; open a PR (do not merge). Explicit-only.
Jujutsu (jj) Git-compatible VCS. Use for any version-control work (status/diff/commit/branch/rebase/merge/etc.).
Lateral-thinking playbook for options and trade-offs; always deliver a five-tier strategy portfolio.
Mine Codex sessions to synthesize your top software design heuristics (no quotes, no evidence).
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.