all publishers

veegee82

@veegee82 source repo

17 published skills

  1. ▌
    Adr Gate · veegee82
    ADR Gate — Architectural Decision Record discipline
    2 repo stars
  2. ▌
    Using Ldd · veegee82
    Use whenever the user prefixes a message with "LDD:" or mentions LDD, loss-driven development, loss, gradient, SGD on code, drift, refinement loop, outer loop, inner loop, method evolution, or "apply LDD". Bootstrap / entry-point skill that explains how to dispatch the other LDD skills and the trigger-phrase table they respond to.
    2 repo stars
  3. ▌
    Define Metric · veegee82
    Use when the agent or the user wants to introduce a new measurable quantity as a first-class loss component — e.g., tracking cyclomatic complexity alongside test_pass_rate, or adding a domain-specific rubric to a reasoning chain. Forbids ad-hoc arithmetic on observations and forbids using a new metric as a load-bearing decision gate until calibration has passed. Extends LDD's loss framework to agent-defined objectives without touching LDD core.
    2 repo stars
  4. ▌
    Architect Mode · veegee82
    Architect Mode — opt-in discipline, orthogonal to the four loops
    2 repo stars
  5. ▌
    Dialectical Cot · veegee82
    Use when a reasoning task requires a multi-step Chain-of-Thought (CoT) AND the task is verifiable (grounded answer, testable code, derivable proof). Forbids greedy step-by-step commitment — every step in the chain goes through thesis/antithesis/synthesis BEFORE entering the chain, using memory-primed antitheses to attack the proposed step. Produces a calibrated predicted-correctness per step and per chain. Applies SGD-on-thoughts in the same way `dialectical-reasoning` applies SGD-on-actions.
    2 repo stars
  6. ▌
    Drift Detection · veegee82
    Use periodically (weekly, at release candidates, before major version bumps) to scan a codebase for cumulative drift that no per-commit gate catches. Complements docs-as-definition-of-done, which prevents drift from being introduced per commit; this skill surfaces drift that already happened despite per-commit gates.
    2 repo stars
  7. ▌
    Host Statusline · veegee82 bundle
    Use at the start of any LDD session running under Claude Code — auto-installs a permanent statusline that shows the current LDD task, loop, iteration, loss, and a Unicode loss-curve sparkline at all times, without any user action or configuration. Idempotent, merge-safe, project-local. Silently no-ops on non-Claude-Code hosts. Fires once per session in parallel with `bootstrap-userspace`.
    2 repo stars
  8. ▌
    Method Evolution · veegee82
    Method-Evolution — the outer loop (`∂L/∂method`)
    2 repo stars
  9. ▌
    Loss Backprop Lens · veegee82
    Use when deciding whether to edit code at all, how large the edit should be, or whether a "working" fix actually generalizes. Applies when iterating on a failing test/run, chasing a flake, committing a sequence of small patches, or tempted to ship on one data point. Frames code changes as gradient steps and forbids overfitting to a single sample or a single test.
    2 repo stars
  10. ▌
    Bootstrap Userspace · veegee82 bundle
    Use at the start of any LDD task when there is no existing `.ldd/trace.log` readable in the working directory — fires before any other LDD skill writes trace state. Detects the host's persistence capabilities (filesystem, artifact/canvas, conversation-history, memory-pointer, inline-only), picks the most durable tier silently without prompting the user, restores any prior trace state it finds, and announces the chosen store in the LDD trace block's `Store :` header line. Makes LDD portable across Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, ChatGPT, and any other host the LLM can introspect.
    2 repo stars
  11. ▌
    Root Cause By Layer · veegee82
    Use when encountering a bug, failing test, or unexpected behavior — especially under time pressure where try/except, retry loops, xfail, type-tolerance shims, "I'll clean up later," or compat-for-both-shapes feel like the fastest path. Forbids symptom patches until structural and conceptual origins are named.
    2 repo stars
  12. ▌
    E2e Driven Iteration · veegee82
    Use at the start of every inner-loop iteration where the goal is to fix a bug / close a failing test / reach a green E2E. Forbids editing code without first running the E2E to capture a fresh loss signal, and forbids declaring "done" without the E2E passing. Makes the cycle "E2E → loss → 5-why-by-layer → fix → E2E" the only admissible rhythm.
    2 repo stars
  13. ▌
    Iterative Refinement · veegee82
    Use when a deliverable (document, diff, design, report, code module) is complete but "good enough, not great" and you want to improve it with a targeted re-iteration instead of starting over. Forbids re-running the task from scratch when refinement is more efficient. Operates on the y-axis (output) not the θ-axis (code or method).
    2 repo stars
  14. ▌
    Dialectical Reasoning · veegee82
    Use when making any non-trivial recommendation, analysis, plan, design decision, code-review note, or architectural trade-off — before presenting to the user or acting. Forces a thesis / antithesis / synthesis pass so first-pass conclusions cannot ship without surviving their strongest counter-case.
    2 repo stars
  15. ▌
    Reproducibility First · veegee82
    Use when you have observed a failing test, a flaky run, a surprising log line, or any single-sample signal you are about to treat as a gradient. Forbids code edits based on one observation unless the log itself is unambiguous signal. Applies before invoking root-cause-by-layer or proposing any fix.
    2 repo stars
  16. ▌
    Loop Driven Engineering · veegee82
    Use at the start of any non-trivial engineering task (feature, bugfix touching more than one file, refactor with observable behavior change, incident response). Orchestrates LDD's four loops — inner (code), refinement (deliverable), outer (method), CoT (reasoning chain, v0.8.0) — with hard iteration budgets, dispatches the specialist skills at the right moments, and forbids declaring "done" without a synced doc-level mental model.
    2 repo stars
  17. ▌
    Docs As Definition Of Done · veegee82
    Use when finishing any code change that modifies behavior, public API, CLI flags, config shape, defaults, error messages, or anything a reader-of-the-docs would model — before committing, pushing, or declaring "done." Forbids deferring doc updates to a follow-up commit, ticket, or "cleanup later."
    2 repo stars