← all publishers

rdleclerc

@rdleclerc source repo

Report this profile Claim this profile

• 12 skills
• 0 followers
• 23 hours ago last updated

1. ▌
   Uberrca · rdleclerc bundle

   Force deep, class-level root cause analysis before patches. Use when asked why/how an incident happened, to do RCA/postmortem/debugging, to investigate stuck loops, production/workflow/agentic-system failures, repeated bugs, suspicious edge cases, or when the user challenges whether a patch addresses the underlying issue rather than a proximate cause.
   0 installs
2. ▌
   Ubergoal · rdleclerc bundle

   Use when material coding or agentic-system work runs as a goal/objective; needs a substantial plan, ledger, multi-agent orchestration, confidence gate, or completion orchestration; or asks which Uber subskill to use. Binds plan authority and routes proof to UberAccept.
   0 installs
3. ▌
   Uberplan · rdleclerc bundle

   Do not auto-trigger from task similarity. Use only when explicitly named by the user or routed by ubergoal. Produces the smallest source-grounded implementation plan that completely addresses the evidenced problem, with proportional proof and evidence-gated escalation.
   0 installs
4. ▌
   Ubershow · rdleclerc bundle

   Use when the user needs high-bandwidth visual communication rather than a text wall: browser-first HTML decision boards, implementation plans, questionnaires, architecture/source/code-review maps, status or incident reports, visual briefs, or interactive decision receipts for Codex/Claude coding workflows. Produces local self-contained HTML artifacts as generated views while preserving Markdown/source/ledger authority.
   0 installs
5. ▌
   Uberaccept · rdleclerc bundle

   Do not auto-trigger from task similarity. Use only when explicitly named by the user or routed by ubergoal. Performs proportional adversarial acceptance against the exact approved scope, candidate diff, and risk-mapped proof before completion or ship claims.
   0 installs
6. ▌
   Uberassess · rdleclerc bundle

   Do not auto-trigger from task similarity. Use only when explicitly asked to assess or deeply research a source, plan artifact, idea seed, open research question, or implementation question for possible adoption, or routed by ubergoal: X/Twitter posts, bookmarked links, articles, GitHub repos, arXiv/papers, videos, Hermes/bookmark signals, internal artifacts, draft plans, planning packets, scraps of ideas, alternatives research, and codebase/docs/forum/GitHub reconnaissance. Produces a source-grounded recommendation packet, not implementation.
   0 installs
7. ▌
   Ubersimplify · rdleclerc bundle

   Do not auto-trigger from task similarity. Use only when explicitly named by the user or routed by ubergoal. Audits or carefully patches codebase complexity, dead code, duplicated policy, poor modularity, silent fallbacks, brittle hidden behavior, or agentic-system bloat with proof gates.
   0 installs
8. ▌
   Uberarchitect · rdleclerc bundle

   Do not auto-trigger from task similarity. Use only when explicitly named by the user or routed by ubergoal, uberassess, uberplan, or uberaccept for system-scale architecture questions: concurrency, scaling, queues, workers, long-running jobs, gateways, orchestration, workflow durability, backpressure, repeated timeouts, or agents stuck in micro-patches. Forces a senior-architect stepback before local code fixes.
   0 installs
9. ▌
   Testing Strategy · rdleclerc bundle

   Use when an agent writes, removes, refactors, reviews, selects, or debugs tests, or decides which tests or product validation to run or whether they are needed. Do not use for command-only execution of an already specified test when no testing decision remains. Choose the smallest contract-preserving proof: one owner per contract, table-driven variants, current-checkout or installed-artifact evidence, and a named reason before escalating to broader suites.
   0 installs
10. ▌
    Uberskillevolver · rdleclerc bundle

    Do not auto-trigger from task similarity. Use only when explicitly named by the user or routed by ubergoal. Captures a lightweight, human-reviewed learning loop for skills, prompts, workflows, multi-agent coding protocols, or agentic-system playbooks after substantial or surprising runs.
    0 installs
11. ▌
    Uber Skill Creator · rdleclerc bundle

    Portable guide for creating, updating, migrating, deprecating, and evaluating Uber-style SKILL.md skills for Codex, Claude, and compatible coding agents. Use when users want to create a new general skill, update an existing skill, audit an existing skill or skill pack with read-only shape lint plus behavioral evals, migrate or purge legacy local skill-creator or skill-creator-pro aliases, add scripts/references/assets, run eval-driven skill iteration, compare with-skill vs without-skill behavior, generate an HTML review report, or tune a skill description for better triggering. For OpenClaw/Gaia/Type0/Soho-specific skills, prefer openclaw-agentic-skill-creator.
    0 installs
12. ▌
    Bad Mini Skill · rdleclerc

    Helpful skill for broad situations. Helpful skill for broad situations. Helpful skill for broad situations. Helpful skill for broad situations. Helpful skill for broad situations. Helpful skill for broad situations. Helpful skill for broad situations. Helpful skill for broad situations. Helpful skill for broad situations. Helpful skill for broad situations. Helpful skill for broad situations. Helpful skill for broad situations. Helpful skill for broad situations. Helpful skill for broad situations. Helpful skill for broad situations. Helpful skill for broad situations. Helpful skill for broad situations. Helpful skill for broad situations. Helpful skill for broad situations. Helpful skill for broad situations. Helpful skill for broad situations. Helpful skill for broad situations. Helpful skill for broad situations. Helpful skill for broad situations. Helpful skill for broad situations. Helpful skill for broad situations. Helpful skill for broad situations. Helpful skill for broad situations. Helpful skill fo
    0 installs