Skill Claude CodeCodex
Concise neutral options with explicit applicability, safety redirects, agency-preserving wording, evidence/uncertainty handling, full-language localization, exact preservation, validation checklist, audit footer, and regression harness.
Skill Claude CodeCodex
Use only for concise, neutral, non-directive suggestions about a user-specified topic. Output practical options with risks/trade-offs, without guarantees, pressure, commands, or professional conclusions.
Skill Claude CodeCodex
Use only when the user asks for suggestions, options, considerations, alternatives, trade-offs, or a neutral recommendation about a specified topic.
Skill Claude CodeCodex
Use only when the user asks for suggestions, options, considerations, alternatives, trade-offs, or a neutral recommendation about a specified topic.
Skill Claude CodeCodex
Use only for suggestions/options/alternatives/trade-offs for specified topic.
Skill Claude CodeCodex
Neutral options with safety boundaries, agency-preserving language, source/uncertainty handling, localization, validation, and audit hooks.
Skill Claude CodeCodex
Concise neutral options with explicit applicability, safety redirects, agency-preserving wording, evidence/uncertainty handling, full-language localization, exact preservation, validation checklist, audit footer, and regression harness.
Skill Claude CodeCodex
Revises operational text for agent execution with minimal wording while preserving intent, safeguards, protected tokens, validation evidence, handoff state, scripts, and localization.
Skill Claude CodeCodex
Improves operational text so AI agents can parse intent, act reliably, and validate completion with the fewest words needed for correct execution.
Skill Claude CodeCodex
Improves operational text so AI agents can parse intent, act reliably, preserve safeguards, and validate completion with the fewest words needed for correct execution.
Skill Claude CodeCodex
Improves operational text so AI agents can act reliably while preserving intent, safeguards, human maintainability, and minimum sufficient wording.
Skill Claude CodeCodex
Improves operational text so AI agents can act reliably while preserving intent, safeguards, human maintainability, and minimum sufficient wording.
Skill Claude CodeCodex
Improves operational text so AI agents can act reliably while preserving intent, safeguards, human maintainability, and minimum sufficient wording.
Skill Claude CodeCodex
Revises operational text for agent execution with minimal wording while preserving intent, safeguards, protected tokens, validation evidence, handoff state, scripts, and localization.
Skill Codex
Sanitize unpushed local git commits from ai-dev-loop R/K loops. Use when a branch has local R: or K: commits and an agent needs to remove .ai-dev-loop/ artifacts, rewrite human-readable commit messages, preserve authors/dates, and prepare history before push or review.
Skill Codex
Sanitize unpushed local git commits from ai-dev-loop R/K loops. Use when a branch has local R: or K: commits and an agent needs to remove .ai-dev-loop/ artifacts, rewrite human-readable commit messages, preserve authors/dates, and prepare history before push or review.
Skill Claude CodeCodex
Run an auditable R/K loop. R reviews requirements, plans, diffs, tests, documentation, risks, and evidence. K responds to every required finding, scans whole-change impact, updates all directly affected files, validates, and records evidence.
Skill Claude CodeCodex
Token-efficient auditable R/K repository loop.
Skill Claude CodeCodex
Token-efficient auditable R/K repository loop with module-on-demand runtime details.
Skill Claude CodeCodex
Token-efficient auditable R/K repository loop with module-on-demand runtime details.
Skill Claude CodeCodex
Build large, diverse, auditable benchmark datasets and measurement harnesses for evaluating prompts, skills, specs, agents, or candidate versions across scenarios, languages, contexts, and risk levels.
Skill Claude CodeCodex
Compare, score, improve, retest, and stop candidate-version work with source-grounded identity, target maps, calibrated objectives, broad category buckets with explicit coverage lenses, validation-tier claim caps, evidence ledgers, recomputable score packets, observability markers, artifact checksums, correction…
Skill Claude CodeCodex
Unpack and compare candidate versions, independently score each one, then build a stronger best-version successor using evidence-backed best practices.
Skill Claude CodeCodex
Compare candidate versions, synthesize an evidence-backed successor, then measure it against the candidates to validate the best measured version before making a recommendation.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: