Skill Claude CodeCodex
Curates and condenses codebase context, file contents, and prompts to optimize LLM token usage and response quality.
not rated 25
+1 19d ago A 29 tokens
original MIT
25Stars on the repository
120Mods indexed here, across every type
19d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
Skill Claude CodeCodex
Resolves complex git rebase and merge conflicts with AST-level context, preserving intent across concurrent branches.
not rated 25
+1 19d ago A 26 tokens
original MIT
Skill Claude CodeCodex
Generates technical interview questions plus an evaluation rubric for a given role or skill area. Use when preparing to interview a candidate and need structured, fair questions rather than ad hoc ones.
not rated 25
+1 19d ago A 41 tokens
original MIT
Skill Claude CodeCodex
Turns raw meeting notes or transcripts into structured decisions and action items. Use after a meeting when raw notes/transcript exist and need to become a shareable summary.
not rated 25
+1 19d ago A 38 tokens
original MIT
Skill Claude CodeCodex
Designs monorepo workspaces, dependency graphs, package sharing, and incremental build pipelines with Turborepo or Nx.
not rated 25
+1 19d ago A 34 tokens
original MIT
Skill Claude CodeCodex
Formats structured end-of-shift summaries covering active incidents, degraded services, and pending follow-ups.
not rated 25
+1 19d ago A 27 tokens
original MIT
Skill Claude CodeCodex
Generates a new-engineer onboarding guide from a codebase's actual structure - setup steps, architecture overview, key files, and where to start. Use when a project has no onboarding doc or an outdated one.
not rated 25
+1 19d ago A 48 tokens
original MIT
Skill Claude CodeCodex
Refines vague, unstructured user prompts into clear, constraint-driven prompts with explicit formats and rules.
not rated 25
+1 19d ago A 24 tokens
original MIT
Skill Claude CodeCodex
Structures raw sprint retro notes into themes and concrete actions. Use after a retro when raw sticky-note-style input (what went well/poorly/to try) needs to become a clean summary with follow-through.
not rated 25
+1 19d ago A 47 tokens
original MIT
Skill Claude CodeCodex
Breaks a single ticket or task into concrete, actionable subtasks. Use when one task feels too large or vague to just start on, at the individual-task level - not whole-project planning.
not rated 25
+1 19d ago A 45 tokens
original MIT
Skill Claude CodeCodex
Quantifies technical debt into an actionable, prioritized burndown backlog with clear ROI estimates.
not rated 25
+1 19d ago A 28 tokens
original MIT
Skill Claude CodeCodex
Audits design documents, sprint estimates, and technical debates for cognitive biases like anchoring, sunk cost, and optimistic scoping.
not rated 25
+1 19d ago A 33 tokens
original MIT
Skill Claude CodeCodex
Compares multiple candidate solutions against explicit criteria and trade-offs, and produces a structured recommendation. Use when the user has several real options and needs a defensible pick, not just a pros/cons list.
not rated 25
+1 19d ago A 44 tokens
original MIT
deep-think
62Skill Claude CodeCodex
Breaks a complicated problem into smaller reasoning steps and evaluates multiple possible approaches before recommending one. Use for genuinely hard, multi-faceted problems, not routine tasks.
not rated 25
+1 19d ago A 36 tokens
original MIT
Skill Claude CodeCodex
Deliberately takes the opposing position to a stated idea or decision and builds the strongest possible case against it, to identify weaknesses before commitment. Use when the user wants a genuine counter-argument, not agreement.
not rated 25
+1 19d ago A 48 tokens
original MIT
Skill Claude CodeCodex
Deconstructs problems down to fundamental truths and foundational constraints rather than reasoning by analogy or convention.
not rated 25
+1 19d ago A 26 tokens
original MIT
grill-me
65Skill Claude CodeCodex
Aggressively reviews, questions, and challenges an idea, implementation, architecture, or plan instead of agreeing with it. Use when the user wants their thinking pressure-tested, not validated.
not rated 25
+1 19d ago A 41 tokens
original MIT
Skill Claude CodeCodex
Runs prospective failure simulations by assuming a project or deployment has failed and working backward to identify vulnerabilities.
not rated 25
+1 19d ago A 28 tokens
original MIT
Skill Claude CodeCodex
Converts vague, informal, or incomplete requirements into clear functional and technical requirements, and flags open questions. Use when a request is too ambiguous to implement directly.
not rated 25
+1 19d ago A 36 tokens
original MIT
Skill Claude CodeCodex
Performs 5-Whys and Ishikawa fishbone causal analysis to discover root causes behind systemic bugs, outages, and regressions.
not rated 25
+1 19d ago A 36 tokens
original MIT
Skill Claude CodeCodex
Analyzes downstream cascade effects, systemic feedback loops, and unintended consequences of technical decisions.
not rated 25
+1 19d ago A 23 tokens
original MIT
Skill Claude CodeCodex
Probes ambiguous specifications, hidden assumptions, and underspecified product requests through structured inquiry.
not rated 25
+1 19d ago A 23 tokens
original MIT
Skill Claude CodeCodex
Constructs weighted, multi-attribute decision matrices evaluating technical, architectural, or library choices.
not rated 25
+1 19d ago A 24 tokens
original MIT
Skill Claude CodeCodex
Deep review of authentication, authorization, session, and SSO flows specifically - token lifecycle, session fixation, logout behavior, and OAuth/SSO correctness. Use when reviewing or designing login, session, or SSO code specifically.
not rated 25
+1 19d ago A 51 tokens
original MIT
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: