Skill Claude CodeCodexCursor
Audit UI for WCAG accessibility issues and fixes.
not rated 9 27d ago A 14 tokens
original MIT
9Stars on the repository
87Mods indexed here, across every type
27d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
Skill Claude CodeCodexCursor
Add or improve code documentation for the current change.
not rated 9 27d ago A 13 tokens
original MIT
Skill Claude CodeCodexCursor
Add consistent error handling to the targeted code.
not rated 9 27d ago A 13 tokens
original MIT
Skill Claude CodeCodexCursor
Address review comments on the current GitHub PR.
not rated 9 27d ago A 15 tokens
original MIT
Skill Claude CodeCodexCursor
Produces a one-page agent permission brief (allowed, approval-required, forbidden, limits, logging, rollback, first-week test plan) before granting an AI agent access to a system, tool, or account. Use for agent risk review, permission design, MCP/tool access planning, or "what should the agent be allowed to do?".
not rated 9 27d ago A 70 tokens
original MIT
Skill Claude CodeCodexCursor
Produces a conservative agent work receipt after completed work: finished output, time estimates, review burden, risks, and value judgment. Use when the user invokes /agent-work-receipt, asks for a work receipt, or wants to measure agent productivity honestly after a session.
not rated 9 27d ago A 60 tokens
original MIT
Skill Claude CodeCodexCursor
Act as an AI operations consultant: interview how a business function's workflows actually run, label each step Human-only / AI-assisted / AI-owned, pick the highest-ROI automation tied to money, margin, or output, warn on AI theater and distraction traps, and recommend one narrow one-week test. Use for automation…
not rated 9 27d ago A 85 tokens
original MIT
Skill Claude CodeCodexCursor
Run a pre-build blind spot pass before the agent builds anything. Treat the user's prompt as the map and the real project as the territory: classify gaps across known knowns, known unknowns, unknown knowns, and unknown unknowns (with deps, edge cases, and blast radius under unknown unknowns); ask 5 to 10 high-leverage…
not rated 9 27d ago A 138 tokens
original MIT
code-review
09Skill Claude CodeCodexCursor
Thorough PR code review before approval.
not rated 9 27d ago A 10 tokens
original MIT
Skill Claude CodeCodexCursor
Commit directly on main/master when explicitly allowed.
not rated 9 27d ago A 13 tokens
original MIT
Skill Claude CodeCodexCursor
Commit on the current branch with conventional message.
not rated 9 27d ago A 14 tokens
original MIT
commit
12Skill Claude CodeCodexCursor
Commit on a new branch with conventional message.
not rated 9 27d ago A 10 tokens
original MIT
Skill Claude CodeCodexCursor
Create a pull request targeting main.
not rated 9 27d ago A 10 tokens
original MIT
debug-issue
14Skill Claude CodeCodexCursor
Systematically debug a reported issue.
not rated 9 27d ago A 10 tokens
original MIT
Skill Claude CodeCodexCursor
Post-build decision ledger and pride gate: list meaningful agent choices and assumptions after work has landed, with why, alternatives, and confidence; flag debt and edge cases; do not change code until the user says revise now. Use when the user invokes /decision-audit or asks for a post-execution decision audit or…
not rated 9 27d ago A 71 tokens
original MIT
Skill Claude CodeCodexCursor
Turn a rough task into an agent Goal (outcome, verification with 3 to 5 success criteria, constraints, boundaries, iteration policy, stopping condition, and helper goals when parallel work is implied) so an agent can run with minimal babysitting. Plan-only, no execution in the same turn. Use for Goal, delegate, run…
not rated 9 27d ago A 94 tokens
original MIT
Skill Claude CodeCodexCursor
Design a reusable agent loop as a graph before running it. Take a TASK and COMPLETION CRITERIA, draw the node graph (input, plan, act, verify, retry or escalate, done), specify context, tools, expected output, and evidence per node, label every transition trigger, set max retries, budget ceilings, and human approval…
not rated 9 27d ago A 157 tokens
original MIT
Skill Claude CodeCodexCursor
Fix compilation/type errors with minimal diff.
not rated 9 27d ago A 12 tokens
MIT
Skill Claude CodeCodexCursor
Diagnose and fix git state problems.
not rated 9 27d ago A 13 tokens
MIT
Skill Claude CodeCodexCursor
Beat a real-world quality bar with a Gauntlet Loop: take a GOAL and a REAL-WORLD EQUIVALENT with an inspectable reference pack, decompose into independent parts, assign specialist builders, and gate each part behind a separate fresh-context critic. Pass only if better than the reference; otherwise return the largest…
not rated 9 27d ago A 139 tokens
MIT
Skill Claude CodeCodexCursor
Generate API documentation from code.
not rated 9 27d ago A 10 tokens
MIT
Skill Claude CodeCodexCursor
Generate PR title and description from branch diff.
not rated 9 27d ago A 12 tokens
MIT
Skill Claude CodeCodexCursor
Sync every git repo in a Cursor multi-root workspace to its remote default branch: discover roots, preflight each repo, fetch --all --prune, checkout default, pull --ff-only. Skips dirty or unsafe repos with a clear report. Use for "sync workspace", "update all repos", "back to main", or reset workspace repos to…
not rated 9 27d ago A 85 tokens
MIT
Skill Claude CodeCodexCursor
Rebuild a minimal instruction set from evidence: confirm a bare baseline, run one real task in-session under guardrails only, log struggles, and add an instruction only after the same failure repeats; retest and keep only if verification improves. Use when the user invokes /instruction-ablation or asks to ablate…
not rated 9 27d ago A 78 tokens
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: