Skill Claude CodeCodex
Find the untested code paths that actually matter, not just the coverage percentage. Use after adding tests.
753
+2 1mo ago A 0 tokens
original MIT
Skill Claude CodeCodex
Capture an architectural decision so the next session (or engineer) knows WHY. Use after any non-obvious technical choice.
753
+2 1mo ago A 27 tokens
original MIT
Skill Claude CodeCodex
Decide whether to add, keep, or remove a dependency. Use before adding any package.
753
+2 1mo ago A 23 tokens
original MIT
Skill Claude CodeCodex
Make frontend output look intentional, not AI-generated. Use for any UI work — components, pages, layouts.
753
+2 1mo ago A 25 tokens
original MIT
eval-harness
29Skill Claude CodeCodex
Build a repeatable eval loop that grades agent output with an LLM judge, so prompt/skill changes get scored against a baseline instead of eyeballed. Reuses loopkit's verifier subagent as the grader — do not build a new one.
753
+2 1mo ago A 54 tokens
original MIT
Skill Claude CodeCodex
Calibrate a reviewer persona with few-shot rubric examples so skepticism stays consistent and doesn't drift lenient over long runs.
753
+2 1mo ago A 28 tokens
original MIT
Skill Claude CodeCodex
Enumerate every end-to-end feature as strict JSON entries with passes:false, editable-passes-only discipline, and priority order. The ledger fresh-context sessions read to know what's done, what's next, and what they're forbidden to touch.
753
+2 1mo ago A 50 tokens
original MIT
flaky-hunter
32Skill Claude CodeCodex
Diagnose and fix tests that pass sometimes and fail other times. Use when CI is red intermittently.
753
+2 1mo ago A 26 tokens
original MIT
Skill Claude CodeCodex
Systematically remove one harness component at a time and measure impact, killing scaffolding that no longer earns its complexity.
753
+2 1mo ago A 28 tokens
original MIT
Skill Claude CodeCodex
Escalate blocked runs to a human via configured channel or fallback to BLOCKED.md and exit the loop. Use when the loop hits an ambiguous spec, a missing credential, a destructive action needing approval, or 3+ consecutive verify failures on the same task.
753
+2 1mo ago A 59 tokens
original MIT
Skill Claude CodeCodex
Author idempotent init.sh under 120s plus sibling test.sh, stop.sh, reset.sh, serve.sh with fixed names the harness relies on.
753
+2 1mo ago A 35 tokens
original MIT
Skill Claude CodeCodex
Validate and constrain untrusted input at the boundary. Use on any handler that accepts external data.
753
+2 1mo ago A 22 tokens
original MIT
Skill Claude CodeCodex
Find and remove unreachable/unused code safely. Use during cleanup or before a refactor.
753
+2 1mo ago A 23 tokens
original MIT
Skill Claude CodeCodex
Design the three states every data UI forgets. Use for any component that fetches or lists data.
753
+2 1mo ago A 27 tokens
original MIT
Skill Claude CodeCodex
Write safe, reversible database migrations for this repo's conventions. Use for any schema change.
753
+2 1mo ago A 22 tokens
original MIT
Skill Claude CodeCodex
Split the Plan/Act/Verify loop across three model tiers — frontier planner, cheap executor, frontier judge — via env vars read by run.sh.
753
+2 1mo ago A 33 tokens
original MIT
owasp-review
41Skill Claude CodeCodex
Security-review a diff against the OWASP Top 10. Use before merging anything that touches auth, input handling, queries, or external calls.
753
+2 1mo ago A 33 tokens
original MIT
Skill Claude CodeCodex
Get a PDF into the model without blowing the context window or losing structure. Native PDF beats OCR-then-text for most cases; extract-then-summarize beats native for very long docs.
753
+2 1mo ago A 43 tokens
original MIT
Skill Claude CodeCodex
Expand a 1-4 sentence product brief into a full spec with a design language, acceptance surface, and an ordered feature list.
753
+2 1mo ago A 31 tokens
original MIT
pr-from-diff
44Skill Claude CodeCodex
Write a PR description a reviewer can approve fast. Use when opening any pull request.
753
+2 1mo ago A 22 tokens
original MIT
Skill Claude CodeCodex
Run the fixed 6-step session-opening sequence — pwd, read progress, git log, count remaining features, init.sh, smoke-test last feature — before touching any new work. The orientation ritual that lets fresh-context sessions reconstruct project state in under a minute.
753
+2 1mo ago A 57 tokens
original MIT
Skill Claude CodeCodex
Cache the parts of the prompt that don't change so a long-running loop stops paying full price on every turn. Use when the system prompt, tool defs, or reference docs are stable across many turns.
753
+2 1mo ago A 44 tokens
original MIT
Skill Claude CodeCodex
Extract the actual cause from a stack trace instead of pattern-matching the error type. Use on any crash or exception.
753
+2 1mo ago A 29 tokens
original MIT
readme-audit
48Skill Claude CodeCodex
Check whether a README actually lets a stranger run the project. Use on any repo's README before publishing.
753
+2 1mo ago A 26 tokens
original MIT