Fergius-Engineering
OrganizationWorking-instinct skills for Claude Code: verify claims against the source, log for the bug you can't reproduce, write like a human, test so the test bites. A reflex layer on top of superpowers.
Categories
Indexed Skills (20)
de-ai-prose
Use when about to show any prose a human will read - docs, README, commit bodies, UI copy, store text.
fix-in-the-shared-layer
Use when a bug surfaces while building on one's own shared code - a library, base class, SDK, or component.
logging-for-remote-diagnosis
Use when building any mechanic that could fail on a machine out of reach - a shipped product, a CLI a user runs, a server.
opportunistic-fixes
Use when noticing an incidental correctness problem - a stale comment, a wrong doc line, a drifted reference - in the area already being edited.
plan-with-teeth
Use when about to write an implementation plan, scope a multi-step change, or enter plan mode - before any plan text exists. Also fires when reviewing a plan that states what code does without evidence behind it.
tests-with-teeth
Use when writing or reviewing any test, or when about to accept "tests pass" as evidence.
using-instincts
Use when doing any work in a project that has the instincts plugin installed
build-release-mindset
Use when touching build scripts, release or packaging steps, publish flows, or CI config.
critical-thinking
Use when about to build something someone proposed, especially when the proposer sounds confident and the idea sounds obviously fine.
entry-point-audit
Use when adding any cross-cutting change - a new gate, limit, permission check, or rule that must apply everywhere.
feasibility-guard
Use when about to build or agree to build a feature, test, or check, especially when the request sounds big or clever.
fix-the-root-cause
Use when fixing any bug, especially one that surfaces far from where the bad state was created.
independent-review-gate
Use when about to call complex or shippable work done, or before merging.
no-duplicate-logic
Use when adding a case, check, or branch to a function that already exists, especially after jumping straight to the insertion point.
performance-at-scale
Use when writing code that runs per item, per frame, or per event, or building a cache or lookup over a collection that can grow large.
project-onto-all-systems
Use when adding or changing a feature, a data model, or any action that creates, edits, or removes state.
question-the-premise
Use when several well-reasoned fixes on the same hypothesis have all failed, or when a symptom looks impossible.
user-action-edge-cases
Use when finishing anything that depends on external state a person controls - a file, a record, a folder.
ux-designer-mindset
Use when building or changing anything a user interacts with - a control, a screen, a flow.
verify-against-code
Use when about to assert any factual claim about what code or a product does - in an answer, a doc, a commit message, or anything a user will see.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.