edbertchan/catstack

edbertchan/catstack · CLAUDE.md

edbertchan/catstack · corpus/skills/cat-mode/SKILL.md · Edbert's personal working conventions, mined from real session history across his projects. Use when Edbert asks to…

edbertchan/catstack · corpus/skills/principle-assert-invariants-not-last-bug/SKILL.md · Apply after a bug ships past review or a passing grade/check: assert the general class of failure instead of patching…

edbertchan/catstack · corpus/skills/principle-bind-to-named-inventory/SKILL.md · Apply after an audit, scoring review, or a request for a "real classifier" / "less arbitrary weights" when existing…

edbertchan/catstack · corpus/skills/principle-build-the-lever/SKILL.md · Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks. Build the tool that does it or…

edbertchan/catstack · corpus/skills/principle-encode-lessons-in-structure/SKILL.md · Apply when you catch yourself writing the same instruction a second time, or notice a recurring correction. Encode the…

edbertchan/catstack · corpus/skills/principle-experience-first/SKILL.md · Apply when product, UX, or feature-scope tradeoffs come up. Choose user delight over implementation convenience; ship…

edbertchan/catstack · corpus/skills/principle-explicit-errors/SKILL.md · Apply whenever code handles an exception (catch, suppress, translate, retry), decides to skip, drop, truncate, or stop…

edbertchan/catstack · corpus/skills/principle-fix-root-causes/SKILL.md · Apply when debugging. Trace each symptom to its root cause and fix it there; reproduce first, ask why until you reach…

edbertchan/catstack · corpus/skills/principle-flag-your-own-corrections/SKILL.md · Apply whenever you are about to admit fault in any wording — a fact, number, claim, or check you already stated turns…

edbertchan/catstack · corpus/skills/principle-foundational-thinking/SKILL.md · Apply before writing logic: choosing core types and data structures, sequencing scaffold-vs-feature work, asking what…

edbertchan/catstack · corpus/skills/principle-generalize-from-rejection/SKILL.md · Apply when a mechanical gate — a lint, validator, blocked-command guard, or CI check — rejects your output for the same…

edbertchan/catstack · corpus/skills/principle-guard-the-context-window/SKILL.md · Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents…

edbertchan/catstack · corpus/skills/principle-laziness-protocol/SKILL.md · Apply when refactoring, evaluating diff size, or tempted to add abstractions, layers, or signal threading. Bias toward…

edbertchan/catstack · corpus/skills/principle-manage-idle-resumption/SKILL.md · Apply when a session may idle for a multi-hour or multi-day gap: polling loops, human-in-the-loop waits, overnight…

edbertchan/catstack · corpus/skills/principle-minimize-reader-load/SKILL.md · Apply when reviewing or shaping code that's hard to trace. Count layers between question and answer, and hidden state…

edbertchan/catstack · corpus/skills/principle-name-the-scorer/SKILL.md · Apply when a product has two (or more) scorers that both emit weights, priorities, or rankings — especially…

edbertchan/catstack · corpus/skills/principle-never-block-on-the-human/SKILL.md · Apply when tempted to ask 'should I do X?' on reversible work. Proceed, present the result, let the human…

edbertchan/catstack · corpus/skills/principle-no-lookahead/SKILL.md · Apply to any evaluation, backtest, benchmark, grader, or training run over data with a time axis or an ordered decision…

edbertchan/catstack · corpus/skills/principle-outcome-oriented-execution/SKILL.md · Apply whenever a change threads a new required value through existing callers, not just named rewrites/migrations — a…

edbertchan/catstack · corpus/skills/principle-prove-it/SKILL.md · Apply before any claim about code, systems, or history. No claim without same-turn evidence; a hedge is a trigger to…

edbertchan/catstack · corpus/skills/principle-push-not-poll/SKILL.md · Apply when designing, reviewing, or authoring any mechanism that waits on a long-running background action: a CI/build…

edbertchan/catstack · corpus/skills/principle-read-state-artifacts/SKILL.md · Apply when designing, reviewing, or authoring any mechanism that checks on work a background process already tracks: a…

edbertchan/catstack · corpus/skills/principle-report-the-disqualifier/SKILL.md · Apply when writing or gating any report that makes a causal claim or summarises a cumulative outcome — a backtest, an…

edbertchan/catstack · corpus/skills/principle-scope-the-session/SKILL.md · Apply when a session's actual work drifts away from what it was opened to do — a side-investigation becomes the main…

edbertchan/catstack · corpus/skills/principle-separate-before-serializing-shared-state/SKILL.md · Apply when concurrent actors might write to the same file, branch, key, or state object. Eliminate the sharing first…

edbertchan/catstack · corpus/skills/principle-sequence-verifiable-units/SKILL.md · Apply to multi-step work (sweeps, migrations, runs of similar edits) and to how you stack commits and PRs. Break work…

edbertchan/catstack · corpus/skills/principle-subagent-inherits-scope/SKILL.md · Apply when spawning or prompting a subagent, fork, explorer, investigator, judge, or worker. A subagent may not act…

edbertchan/catstack · corpus/skills/principle-subtract-before-you-add/SKILL.md · Apply when sequencing an addition, refactor, or rewrite. Remove dead weight, redundant validators, and stub references…

edbertchan/catstack · corpus/skills/principle-trace-token-burn-loop/SKILL.md · Apply when analyzing token burn or agent session spend. Prevents mistaking the top task_type or prompt_type for the…

edbertchan/catstack · corpus/skills/principle-type-system-discipline/SKILL.md · Apply when designing types, reviewing a function signature, or writing code in any statically-typed language. Make…

edbertchan/catstack · corpus/skills/prove-it-ship-gate/SKILL.md · Auto-trigger when claiming a feature, worker, or integration is done, shipped, or working and the Goal includes live…

edbertchan/catstack · corpus/skills/report-rendering/SKILL.md · Apply when a report, analysis, or write-up is finished and someone other than the author will read it. Ship it as a…

edbertchan/catstack · engine/skills/automate-me/SKILL.md · Mine session history for durable working-style preferences and turn them into one personal "<handle>-mode" skill agents…

edbertchan/catstack · engine/skills/create-skill/SKILL.md · Create or install an agent skill for Claude, Cursor, Codex, and Muse together. Use when authoring a new skill, adding…

edbertchan/catstack · engine/skills/draft-pr/SKILL.md · Draft or update a pull request using a disciplined PR schema (Summary, Review Claim, Review Lane, Review Unit, Safety…

edbertchan/catstack · engine/skills/make-pr/SKILL.md · catstack-local overlay for the draft-pr skill: adds extra gates before publishing a PR that touches engine/hooks…

edbertchan/catstack · engine/skills/phrase-judge/SKILL.md · Use when writing, fixing, or working around any checker, gate, or lint, in any repo, that decides based on what a text…

edbertchan/catstack · engine/skills/reflect/SKILL.md · Mine a conversation transcript — and the commit history of the files it touched — for durable learnings, then route…

edbertchan/catstack · engine/skills/thrash-reflect-automate/SKILL.md · On a grading/validation board FAIL or NEEDS_WORK, or the user saying "/thrash": auto-run a short reflect, fix the class…

edbertchan/catstack · product/skills/admin-bypass-sweep/SKILL.md · MANUAL, HUMAN-ONLY skill. Force-merges every open PR labeled admin-bypass directly to the trunk branch, bypassing the…

edbertchan/catstack · product/skills/alternatives-considered/SKILL.md · Produce the real option set for a decision before committing to the first shape that came to mind. Use before a design…

edbertchan/catstack · product/skills/ci-job-timing/SKILL.md · Repeatable per-step timing report for any GitLab CI job, from Datadog. Use when asked how long a CI job's steps take…

edbertchan/catstack · product/skills/diu/SKILL.md · Default communication rule, two parts. (1) Brevity: before finishing any response, check whether it would run over…

edbertchan/catstack · product/skills/event-wait/SKILL.md · Wait for a background job, workflow, build, or continuous-integration run to finish by subscribing to the events it…

edbertchan/catstack · product/skills/how/SKILL.md · Trace how a subsystem actually works before changing it. Use for "how does X work", a walkthrough before an edit, or…

edbertchan/catstack · product/skills/i-have-adhd/SKILL.md · Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns…

edbertchan/catstack · product/skills/independent-judge-swarm/SKILL.md · Grade an artifact with a mechanical precheck plus two independent judges (Fable + Codex). Building agent must not…

edbertchan/catstack · product/skills/land-stack/SKILL.md · Land (queue/merge) a stacked pull request safely, on any repo using a PR-stacking workflow (Mergify, Graphite, or…

edbertchan/catstack · product/skills/loop-generator/SKILL.md · Generate a reusable loop instruction doc and driver script for a recurring babysit/watch/retry task (e.g. "keep this PR…

edbertchan/catstack · product/skills/narrow-the-scope/SKILL.md · Notice live, mid-session, when repeated attempts at one problem aren't converging — the same error recurring, several…

edbertchan/catstack · product/skills/plan-first/SKILL.md · Front door for work that will span more than one file, review unit, or commit. Produces the plan before the first edit…

edbertchan/catstack · product/skills/review-stack/SKILL.md · Build a layered code review page for a branch as a published artifact, one review claim per slice in dependency order…

edbertchan/catstack · product/skills/ship-a-detector/SKILL.md · Author a hook or gate detector end to end: the seven defect kinds this repo keeps re-shipping, then the install, test…

edbertchan/catstack · product/skills/show-me-your-work/SKILL.md · Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why…

edbertchan/catstack · product/skills/skill-ab-token-gate/SKILL.md · After changing a skill or hook meant to cut context/token cost, run a paired A/B workload N times (default 5)…

edbertchan/catstack · product/skills/spike-and-validate/SKILL.md · Turn an untested assumption into real output by building the smallest throwaway that would kill it, running it, then…

edbertchan/catstack · product/skills/split-scope/SKILL.md · Shape code changes and PR stacks so each diff is easy to review: one local claim, one safety invariant, clear…

edbertchan/catstack · product/skills/spreadsheet-authoring/SKILL.md · Design scalable spreadsheet models with category-level raw data, formula- driven aggregation tables, provenance, and…

edbertchan/catstack · product/skills/technical-writing/SKILL.md · Write a document a tired engineer understands on the first read. Use for /technical-writing, or when writing or…

edbertchan/catstack · product/skills/visual-proof/SKILL.md · Capture and present trustworthy before/after visual evidence (screenshots, video) for a UI-affecting change. Use when a…

edbertchan/catstack · product/skills/why/SKILL.md · Recover why code is shaped the way it is before changing it. Use for "why does X work this way", "why was this…