All authors
Claude Skills by EdbertChan
github.com/EdbertChan60 skills0 installs53 views
- Always OnWhen asked to create, add, install, or author a skill, or when about to write a new `SKILL.md` / home-link a skill directory, read the `create-skill` skill first (`engine/skills/create-skill/SKILL.md` or the installed `create-skill` skill). A skill MUST be available to Claude, Cursor, Codex, and Muse unless it is listed in `CLAUDE_ONLY_SKILLS` or `MUSE_ONLY_SKILLS` in catstack `install.sh`. Prefer catstack `product/skills/<name>/` (or corpus) + `./install.sh`. Project-skill home links MUST hi...Votes: 0GitHub stars: 4
- CommandsCreate or update a pull request using draft-pr (or the repo make-pr overlay)Votes: 0GitHub stars: 4
- Cat ModeEdbert's personal working conventions, mined from real session history across his projects. Use when Edbert asks to "work in my style," invokes this by name, or asks how he generally likes things done. Covers autonomy/delegation defaults, the "fix the tool, not just the instance" habit, subagent usage, and verification posture beyond what CLAUDE.md's evidence rules already cover.Votes: 0GitHub stars: 4
- Principle Assert Invariants Not Last BugApply after a bug ships past review or a passing grade/check: assert the general class of failure instead of patching only the specific instance that was caught. Use on /reflect, whenever a fix's own commit message reads like 'fix X for ticker/case Y', or whenever a fix makes a row disappear instead of shipping it with a status.Votes: 0GitHub stars: 4
- Principle Bind To Named InventoryApply after an audit, scoring review, or a request for a "real classifier" / "less arbitrary weights" when existing scorers, rankers, or weight formulas were already named. Pick among those named gaps before proposing a new model or library.Votes: 0GitHub stars: 4
- Principle Build The LeverApply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks. Build the tool that does it or proves it (codemod, script, generator, or a skill your subagents follow) instead of working by hand. The tool is the artifact a reviewer can rerun.Votes: 0GitHub stars: 4
- Principle Encode Lessons In StructureApply when you catch yourself writing the same instruction a second time, or notice a recurring correction. Encode the rule as a lint, metadata flag, runtime check, or script instead of more text.Votes: 0GitHub stars: 4
- Principle Experience FirstApply when product, UX, or feature-scope tradeoffs come up. Choose user delight over implementation convenience; ship fewer polished features over more rough ones.Votes: 0GitHub stars: 4
- Principle Explicit ErrorsApply whenever code handles an exception (catch, suppress, translate, retry), decides to skip, drop, truncate, or stop early on data (an empty parse, a missing lookup, an unpriced row, a lookback or coverage cap, a loop that reads only the first source), or writes the text of an error, failure, or rejection message that a person or agent will read to fix the problem.Votes: 0GitHub stars: 4
- Principle Fix Root CausesApply when debugging. Trace each symptom to its root cause and fix it there; reproduce first, ask why until you reach it, resist nil-check guards that silence crashes.Votes: 0GitHub stars: 4
- Principle Flag Your Own CorrectionsApply whenever you are about to admit fault in any wording — a fact, number, claim, or check you already stated turns out to be wrong, vacuous, premature, or unverified. Say so explicitly rather than quietly citing the corrected value, and treat the admission itself as a reflect trigger. Auto-fires because no regex can enumerate the ways a model admits error.Votes: 0GitHub stars: 4
- Principle Foundational ThinkingApply before writing logic: choosing core types and data structures, sequencing scaffold-vs-feature work, asking what concurrent actors share. Get the data structures right so downstream code becomes obvious.Votes: 0GitHub stars: 4
- Principle Generalize From RejectionApply when a mechanical gate — a lint, validator, blocked-command guard, or CI check — rejects your output for the same reason twice in one session. Fix the generation pattern producing the violation, not just the specific instance.Votes: 0GitHub stars: 4
- Principle Guard The Context WindowApply when context is filling up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents; keep summaries in the main thread, not raw payloads.Votes: 0GitHub stars: 4
- Principle Laziness ProtocolApply when refactoring, evaluating diff size, or tempted to add abstractions, layers, or signal threading. Bias toward deletion and the smallest change that solves the problem.Votes: 0GitHub stars: 4
- Principle Manage Idle ResumptionApply when a session may idle for a multi-hour or multi-day gap: polling loops, human-in-the-loop waits, overnight runs, babysit/watch/retry work. Compact or restart deliberately before resuming instead of letting the prompt cache lapse.Votes: 0GitHub stars: 4
- Principle Minimize Reader LoadApply when reviewing or shaping code that's hard to trace. Count layers between question and answer, and hidden state in the reader's head; collapse one-caller wrappers and shrink mutable scope.Votes: 0GitHub stars: 4
- Principle Name The ScorerApply when a product has two (or more) scorers that both emit weights, priorities, or rankings — especially hand-authored theme/report priorities beside learned historical-case tag weights. Name which scorer produced which number; never imply one sets the other unless wiring is explicit.Votes: 0GitHub stars: 4
- Principle Never Block On The HumanApply when tempted to ask 'should I do X?' on reversible work. Proceed, present the result, let the human course-correct after the fact; reserve confirmation for irreversible actions.Votes: 0GitHub stars: 4
- Principle No LookaheadApply to any evaluation, backtest, benchmark, grader, or training run over data with a time axis or an ordered decision sequence. Score a decision only against inputs that existed before that decision was made. Covers what the field calls look-ahead bias, target leakage, point-in-time correctness, and repainting. Reach for it on: a backtest or walk-forward run, a feature computed over a full history, a retrieval or agent eval, a label assigned after the outcome was known, or any result that l...Votes: 0GitHub stars: 4
- Principle Outcome Oriented ExecutionApply whenever a change threads a new required value through existing callers, not just named rewrites/migrations — a new required field, a new parameter, a new required IPC/API argument. Converge on the target shape in one slice; don't preserve smooth intermediate states with throwaway compatibility code.Votes: 0GitHub stars: 4
- Principle Prove ItApply before any claim about code, systems, or history. No claim without same-turn evidence; a hedge is a trigger to verify, never a place to stop. Routes the four investigation products that build the evidence. Unlike the other principles this one auto-fires: it must intercept a claim as it forms, not be named after the fact.Votes: 0GitHub stars: 4
- Principle Push Not PollApply when designing, reviewing, or authoring any mechanism that waits on a long-running background action: a CI/build watcher, a deploy or merge poller, a status-check loop, an agent babysitting a backgrounded command. Prefer a push/wakeup signal over a tight poll loop.Votes: 0GitHub stars: 4
- Principle Report The DisqualifierApply when writing or gating any report that makes a causal claim or summarises a cumulative outcome — a backtest, an experiment write-up, a capacity or cost model, a postmortem, an eval summary, a benchmark table. The report must carry what would change the reader's decision: what observation would refute the claim, whether the path crossed a state it could not return from, what the headline was before and after the fix, and which unvaried assumption flips the sign.Votes: 0GitHub stars: 4
- Principle Scope The SessionApply when a session's actual work drifts away from what it was opened to do — a side-investigation becomes the main thread, or an unrelated request gets absorbed into an existing session. Start a fresh session instead of letting scope creep silently expand the one you're in.Votes: 0GitHub stars: 4
- Principle Separate Before Serializing Shared StateApply when concurrent actors might write to the same file, branch, key, or state object. Eliminate the sharing first; serialize structurally only when one shared writer is a real invariant.Votes: 0GitHub stars: 4
- Principle Sequence Verifiable UnitsApply to multi-step work (sweeps, migrations, runs of similar edits) and to how you stack commits and PRs. Break work into small units that each end in a verifiable state, check each before the next, and order delivery so the sequence proves itself to a reviewer.Votes: 0GitHub stars: 4
- Principle Subagent Inherits ScopeApply when spawning or prompting a subagent, fork, explorer, investigator, judge, or worker. A subagent may not act outside the scope its parent gave it, and may not widen that scope on its own. A subagent that finds the parent's premise wrong surfaces the contradiction with evidence instead of acting on it or quietly conforming to it.Votes: 0GitHub stars: 4
- Principle Subtract Before You AddApply when sequencing an addition, refactor, or rewrite. Remove dead weight, redundant validators, and stub references first, then build on the simpler base.Votes: 0GitHub stars: 4
- Principle Trace Token Burn LoopApply when analyzing token burn or agent session spend. Prevents mistaking the top task_type or prompt_type for the root cause. Forces a trace from the session back to the loop script or plan entry point before prescribing a fix.Votes: 0GitHub stars: 4
- Principle Type System DisciplineApply when designing types, reviewing a function signature, or writing code in any statically-typed language. Make illegal states unrepresentable, brand semantic primitives, parse external data at boundaries, refuse to lie to the compiler, exhaust variants, derive from authoritative schemas.Votes: 0GitHub stars: 4
- Prove It Ship GateAuto-trigger when claiming a feature, worker, or integration is done, shipped, or working and the Goal includes live side effects — an external service (Linear tickets, deploy, live mine, external APIs) or the user's own machine, session, or screen (an e2e or Playwright run, an Electron window, a popup on their desktop). Unit/fixture tests and UI registration alone are not enough — route to prove-it for live evidence before treating the claim as settled.Votes: 0GitHub stars: 4
- Report RenderingApply when a report, analysis, or write-up is finished and someone other than the author will read it. Ship it as a single self-contained HTML file, and a PDF where a fixed page is wanted. Markdown split across several files in a repo is a working artifact, not a delivered report. Reach for it on: a multi-section analysis, a report with figures, anything to be handed to someone without a checkout, or any request to 'show me the report'.Votes: 0GitHub stars: 4
- Automate MeMine session history for durable working-style preferences and turn them into one personal "<handle>-mode" skill agents will follow. Use when the user says "automate me," asks to capture how they work into a skill, wants an existing mode skill updated or refreshed, or when reflect surfaces a recurring personal-preference pattern (not a code lesson) across sessions. Must invoke — do not wait — when the user had to restate a named constraint, keep iterating, or change product direction because ...Votes: 0GitHub stars: 4
- Create SkillCreate or install an agent skill for Claude, Cursor, Codex, and Muse together. Use when authoring a new skill, adding SKILL.md, home-linking a project skill, or when the user says create-skill / install a skill. Overrides single-harness Cursor-only install advice.Votes: 0GitHub stars: 4
- Draft PrDraft or update a pull request using a disciplined PR schema (Summary, Review Claim, Review Lane, Review Unit, Safety Invariant, Slice Rationale, Non-goals, Measured, Test Plan, Revert Plan), a diff-atomicity gate, and visual-proof rules for UI-impacting changes. Always on after catstack install.sh via Cursor ~/.cursor/rules/draft-pr-precedence.mdc, Claude CLAUDE.md, Codex AGENTS.md, and slash commands /pr-skill, /draft-pr, /make-pr. Trigger when asked to make a PR, draft or update a PR body,...Votes: 0GitHub stars: 4
- Make Prcatstack-local overlay for the draft-pr skill: adds extra gates before publishing a PR that touches engine/hooks, engine|corpus|product skills -- hook e2e coverage, three-harness install, and ecosystem boundaries. Loaded automatically instead of draft-pr for PRs in this repo.Votes: 0GitHub stars: 4
- Phrase JudgeUse when writing, fixing, or working around any checker, gate, or lint, in any repo, that decides based on what a text means.Votes: 0GitHub stars: 4
- ReflectMine a conversation transcript — and the commit history of the files it touched — for durable learnings, then route Accepted items into concrete skill/code edits via an auto-spawned worktree in the repo that owns the named skill + PR (never merge). Working-style preferences route to the sibling skill automate-me, not a task skill edit. User involvement, forced restatement, "you fucked up/messed up", or the same type of complaint twice is a FAILURE and must route to automate-me. Use when the u...Votes: 0GitHub stars: 4
- Thrash Reflect AutomateOn a grading/validation board FAIL or NEEDS_WORK, or the user saying "/thrash": auto-run a short reflect, fix the class of bug (not just the named instance), codify the invariant in the relevant skill/rule, then automate a catch and re-validate. Collapse phrase for "reflect and automate after every failure" — do not wait for the user to re-prompt.Votes: 0GitHub stars: 4
- Admin Bypass SweepMANUAL, HUMAN-ONLY skill. Force-merges every open PR labeled admin-bypass directly to the trunk branch, bypassing the merge queue and required checks via GitHub admin override (`gh pr merge --admin`). Do not auto-invoke this skill from a natural-language request, a description match, or another agent's delegation. Only run this skill when a human has typed its literal slash command themselves in the current turn (the exact form depends on how it was installed — see the "STOP" section). See th...Votes: 0GitHub stars: 4
- Alternatives ConsideredProduce the real option set for a decision before committing to the first shape that came to mind. Use before a design, a schema, a naming or format choice, or any change expensive to reverse. Every option is labeled considered (cited) or invented (untested); invented options route to `spike-and-validate` before they can decide anything.Votes: 0GitHub stars: 4
- DiuDefault communication rule, two parts. (1) Brevity: before finishing any response, check whether it would run over roughly 150 words or lean on unexplained jargon. If so, and the user has not explicitly asked for full technical detail in the same turn, replace it with an ELI5 answer under 40 words instead. Also triggers immediately on a literal ELI5 request in the user's message (eli5, ELI5, Eli5, "ELI 5" with a space, or an explicit word cap like "< 40 words"), even with no other context. Fi...Votes: 0GitHub stars: 4
- HowTrace how a subsystem actually works before changing it. Use for "how does X work", a walkthrough before an edit, or placement questions ("where should this live", "which package owns this"). Fans out read-only explorers for a subsystem, one explainer for a narrow question. Use `why` for motivation, `alternatives-considered` for options.Votes: 0GitHub stars: 4
- I Have AdhdShape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific time estimates, make wins visible. Invoke with /i-have-adhd; stays on until "stop adhd mode".Votes: 0GitHub stars: 4
- Independent Judge SwarmGrade an artifact with a mechanical precheck plus two independent judges (Fable + Codex). Building agent must not self-grade. Use for /grade, /holdings-sheet-swarm-grade, sheet/report second opinions, or when a PASS from the author alone is not enough. Domain files under domains/ bind coding vs equities triggers and cwd scripts.Votes: 0GitHub stars: 4
- Land StackLand (queue/merge) a stacked pull request safely, on any repo using a PR-stacking workflow (Mergify, Graphite, or similar). Trigger when asked to land, merge, ship, or queue a PR or PR stack. Enforces that you act only on SHA-verified PR numbers — never a PR found by branch name.Votes: 0GitHub stars: 4
- Loop GeneratorGenerate a reusable loop instruction doc and driver script for a recurring babysit/watch/retry task (e.g. "keep this PR merge-ready," "retry failed jobs until they pass," "watch this queue and fix what breaks"). Trigger: "loop generator", "generate a loop", or requests to build a reusable watch/retry loop.Votes: 0GitHub stars: 4
- Narrow The ScopeNotice live, mid-session, when repeated attempts at one problem aren't converging — the same error recurring, several edit-and-guess cycles on the same file or area, or a fix that keeps growing instead of landing — and say so out loud instead of quietly grinding on. Usually means the attempted scope is bigger than what's actually been verified to work; the fix is a smaller, checkable slice, not another full-scope guess. Trigger on: the same error text recurring across attempts, three or more ...Votes: 0GitHub stars: 4
- Plan FirstFront door for work that will span more than one file, review unit, or commit. Produces the plan before the first edit: the claim, the done-gate, the slice boundaries, the gates that will run, and the base it runs against. Names the invariants that apply rather than restating them. Use before authoring implementation work, or when a task is about to become a PR stack.Votes: 0GitHub stars: 4