All authors
Claude Skills by EdbertChan
github.com/EdbertChan60 skills0 installs53 views
- Ship A DetectorAuthor a hook or gate detector end to end: the seven defect kinds this repo keeps re-shipping, then the install, test, README, and inventory wiring a detector is not finished without. Trigger before writing or widening anything under engine/hooks/ or a scripts/check_*.py gate — a new PreToolUse/Stop/UserPromptSubmit hook, a new detector inside an existing hook, or a regex change to one that already ships.Votes: 0GitHub stars: 4
- Show Me Your WorkKeep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result). Local by default; commit it when a reviewer needs the trail. Use for /show-me-your-work, overnight, babysit, autonomous, or multi-phase runs, or work a human reviews after stepping away. Not for a short same-turn fix — that's the evidence rules / prove-it gate.Votes: 0GitHub stars: 4
- Skill Ab Token GateAfter changing a skill or hook meant to cut context/token cost, run a paired A/B workload N times (default 5), aggregate native parent+subagent tokens, publish a GitHub gist with the report and raw session JSONL, and only treat the change as validated when treatment median inclusive tokens beat control. Expand later to other models; default harness is Codex rollout usage.Votes: 0GitHub stars: 4
- Spike And ValidateTurn an untested assumption into real output by building the smallest throwaway that would kill it, running it, then discarding the code and keeping the finding. Use before committing to an invented option, an unfamiliar library or API, or a performance assumption. The gate on `alternatives-considered`.Votes: 0GitHub stars: 4
- Split ScopeShape code changes and PR stacks so each diff is easy to review: one local claim, one safety invariant, clear architectural effect, and an explicit reason for the slice. Trigger before authoring implementation work, PR stacks, or any multi-diff plan, or when asked to split/scope/compress a change into reviewable pieces.Votes: 0GitHub stars: 4
- Visual ProofCapture and present trustworthy before/after visual evidence (screenshots, video) for a UI-affecting change. Use when a PR modifies UI, the user asks for visual proof or before/after screenshots, or when reviewing a UI change and wanting to see what actually changed.Votes: 0GitHub stars: 4
- WhyRecover why code is shaped the way it is before changing it. Use for "why does X work this way", "why was this threshold picked", design rationale, and dead-code questions. Also run it as the research step before reverting a commit, deleting or loosening a guard, check, test, or invariant, or naming a past commit as a root cause. Anchors in git history and PR bodies first, then fans out one investigator per available evidence source and reports every null. Use `how` for runtime behavior.Votes: 0GitHub stars: 4
- Event WaitWait for a background job, workflow, build, or continuous-integration run to finish by subscribing to the events it already pushes, instead of asking for status over and over. Use when a task must block until something elsewhere completes, when many such waits must run at once, or when a wait needs to wake an idle session. Replaces hand-rolled one-off listeners and status polling loops.Votes: 0GitHub stars: 4
- Principle Read State ArtifactsApply when designing, reviewing, or authoring any mechanism that checks on work a background process already tracks: a babysit/watcher loop, a status check on a queue or worker, an agent verifying what a cron already did. Prefer reading the state artifact the worker already wrote (a ledger, digest, or status file) over re-deriving that state with live commands inside a session transcript.Votes: 0GitHub stars: 4
- Spreadsheet AuthoringDesign scalable spreadsheet models with category-level raw data, formula- driven aggregation tables, provenance, and charts. Use when creating or restructuring Excel or Google Sheets workbooks that must grow by adding rows.Votes: 0GitHub stars: 4