All authors
Claude Skills by choiyounggi
github.com/choiyounggi20 skills1 installs47 views
- ConfigureSet up dev-loop's capability-role tool profile — map `knowledge` (your domain wiki / MCP), `verify` (your project's test/build/lint/typecheck/QA command), `explore` (code search), `tacit` (past incidents), and `design` (Figma/visual spec) to the actual tools this environment has, then write ~/.claude/dev-loop/tools.json (global) or <repo>/.dev-loop/tools.json (per-repo). Use when asked to "configure dev-loop", "set up tools", "map my wiki/test command", or "/dev-loop:configure".Votes: 0GitHub stars: 5
- Knowledge FlushDrain queued ★ Insight candidates (harvested from your sessions) into the wiki as a reviewed PR. For each candidate it researches and verifies the best-practice against real sources, checks existing wiki layers for duplicates and links, decides the target layer/category (or justifies a new one), runs wiki-ingest, then opens ONE PR per flush for you to review and merge/reject. Never auto-merges. Use when asked to "flush knowledge", "process the insight queue", "ingest what I learned", or "/dev...Votes: 0GitHub stars: 5
- Loop ImplementThe single implementation loop. It plans via wiki-plan (step 2, required) into an ordered, wiki-navigated task list, then executes those tasks in order, each loading only its named wiki pages, writing tests first, getting an independent test-quality audit, and judging against done; on failure it reflects and retries (bounded). Use for a non-trivial task or feature. Skip typos, config values, and simple renames.Votes: 0GitHub stars: 5
- OrchestrateOrchestrate one natural-language goal into parallel tmux Claude Code sessions. It decomposes the goal (with your approval), plans each task with wiki-plan, implements and reviews, runs an integration test, and merges after your confirmation. Use to build a goal across multiple sessions. For a single task, use loop-implement instead.Votes: 0GitHub stars: 5
- Wiki IngestAdd one verified lesson or edge case to the bundled wiki. Route it to the right domain and category, merge into an existing page before creating a new one, and enforce sourcing and positive-guidance rules. Use when capturing a documented best practice or a production edge case.Votes: 0GitHub stars: 5
- Wiki LintHealth-check the bundled wiki. Detect unsourced claims, bare prohibitions, broken links, index and page trigger mismatches, vague qualifiers, oversized pages, stale dates, and model-era re-verification candidates, then fix them; reports a numeric health score (0-100). Use to keep the wiki healthy before drift compounds. Check 18 lists zero-citation pages from the optional usage telemetry as a review queue. Check 19 reports near-duplicate trigger pairs from the optional vector index.Votes: 0GitHub stars: 5
- Wiki PlanThe fixed planning methodology for a capable model. Make every design decision grounded in a bundled wiki page (recording a decision-to-page map), then decompose the work into ordered, self-contained tasks, each naming the exact wiki pages that govern it. Runs as loop-implement step 2.Votes: 0GitHub stars: 5
- Wiki QueryAnswer a development question from the wiki with citations, loading only the pages whose triggers match. If the answer required synthesis across multiple pages and the question is likely to recur, file the synthesis back as a new page so knowledge compounds.Votes: 0GitHub stars: 5
- Graph SetupOnboard a workspace of git repos onto the graphify code graph — detect or (with consent) install graphify, record the workspace roots in tools.json, build absent graphs with graphify update after one batch confirmation, and install graphify's post-commit/post-checkout hooks plus dev-loop's post-merge hook per repo. Use when asked to "set up the code graph", "onboard the workspace", "install graphify", "graph setup", or "/dev-loop:graph-setup".Votes: 0GitHub stars: 5
- Tasksskills/orchestrate/SKILL.md lists lens 6 `Excess` after lens 5, and all three tier statements in SKILL.md (profile table row, Phase 4 Lens set by tier paragraph) include lens 6 for every tier. - wiki/qa/document-verification/editing-a-gated-document.md — use for: anchor inventory before editing (lens_order, "exactly five", "1 and 3 only") - wiki/qa/process/fresh-context-code-review.md — use for: why the check sits in the fresh-context reviewer (D1) - the lens 6 text, verbatim, in plans/excess-Votes: 0GitHub stars: 5
- PlansGoal: close the "Tutor" gap in our knowledge loop. Today the flow is one-way (capture → store → recall by the LLM); nothing ever tests whether 영기 has actually internalized the lessons in HABITS.md. This adds the reverse flow: spaced, diagnostic self-quizzing on distilled lessons.Votes: 0GitHub stars: 3
- Self TestProve the guardrails Bash guard is live — runs a simulation that feeds representative dangerous commands (curl|sh, rm -rf, DROP TABLE, kubectl delete, cloud deletes, …) through the real guard and shows the block/ask decision for each, WITHOUT executing any of them. Use when asked to verify the guard is working, or right after installing guardrails.Votes: 0GitHub stars: 3
- ConsolidatePeriodically merge the memory index, long-tier memory files, and the habit file — deduplicate, resolve contradictions to the current truth, absolutize dates, bring HABITS.md back under budget — and propose the result for your confirmation before any write. Use when MEMORY.md grows large (~120+ lines), when the habit file is over budget, or when memories accumulate duplicates, contradictions, or stale facts.Votes: 0GitHub stars: 3
- HabitDistill a lesson — a mistake, a user correction, or a praised behavior — into HABITS.md as a positive practice or a hard line, after it clears the damage/recurrence/generality gate. Use after the user corrects you, after an incident, or when a correction signal fires.Votes: 0GitHub stars: 3
- IdentitySet, change, or decline the user/assistant names that memory-loop injects at session start. Use when the user wants to set up names, rename either party, ask the assistant to pick its own name, or stop the name-setup offer from appearing.Votes: 0GitHub stars: 3
- RememberSave gate for persistent memories — confirm tier (long/short) and expiry with the user before writing, so hallucinated or transient facts never enter long-term memory. Use whenever saving a memory file, and when the expiry sweep reports archived memories.Votes: 0GitHub stars: 3
- SetupFirst-time memory-loop setup — offer identity names, create HABITS.md and OUTPUT.md from the templates, wire their imports into ~/.claude/CLAUDE.md, write an initial config, and verify the hooks respond.Votes: 0GitHub stars: 3
- TutorRun a spaced-repetition self-quiz over lessons already distilled into HABITS.md — one novel-scenario transfer question per due item, anti-sycophancy grading, and a 1-4 recall rating logged through the tutor scheduler. Use when the user asks to be quizzed or reviewed (English or Korean), or replies to a memory-loop tutor due-reminder line ("N개 복습 항목이 대기 중").Votes: 0GitHub stars: 3
- Loop ImplementClose a single implementation task with a methodology-grounded verification loop — define done, analyze, plan, write tests first (Red), implement (Green), run, self-review, get an independent test-quality audit, then judge against done; on failure reflect and retry (bounded). Use for one non-trivial task (feature, fix, behavior-changing refactor). Skip for typos, config values, simple renames.Votes: 0GitHub stars: 2
- OrchestrateOrchestrate one natural-language goal into parallel tmux Claude Code sessions — clarify requirements, branch by environment, decompose into tasks (with approval), launch a session per task running loop-implement, review and integration-test, then merge after your confirmation. Use when asked to build/implement a goal "with the orchestrator" or to split work across multiple sessions. For a single task, use loop-implement instead.Votes: 0GitHub stars: 2