All authors
Claude Skills by mcorbett51090
github.com/mcorbett51090964 skills6 installs216 views
- Declarative VisualizationAuthor a Vega-Lite / Deneb / SVG spec for a stated intent on any surface (web vega-embed, react-vega, Evidence, Observable, Power BI Deneb, Tableau extension/SVG, SVG-in-DAX). Six-step method: pick grammar → bind data → encode → wire interactivity → test null/empty → verify via render loop. Ships a surface-agnostic spec-patterns library. Mandatory security audit (no data.url, no remote loader, no SVG script) enforced by lint.py (Gate 101). Complements the visual-feedback-loop (render referee)...Votes: 0GitHub stars: 7
- Dependency Update SweepWhen a tracked host tool (Claude Code, Copilot CLI/Chat, Codex CLI, Cursor, Gemini CLI, Aider, Windsurf — read live from host-support.json) ships a new version, scan the repo for citation-marked drift, auto-apply safe mechanical fixes, and queue judgment calls for review. Reach for this skill on "a host tool updated, what needs to change" or via the SessionStart nudge.Votes: 0GitHub stars: 7
- Design CloneCapture a reference website's full design schema (spacing/type/grid/elevation/component recipes) and apply it to a target — cloning the craft while swapping in the target's own brand and structurally blocking the reference's identity from leaking. Fidelity is browser-gated; trade dress is not cleared here.Votes: 0GitHub stars: 7
- Design LinkBind THIS repo to one of your claude.ai/design design-system projects in one step — lists your projects, lets you pick, and writes .ravenclaude/design-project.json so every session's capability banner surfaces the link and the agent can read/edit the project. Use when starting design work in a repo that has no .ravenclaude/design-project.json yet (or to re-point it). Pairs with the built-in /design-sync skill (which does the actual component sync) and the DesignSync tool.Votes: 0GitHub stars: 7
- Diff BudgetEnforces a per-PR file-count and LoC budget. PRs touching >5 files or >400 LoC route to architectural review before merge. Counters T-1 (premature abstraction) + T-4 (going off-script) — Copilot CLI degrades sharply past 10 files per file, and uncontrolled diff growth is the strongest predictor of off-pattern mutations.Votes: 0GitHub stars: 7
- Draft Agent BriefUse this skill when the user wants to create a new agent and has a clear business goal but isn't fluent in the agent's target domain. Walks them through producing a strong brief by filling in `templates/agent-brief.md` from their plain-language description, then iterating once or twice before building or dispatching the agent. Triggers when the user asks for "a new agent that does X" without already supplying the technical spec, or when they've filled the brief template and left blanks where ...Votes: 0GitHub stars: 7
- Environment DiscoveryAuto-discover the consumer's environment posture by probing installed CLIs (pac / az / aws / gcloud / gh) with read-only commands at session start, decoding JWTs for role/scope claims, and assembling a draft `.ravenclaude/environment-context.md` for save/edit/skip. Streamlines proposal 2026-05-22-001's permission-awareness mechanism.Votes: 0GitHub stars: 7
- External Agent OnboardingOnboards a non-Claude-Code coding agent (GitHub Copilot CLI / OpenAI Codex CLI / Cursor / Aider / Devin Desktop) to this repo at session start. Use when this repo will be operated on by an agent that does not natively read CLAUDE.md. Routes through AGENTS.md, then layers the per-host wiring, version floors, and failure-mode mitigations that host actually needs.Votes: 0GitHub stars: 7
- Forge PipelineThe FORGE gated-planning pipeline that /forge runs: depth-scaled gates that turn any idea into a two-panel-reviewed, critic-checked, tiebroken, routed plan. Mimics Claude Code Ultraplan's deep-plan loop and improves it with cross-model divergence, a fact-verification gate, a correlated-error critic, and a binding tribunal for conflicts.Votes: 0GitHub stars: 7
- Game Theory BasicsUse this when multiple agents or parties have incentives — sketch payoffs, dominant strategies, and equilibrium intuition for coordination, gates, and escalation.Votes: 0GitHub stars: 7
- Github Gold StandardScore a consumer repo's GitHub-development protocol against the shipped gold-standard catalog and produce a remediation queue ranked by leverage. A 10-row core rubric (mapping 1:1 to the P3 exemplar-repo catalog + the P4 Actions-hardening rules) plus 3 agent-operability rows for the agent-as-primary-GitHub-operator bar — each row is a check the agent runs against .github/workflows/*, the repo's .git, and its ruleset, a pass/partial/fail verdict, and the shipped fix (an /init-agent-ready templ...Votes: 0GitHub stars: 7
- Knowledge File Staleness SweepRun a periodic staleness sweep over all `plugins/<plugin>/knowledge/*.md` files and any decision-tree sections — flag entries past their `last-verified` window, categorize by re-verification effort (Tier 1-5 per Researcher schema), produce a remediation queue with named re-verifiers. Reach for this skill on the Researcher's weekly cadence OR before a marketplace release. Used by `deep-researcher` (primary) plus the maintainer.Votes: 0GitHub stars: 7
- Knowledge HealthSurface knowledge-file staleness across all plugins as a Structured Output block. Wraps the `knowledge-health.py` script — sweeps `plugins/*/knowledge/**.md`, groups files by bucket (stale / due_soon / untracked / fresh), and returns a remediation queue. Used by the release checklist and the `ravenclaude doctor` health check. Read this skill before answering "is our knowledge layer current?", "which knowledge files are stale?", or before tagging a marketplace release.Votes: 0GitHub stars: 7
- MimirClaude-Code-session-state surfacing contract for the Mímir dashboard tab. Documents the five reachable on-disk sources under `~/.claude/` and `<project>/.claude/`, the encoded-path algorithm + reverse-decode fallback, the hard scrubbing/torn-write/staleness/worktree/server-parity invariants, the per-card source map, and the honest empty-state contract for in-process-only fields. Read this before authoring or modifying `_read_mimir` (in both `serve-dashboards.py` copies), the `/__mimir` endpoi...Votes: 0GitHub stars: 7
- New WorktreeCreate an isolated git worktree under .claude/worktrees/ for a sub-agent to work in. Use this before dispatching any coder agent so that parallel work cannot collide.Votes: 0GitHub stars: 7
- Pbir Layout EngineDeterministic layout-arithmetic linter for dashboard/report page definitions. Runs seven checks — no-overlap (AABB), within-canvas, equal-gap, column-alignment, and three PBIR-specific invariants (no-empty-binding, bounded theme-override count, visualType/displayOption schema validity) — against a page JSON, a page directory, or a fixture set. Stdlib-only, no network, exit-coded for CI. The load-bearing technical core under the data-viz-designer agent; usable standalone to lint a Power BI PBI...Votes: 0GitHub stars: 7
- Permission HygieneDiagnose and improve a Claude Code project's permission setup — the `.claude/settings.json` allow/ask/deny rules and the `.claude/settings.local.json` personal overrides. Use when settings.local.json has grown bloated (>20 rules, many one-shot), when permission prompts feel too frequent or too coarse, or before sharing a project's settings.json with a team. Companion to the Claude Code core `/fewer-permission-prompts` skill (which is the data-driven sweep); this skill is the design discipline...Votes: 0GitHub stars: 7
- Plugin Release ChecklistPre-release checklist for shipping any plugin update through this marketplace — plugin.json + marketplace.json + architecture.md version-mirror discipline, .repo-layout.json glob coverage for new dirs, CLAUDE.md skill / template tables synced, JSON validation, prettier check, audit-gates meta-test, and the consumer migration-note rule. Includes the exact bash commands to run (Windows PowerShell + bash). Reach for this skill at the end of any plugin PR or before merging a release-candidate bra...Votes: 0GitHub stars: 7
- Probe KitRun a ready-made CONTROL probe alongside any negative result — http/dns/file/cmd. A negative is not a diagnosis until a positive control on the same subsystem has been observed. Makes the right action one line instead of an idea you have to have.Votes: 0GitHub stars: 7
- Prompt OptimizerRewrites an ambiguous-but-single-domain (domain_count<=1) user prompt via emit_optimized_prompt, or drafts an advisory multi-domain dispatch plan via emit_dispatch_plan (domain_count>=2), before the turn runs — surfacing constraints, missing context, and wild assumptions instead of silently guessing or fragmenting. Phase 5 screens/formats either generator's output before injection. Companion generators to prompt-optimizer-gate.sh's Tier-1 classifier.Votes: 0GitHub stars: 7
- Prompt Pattern LibraryCurated, applied prompt-pattern catalog used across this marketplace — decision-tree traversal pre-action prior, alternate-methods-before-blocked, Structured Output Protocol `---RESULT_START---` block, scenario-retrieval inline prior, escalation-by-mandatory-phrasing, citation-aware research, environment-context preamble, orchestrator-worker reinforcement, agent-scenario-authoring frontmatter, claim-grounding/source-honesty marker. Each pattern includes when to use it, what it composes with, ...Votes: 0GitHub stars: 7
- PseudonymizeReversibly pseudonymize names/entities in text BEFORE sending it to a model, and restore them in the reply. Deterministic denylist (reliable) + structured PII + optional NER; local vault; residual scan. Pseudonymizes, does NOT anonymize.Votes: 0GitHub stars: 7
- Quantitative Problem SolvingUse this when something failed or may fail — enumerate failure hypotheses, cost each try, update P(cause|history), and pick the next action by expected value / EVPI.Votes: 0GitHub stars: 7
- Ravenclaude Core OrchestrationUse this when leading multi-agent work — dispatch specialists, gate reviews, handoffs, walls, plan→build→verify, and disciplined problem-solving (first principles, Occam, quantitative failure analysis).Votes: 0GitHub stars: 7
- Rc Deep ResearchDeep research harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report. Includes an inline substrate adapter that reads .ravenclaude/run-config.json once at startup; when enabled:false (the default) all agent() calls are byte-identical to the pre-port baseline (a behavioral invariant — no gate currently CI-enforces it).Votes: 0GitHub stars: 7
- Refine To RubricIterate an artifact until it measurably passes a BOUNDED rubric — the Convergence Engine. Objective/deterministic gates run BEFORE any model judge, the judge is a DIFFERENT model than the author (never self-grade), the stop decision is a model-free predicate, and it emits the BEST iteration (keep-best/regression-revert) under a hard iteration cap + model-call budget. The engine NEVER claims perfect — verdicts are rubric-pass | capped | plateaued | budget-exhausted with an honest residual-gaps...Votes: 0GitHub stars: 7
- Repo Build StudioBuild a website or dashboard by prompting Claude and watching it render live, then commit it back — by COMPOSING existing surfaces (Claude Code on the web + a self-contained-HTML constraint + a GitHub Pages/githack branch preview + a PR), not by building a custom backend. Use when someone wants the "pick a repo, prompt, see it build, ship it" loop. Covers the static/self-contained case fully; says when a real data-connected dashboard needs the heavier Tier-1 path.Votes: 0GitHub stars: 7
- Repo ReviewWhole-repo systematic bug sweep — deterministic chunking + a content-hash cache + a Workflow-orchestrated multi-dimension review fan-out (correctness / security / concurrency / resource-leaks / error-handling / performance / ci-cd-actions-security / dead-code-simplification), cross-model-checked at higher tiers, merged and verified before any fix is proposed. Distinct from Claude Code's own built-in /code-review, which reviews a diff/PR/branch — this skill reviews the whole tree, including Gi...Votes: 0GitHub stars: 7
- ResearcherMeta-skill that keeps all agents, skills, and knowledge files current and honest — Daily Quick Check + Weekly Deep Research modes. Categorization schema (Tier 1 Consensus / 2 Strong-but-Contextual / 3 Divergent / 4 Emerging / 5 Deprecated). Includes 90-day staleness checks for decision trees AND `.ravenclaude/environment-context.md`.Votes: 0GitHub stars: 7
- Review Staged ContributionsFor the RavenClaude marketplace maintainer. Walks every file in docs/staging/incoming/ one at a time, runs a security sweep + topic-expert analysis on each, presents each with a keep/update/deny prompt, promotes approved submissions to their canonical location (docs/memory-bank/lessons-learned.md for lessons, docs/best-practices/<slug>.md for best-practices), and deletes denied ones. Trigger when the maintainer says any of "check for updates", "check the staging queue", "anything in staging",...Votes: 0GitHub stars: 7
- Routine Review TribunalGate an unattended scheduled routine's produced diff/PR through a two-panel, cross-model tribunal (mirrors /forge-pipeline's divergent-panel + tiebreak shape, applied after the fact) before it is finalized: approved as-is, sent back for a bounded revision round, or escalated to a human. Use at the end of any routine whose run contract ends in opening or updating a PR (plugin-discovery, research-cadence).Votes: 0GitHub stars: 7
- Run Full Test SuiteRun the project's full quality gate — format check, lint, typecheck, unit tests, integration tests — in order, fail fast, summarize. Use before reporting any non-trivial change as complete.Votes: 0GitHub stars: 7
- Scenario RetrievalConsult the unverified scenarios bank (`plugins/<plugin>/scenarios/*.md`) before answering plugin-domain questions. Glob + tag-filter + recency-weight, surface top 2-3 with mandatory unverified-scenario preamble ("Based on N unverified scenarios from YYYY-MM tagged [scope] — verify in your environment"). Secondary source — never replaces canonical knowledge files.Votes: 0GitHub stars: 7
- ScoutDiscover great-but-low-visibility ideas — the fringe excellence mainstream search buries under popularity. Given a seed (a name, repo, post, or topic), traverse its citation/collaborator graph + the periphery sources, score each candidate on depth × novelty × practitioner-grounding MINUS a popularity penalty, dedup against the idea-board + installed plugins, and emit a ranked shortlist that routes the best finds into /forge. Use when you spot a promising fringe idea (often on LinkedIn / X / G...Votes: 0GitHub stars: 7
- Session HandoffWrite a run-dir handoff and start a NEW interactive session (unbounded TUI — never a headless print-flag). Use for /handoff, context full, fresh window, quota host-switch, 'pass remaining work to Grok'. NOT for one bounded Grok/Copilot job → cheap-lane-delegation.Votes: 0GitHub stars: 7
- Session RelayHand a mid-flight finding or a small, well-scoped task to the RIGHT peer Claude Code session — the one already working in the relevant worktree/branch — via ListAgents/SendMessage, instead of paging the human or letting the finding go stale until that session's next Stop. Use when you discover something relevant to another live worktree; NOT for routine sub-agent dispatch (spawn-team) or starting a new peer session.Votes: 0GitHub stars: 7
- Set PostureTranslate `.ravenclaude/comfort-posture.yaml` into `.claude/settings.json` permission rules. Owns the (category, level) → permission-rule emission table that the `/set-posture` slash command applies. Read this skill when authoring or reviewing the translation logic, when a category is missing rules, or when a level's behavior surprises you.Votes: 0GitHub stars: 7
- Skill IndexLook up any skill in the marketplace by name or topic, including a disabled one, and get its exact re-enable command. Reach for this when you suspect a skill exists for the current task but it is not in your listing.Votes: 0GitHub stars: 7
- Spawn TeamTeam Lead dispatch playbook. Pick the surface first (slash command vs skill vs specialist agent vs orchestration shape — Step 1.25), then whether to delegate (Step 1.5), then which agents and order. Load whenever choosing skill vs agent vs slash, weighing delegation, or about to dispatch more than one agent. Keeps routing consistent; platform description-match alone is not the router.Votes: 0GitHub stars: 7
- Spec Reread RitualBefore writing any code for a task in a multi-task build, the agent MUST re-read the relevant spec section verbatim, paste it into the work log, and quote the prior. NO work from memory. Counters the "100% spec drift" failure mode from the Claude Code bug study (issue #19739) — where 11/11 sessions drifted from the spec and exact-match format compliance was 0%.Votes: 0GitHub stars: 7
- Structured OutputEnforce the Structured Output Protocol — every sub-agent handoff ends with a `---RESULT_START--- ... ---RESULT_END---` JSON block alongside the human-readable Markdown. Team Lead parses the JSON for routing; Markdown stays for human review. Active across all 14 core specialists.Votes: 0GitHub stars: 7
- Svg Report LintLint a standalone SVG file for geometry soundness, legibility, and security before committing to a report or embedding in Power BI/Tableau. Checks viewBox presence and aspect ratio, minimum text font-size, and the security floor: no <script>, no on* handlers, no <foreignObject>, no remote href/use. Gate 103. Complements declarative-visualization (Vega-Lite/JSON spec lint, Gate 101) and pbir-layout-engine (coordinate arithmetic). NOT for Vega-Lite JSON specs (use declarative-visualization) or ...Votes: 0GitHub stars: 7
- Terminal Status IndicatorsMake VS Code terminal tabs show 🔔 + chime the moment an agent session needs you, across many parallel Copilot/Claude terminals. Installs three layers: workspace settings (tab bell icon + audio cue), a shell prompt hook (bell on command completion), and a background /proc-io watcher that rings a terminal's PTY bell when its agent process goes idle after responding. Use in a Codespace / VS Code setup where you run multiple background agent sessions and can't tell which one is waiting for input...Votes: 0GitHub stars: 7
- Thing Denial KbThe Thing-denial knowledge base (Muninn). When the command/decision tribunal DENIES or DEFERS an action, consult this to identify WHY the same block keeps happening and the known fix, then teach the KB a new resolution once you solve one. Read it the moment the Thing blocks you. Reads the Sága audit logs; never touches the tribunal's live path.Votes: 0GitHub stars: 7
- ThingCommand review (the Thing) — the opt-in command-review tribunal that votes ALLOW/EDIT/DENY on shell commands (and ALLOW/DENY on file edits) a comfort-posture category is set to review. Read this when wiring, debugging, or explaining the tribunal: the PreToolUse orchestrator, the reviewer panel + tie-breaker, the deterministic concern evaluator, the tier model, the dashboard-configurable panel, the per-category toggle, the audit trail, and the fail-closed rules. T5 = tiered routing (low→extrem...Votes: 0GitHub stars: 7
- Two Panel Plan ReviewTwo fresh-independent expert panels review a strategic plan, fill its gaps, author a tactical build plan, then a different panel cold-reviews the build plan and emits P0/P1 recommendations. Includes an upfront advisory routing analysis recommending Ultraplan (cloud) vs. local for the task.Votes: 0GitHub stars: 7
- Update RavenclaudeBring a RavenClaude install up to date when it's stale, when new skills/agents aren't showing, or after upstream changes ship. Covers both hosts: under GitHub Copilot CLI the update is `git pull` in the marketplace clone then re-running `ravenclaude setup` (idempotent); under Claude Code it's `/plugin marketplace update ravenclaude` then `/reload-plugins`. Read this skill on triggers like 'update ravenclaude', 'ravenclaude is stale', 'refresh skills', or 'new skills not showing'.Votes: 0GitHub stars: 7
- Visual Feedback LoopRender → see → critique → edit → re-render: the discipline (and a deterministic referee) that lets an agent inspect its OWN rendered output — a web page, a dashboard, a Power BI / Tableau report — and iterate toward correctness/pixel-perfection against objective stopping signals instead of 'looks better'. The referee (driver.py) merges the pbir-layout-engine layout linter with agent-captured console/Lighthouse evidence into one pass/fail verdict. Use when building or refining any visual surfa...Votes: 0GitHub stars: 7
- Wall HandlingWhen an agent hits a wall (same tool + same error 3+ times, an impossible TypeScript fix, a missing API surface, a failing test it can't resolve in one attempt), STOP — do not invent the API, do not delete the prop, do not '@ts-ignore'. Take the documented default with an inline comment, or ask the user. Counters the "agents push forward through impossible tasks" failure mode (Cognition/Devin retrospective + Claude Code spec-drift study).Votes: 0GitHub stars: 7
- Webfetch HardeningDeterministic sanitizer floor for WebFetch return envelopes — strip injection-shaped blocks before any agent treats fetched-body content as authoritative. Two confirmed-in-wild observations (2026-06-02) at ibcs.com/standards and the FT chart-doctor GitHub tree drove this. Used by any agent that issues a WebFetch — deep-researcher (most exposed), architect, code-reviewer, security-reviewer, plugin-release-checklist, dashboard-builder, power-bi-engineer.Votes: 0GitHub stars: 7