Claude Skills by kelp

github.com/kelp

30 skillsA× 28B× 20 installs37 views

Cross ReviewAMulti-model code review with cross-validation. Orchestrates independent Claude and GPT-5.4 reviews, cross-validates findings, outputs merged fix list. Use when reviewing code changes, auditing files, or wanting a second opinion. Triggers on: "cross-review", "multi-model review", "review with codex", "get a second opinion on this code".data-airustgoVotes: 0GitHub stars: 2
Kb CaptureACapture the current conversation, a source, or a synthesis into Travis's personal knowledge base as a well-formed wiki note. Writes correct frontmatter with today's date, picks the right bucket (sources/external, reports/, concepts/, questions/), cites existing source IDs, and runs just refresh to reindex afterward. Use when the user says "capture this", "save this to the KB", "add this as a note", "/kb-capture", or asks to file a finished research output.data-aigoshellVotes: 0GitHub stars: 2
Kb IngestBDownload an external documentation site into Travis's personal knowledge base as a doc pack and source note. Use when the user says "/kb-ingest <url>", "ingest these docs", "add these docs to the KB", or "download reference docs". Runs webdown crawl via the knowledge repo's ingest-pack recipe, then creates a MANIFEST.md and source note automatically.data-aigoshellVotes: 0GitHub stars: 2
Kb Research PolicyARouting and retrieval policy for Travis's personal knowledge base at ~/code/knowledge (or the knowledge-base: path in the active project CLAUDE.md). Use when the user asks about past research, prior notes, captured sources, topics they have studied, or anything that might live in a personal wiki of synthesized notes. Triggers on phrases like "what do we know about", "check my notes", "any research on", "from the KB", "have I looked into", "do I have notes on". Tells you to read the cheap inde...data-aishellbashVotes: 0GitHub stars: 2
Tdd InitAAdd TDD pipeline configuration template to this project's CLAUDE.md. Run this to set up the pipeline for a new project.data-aiVotes: 0GitHub stars: 2
Tdd OrchestrateAEnforce strict red-green-refactor TDD for any task. Use when implementing features, fixing bugs, adding functionality, or building new modules. Routes to the full 7-agent pipeline for new modules with 3+ behaviors, or runs inline red-green-refactor for bug fixes and small changes. Triggers on: "use TDD", "fix this bug", "add a feature", "implement", "run the pipeline", "TDD pipeline", "build a module with TDD", or any coding task in a project with TDD in its CLAUDE.md.developmentgoshellVotes: 0GitHub stars: 2
Skills DirectorySkills Directory Look up any of 103,619 scanned skills — grade, score, and every finding. Free.Check a skill
Tiger CheckAAudit Zig source files for Tiger Style violations -- functions > 70 lines, lines > 100 columns, usize usage, direct recursion, compound assert(a and b), and bare while (true) without an adjacent assert.data-aiexpressgitVotes: 0GitHub stars: 2
Tiger InitAAdd TigerBeetle's Tiger Style guidance to this project's CLAUDE.md. Run this in any Zig project to apply Tiger Style's rules on assertions, bounded loops, static memory, naming, function shape, comments, and formatting.data-aiVotes: 0GitHub stars: 2
Tiger PatternsATiger Style rules for Zig: assertions (2+ per fn, paired positive/negative space), bounded loops (no recursion), static memory after init, snake_case naming with unit suffixes, 70-line function limit, 100-column line limit, zig fmt. Use when writing or reviewing Zig in a project that follows Tiger Style.data-aigoapiVotes: 0GitHub stars: 2
Zig CheckAAudit Zig source files for Zig 0.15.x mistakes -- checks for removed APIs (getStdOut, usingnamespace, BoundedArray, async), missing flush, wrong ArrayList usage, ambiguous format strings, signed division, and renamed stdlib functions.data-aigitapiVotes: 0GitHub stars: 2
Zig InitAAdd Zig 0.15.x training corrections to this project's CLAUDE.md. Run this in any Zig project to fix Claude's outdated patterns for I/O, ArrayList, format strings, build.zig, BoundedArray, and usingnamespace.data-aiVotes: 0GitHub stars: 2
Zig PatternsACorrect Zig 0.15.x patterns for I/O, ArrayList, format strings, and build.zig. Use when writing or reviewing any Zig code -- Claude's training data is outdated for these APIs.data-aigoshellVotes: 0GitHub stars: 2
PairAPair program with a persistent navigator on Codex, Grok, or Claude. The current session drives (edits, tests); the named harness navigates in a read-only warm session. Use when the user wants to pair, get iterative review from another harness, or says "/pair", "pair with grok", "pair with codex". Subcommands: start, design, review, judge, resume, status, end, or a freeform message. A Fable judge breaks deadlocks when Claude is the driver.ai-agentsgoshellVotes: 0GitHub stars: 2
Fleet EfficiencyAHow to brief, dispatch, and right-size subagents, plus the context-handoff, prompt-cache, and model-tier rules for agent fleets. Read BEFORE any Agent call: choosing an agent type or model, deciding whether a task is worth delegating, or when a delegated result comes back thin. Required before launching 3+ parallel agents, writing a Workflow script, or running audits, migrations, or multi-stage pipelines. Every agent dispatch names its model explicitly.ai-agentsrustgoVotes: 0GitHub stars: 2
Fleet LeadARun a two-lead agent fleet against one repo: a drive lead that claims work units, commits and opens PRs, and a gate lead that watches CI, drains review comments, and restarts the drive lead when it stalls. Read when starting or joining a fleet, claiming or releasing a unit, or when a unit has gone quiet. Covers unit claiming with a file-disjointness check, heartbeats, and restart from a ledger.developmentrustgoVotes: 0GitHub stars: 2
Cross ReviewANative code review from Claude, Codex, and/or Grok. Call one harness or any set. Each callee uses its own reviewer. Triggers on: "cross-review", "review with grok", "ask Codex to review", "multi-harness review".ai-agentsgobashVotes: 0GitHub stars: 2
Kb CaptureACapture the current conversation, a source, or a synthesis into your personal knowledge base as a well-formed wiki note. Writes correct frontmatter with today's date, picks the right bucket (sources/external, reports/, concepts/, questions/), cites existing source IDs, and runs just refresh to reindex afterward. Use when the user says "capture this", "save this to the KB", "add this as a note", "/kb-capture", or asks to file a finished research output.ai-agentsgobashVotes: 0GitHub stars: 2
Kb IngestBDownload an external documentation site into your personal knowledge base as a doc pack and source note. Use when the user says "/kb-ingest <url>", "ingest these docs", "add these docs to the KB", or "download reference docs". Runs webdown crawl via the knowledge repo's ingest-pack recipe, then creates a MANIFEST.md and source note automatically.ai-agentsgoshellVotes: 0GitHub stars: 2
Kb Research PolicyARouting and retrieval policy for your personal knowledge base at ~/code/knowledge (or the knowledge-base: path in the active project CLAUDE.md). Use when the user asks about past research, prior notes, captured sources, topics they have studied, or anything that might live in a personal wiki of synthesized notes. Triggers on phrases like "what do we know about", "check my notes", "any research on", "from the KB", "have I looked into", "do I have notes on". Tells you to read the cheap index/ f...ai-agentsbashdocumentationVotes: 0GitHub stars: 2
Next Issue InitAAdd Next issue binding to this project's CLAUDE.md. Run this to set up the next-issue plugin for a new project.ai-agentsgitVotes: 0GitHub stars: 2
Next IssueALand one GitHub child issue as one pull request: choose the next child issue, write a plan, review the plan (three axes, or Astra only for a non-behavior exception), implement with red-green TDD, open a draft pull request, and drain review comments until CI is green and no threads remain. Use when starting a slice, landing the next child issue, planning a slice, or when asked to address all PR review comments until they are fixed. Previously /next-todo.ai-agentsgogitVotes: 0GitHub stars: 2
Next ParentALand one GitHub parent issue's remaining open sub-issues by running next-issue once per child. Default is the parent of the next ready sub-issue. Use when the user runs /next-parent or asks to land a parent issue. Do not use this for a single sub-issue; that is /next-issue.ai-agentsgogitVotes: 0GitHub stars: 2
Tdd InitAAdd the TDD pipeline configuration template to this project's instructions file (CLAUDE.md or AGENTS.md). Run this to set up the pipeline for a new project.ai-agentsVotes: 0GitHub stars: 2
Tdd OrchestrateAEnforce strict red-green-refactor TDD for any task. Use when the user asks for TDD or the pipeline ("use TDD", "run the pipeline", "TDD pipeline", "build a module with TDD", "fix this bug with TDD"), or for any coding task in a project whose instructions file has a TDD Pipeline Configuration section. Routes to the full 7-stage pipeline for new modules with 3+ behaviors, or runs inline red-green-refactor for bug fixes and small changes. Role agents default to Opus; pass `--model <name>` to pin...ai-agentsrustgoVotes: 0GitHub stars: 2
Tiger CheckAAudit Zig source files for Tiger Style violations -- functions > 70 lines, lines > 100 columns, usize usage, direct recursion, compound assert(a and b), and bare while (true) without an adjacent assert.ai-agentsexpressgitVotes: 0GitHub stars: 2
Tiger InitAAdd TigerBeetle's Tiger Style guidance to this project's CLAUDE.md. Run this in any Zig project to apply Tiger Style's rules on assertions, bounded loops, static memory, naming, function shape, comments, and formatting.ai-agentsVotes: 0GitHub stars: 2
Tiger PatternsATiger Style rules for Zig: assertions (2+ per fn, paired positive/negative space), bounded loops (no recursion), static memory after init, snake_case naming with unit suffixes, 70-line function limit, 100-column line limit, zig fmt. Use when writing or reviewing Zig in a project that follows Tiger Style.ai-agentsgoapiVotes: 0GitHub stars: 2
Zig CheckAAudit Zig source files for outdated APIs against the project's Zig version (0.15.x or 0.16.x). Detects removed APIs, missing io parameters, missing flush, wrong ArrayList usage, ambiguous format strings, signed division, and renamed stdlib functions.ai-agentsshellbashVotes: 0GitHub stars: 2
Zig InitAAdd Zig training corrections to this project's CLAUDE.md. Detects whether the project targets Zig 0.15.x or 0.16.x and appends the matching corrections. Run this in any Zig project to fix Claude's outdated patterns for I/O, ArrayList, format strings, build.zig, and (for 0.16) the new Io interface, std.fs -> std.Io move, and indexOf -> find rename.ai-agentsbashVotes: 0GitHub stars: 2
Zig PatternsACorrect Zig patterns for I/O, ArrayList, format strings, build.zig, and (for 0.16) the Io interface, std.fs -> std.Io move, and indexOf -> find rename. Use when writing or reviewing any Zig code -- Claude's training data is outdated for these APIs. Detects whether the project targets 0.15.x or 0.16.x and shows the matching reference.ai-agentsgoshellVotes: 0GitHub stars: 2