codejunkie99
- 162 skills
- 0 followers
- 2.3k repo stars
- yesterday last updated
- ▌ Longwatch · codejunkie99Use when a single prompt is not enough: run a planned multi-turn conversation against the user's own chatbot or agent to see whether its rules wear down over many turns, role changes, or a slow build-up, and keep the full transcript.
- ▌ Portchart · codejunkie99Use when the user wants to know which ports and services are open on hosts they own, usually their local docker compose stack or a staging box, before running web checks. TCP connect scans only, JSON output.
- ▌ Bilgecheck · codejunkie99Use when auditing an agent setup: MCP server configs, SKILL.md files, AGENTS.md, CLAUDE.md, hooks, and tool descriptions, for hidden instructions, invisible unicode, exfiltration asks, unpinned remote servers, and changes since the last check. Offline.
- ▌ Probeplate · codejunkie99Use when running small, written-down HTTP checks against the user's own staging URL, such as exposed admin paths, debug pages, missing security headers, or leaked .git and .env files. Each check is a template that declares passive or active.
- ▌ Squallfuzz · codejunkie99Use when a specific parser, decoder, or input-handling function in the user's own code should be stress-tested with generated inputs, starting from a static finding, with a harness written for it and crashes turned into findings.
- ▌ Be Paranoid · codejunkie99The /be-paranoid command. Use before any security-sensitive task, review, or release to rewrite the task through three lenses (attacker, proof, blind spot), pick which keelsec skills to run and in what order with a pass check for each, and finish with one merged, deduplicated verdict.
- ▌ Evalyard · codejunkie99Use when the user wants their AI feature's safety and quality checks kept as versioned test cases in the repo and run in CI on every change, with failures showing up in the same SARIF and JSON as code findings.
- ▌ Hullscan · codejunkie99Use when auditing the build and deploy files of a repo in one pass: Dockerfile, docker-compose, and later Kubernetes YAML and Terraform, plus a secret and dependency sweep of the same tree so nothing slips between tools.
- ▌ Jibprobe · codejunkie99Use when testing whether the user's own LLM feature or AI code reviewer can be steered by planted text, leaks a planted fake secret, or calls tools it should not. Has a reviewer mode that plants injection canaries in a test diff.
- ▌ Keyprove · codejunkie99Use after a secret scan, to sort each found credential by provider and type, judge how bad a leak would be, and, only with the user's explicit yes per provider, check whether a key is still live using a read-only identity call.
- ▌ Ropewalk · codejunkie99Use when the user wants an agent-driven exploration of their own running staging app, following leads from the static findings, with a closed set of tools and a hard scope, to find issues no single scanner reaches, such as broken access control between users.
- ▌ Seamread · codejunkie99Use when reviewing a branch diff or pull request for security issues with an AI reviewer, in a way that treats the diff as untrusted data and resists instructions hidden in code, comments, commit messages, or file names.
- ▌ Sinkmark · codejunkie99Use when reviewing Python source for injection bugs, especially SQL built from strings, eval or exec of input, shell=True, pickle or unsafe yaml loads. Traces web input to dangerous calls across functions in the same file. Local only.
- ▌ Tidegate · codejunkie99Use when you need to see how the user's running staging web app actually behaves: crawl its pages and forms, watch the traffic for passive issues, and tie each dynamic hit back to the source line that causes it.
- ▌ Depfathom · codejunkie99Use when checking a project's dependencies for known vulnerabilities from manifests or lockfiles, including package.json with no lockfile, requirements.txt, and version conflicts. Groups CVE, GHSA, and PYSEC aliases into one finding per advisory.
- ▌ Drillcard · codejunkie99Use when the user wants a full security workflow on their own repo rather than one scan: confirm scope, run the local checks, triage, fix, re-scan, and write the PR note. It is the playbook layer that drives the other keelsec skills in order.
- ▌ Holdsweep · codejunkie99Use when you have a built container image or an SBOM (CycloneDX or SPDX) and want to know which packages inside it carry known vulnerabilities, without double counting what the source dependency scan already found.
- ▌ Lastproof · codejunkie99Use when a static finding needs a yes or no: take one specific finding, such as a suspected SQL injection, and try a safe, read-only proof against the user's own staging app to mark it confirmed, not reproduced, or inconclusive.
- ▌
- ▌ Tldraw 2 · codejunkie99 bundleCreate and edit diagrams on a connected tldraw canvas using observed shape IDs.
- ▌ Design Md 2 · codejunkie99Apply the project DESIGN.md visual design contract and its existing tokens.
- ▌ Git Proxy 2 · codejunkie99 bundlePerform Git operations with branch protections and verification checks.
- ▌ Data Layer 2 · codejunkie99Inspect cross-tool agent activity, usage, scheduled work, and local reports.
- ▌ Loop Guard 2 · codejunkie99Check loop budgets and checkpoints, stopping on cancellation or stagnation.
- ▌ Skillforge 2 · codejunkie99Create a reusable project skill after checking existing capabilities and conventions.
- ▌ Loop Triage 2 · codejunkie99Summarize a loop contract and checkpoint without modifying the project.
- ▌ Data Flywheel 2 · codejunkie99Export approved, redacted agent runs into local retrieval artifacts and evaluation cases.
- ▌ Loop Verifier 2 · codejunkie99Verify loop work against its contract and configured deterministic checks.
- ▌ Memory Manager 2 · codejunkie99Review and maintain project memory while preserving evidence and separate memory layers.
- ▌ Deploy Checklist 2 · codejunkie99Check release readiness and request human approval before deploying.
- ▌ Loop Constraints 2 · codejunkie99Check loop contracts, permissions, and file-change limits before acting.
- ▌ Debug Investigator 2 · codejunkie99Reproduce, isolate, and verify the root cause of a software failure.
- ▌ Caveman 2 · codejunkie99 bundleUltra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".
- ▌ Cavecrew 2 · codejunkie99 bundleWhen to delegate to `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit) or `cavecrew-reviewer` (diff review) instead of working inline or using `Explore`. Their output is compressed, so main context lasts longer.
- ▌ Company Harness 2 · codejunkie99Build or operate a company-specific harness using bounded work packets, evidence-led artifacts, model-route records, UI artifacts, and dashboards.
- ▌ Company Dashboard 2 · codejunkie99Build an inspectable operational dashboard with metric definitions, data lineage, freshness, permissions, states, and verification evidence.
- ▌ Model Route Record 2 · codejunkie99Record an eligible model tier, rationale, and fallback for a bounded company work packet.
- ▌ Company UI Artifact 2 · codejunkie99Turn a company work packet into a usable UI with explicit users, tasks, data contracts, states, implementation details, and verification evidence.
- ▌ Company Work Packet 2 · codejunkie99Convert a company request into a bounded packet with explicit outcome, scope, authority, inputs, outputs, and checks.
- ▌ Company Code Delivery 2 · codejunkie99Deliver a scoped code or app change with repository evidence, focused verification, reviewable artifacts, and explicit release authority.
- ▌ Company Artifact Review 2 · codejunkie99Package company work as a reviewable artifact with provenance, evidence, authority, unresolved questions, and a recorded review state.
- ▌ Customer Evidence Research 2 · codejunkie99Produce a source-led customer research artifact that separates evidence, claims, inference, uncertainty, and next actions.
- ▌ Design Brain 2 · codejunkie99 bundleBuild and maintain a design knowledge system from website URLs and screenshots. Captures inspiration, extracts reusable patterns, synthesizes connections, and builds persistent design memory. Ripgrep-first — no external LLM required.
- ▌
- ▌
- ▌ Fable · codejunkie99 bundleUse the locally authenticated Claude Code Fable 5.1 model only as the orchestrator for a task, then execute implementation with GPT-5.6 Luna or DeepSeek V4 Flash. Use when the user invokes $fable or asks Fable to orchestrate Codex agents.
- ▌ Graph Engineering · codejunkie99 bundleTeaches an agent graph engineering — both halves. Knowledge graphs (ontology design, entity/relation/event extraction, fusion, GraphRAG/memory serving; distilled and translated from Southeast University's graduate Knowledge Graph course, npubird/KnowledgeGraphCourse, 4.4K stars) and task graphs (agent orchestration — parallel fan-out, verifier separation, the stop rule, human gates). Use when asked to build a knowledge graph, extract entities/relations from text, design an ontology, dedupe/merge entities, add graph memory or GraphRAG to an agent, orchestrate multi-agent workflows as a graph, or LEARN graph engineering — in teaching mode the agent explains each stage with worked examples and generates visual diagram artifacts.
- ▌ Design Brain · codejunkie99Build and query a relational markdown design memory using design-brain-memory and Agent Browser CLI.
- ▌ Setup · codejunkie99Conversational onboarding that generates a personalized design knowledge system. Asks about your design practice, then creates identity, methodology, MOCs, and processing pipeline.
- ▌ Sol · codejunkie99Use Sol to review work or rewrite prompts. Use when the user invokes /sol or wants the Sol utility.
- ▌ Loop · codejunkie99Run the self-improving DeepSeek/Luna/Sol loop. Use when the user says "/loop", "$loop start", or asks to start a self-improving loop with a task, including a repeating 10-minute cadence.
- ▌ Luna · codejunkie99Use Luna to watch, grade, or run bounded worker tasks. Use when the user invokes /luna or wants the Luna utility.
- ▌ Flash · codejunkie99Run the task on DeepSeek V4 Flash. Use when the user invokes /flash or wants the fast DeepSeek utility.
- ▌ Utility · codejunkie99Show the utility-to-model menu for slash commands. Use when the user invokes /utility or asks for the model menu.
- ▌ Deepseek · codejunkie99Run the task on DeepSeek V4 Pro. Use when the user invokes /deepseek or wants deeper DeepSeek reasoning.
- ▌ Systemverilog Rtl Design · codejunkie99Provides RTL design patterns, synthesis guidelines, and coding templates. Use when the user mentions 'module design', 'FSM', 'state machine', 'pipeline', 'synthesizable', 'parameterize', 'parameter', 'localparam', 'clock domain', 'CDC', 'FIFO', 'register file', 'always_ff', 'always_comb', 'generate', or asks about synthesis-related coding.
- ▌ Systemverilog Lint Fixing · codejunkie99This skill should be used when the user mentions 'lint error', 'width mismatch', 'inferred latch', 'undriven signal', 'fix warnings', 'Verilator error', 'WIDTHTRUNC', 'BLKSEQ', or asks to 'check my code' or 'find errors'. Provides error-specific fix patterns for SystemVerilog lint issues.
- ▌ Vcd Waveform Analysis · codejunkie99This skill should be used when the user mentions 'waveform', 'VCD file', 'simulation results', 'signal trace', 'debug the output', 'what happened in sim', 'show me the waves', or 'analyze timing'. Provides VCD parsing, clock detection, anomaly identification, and signal tracing techniques.
- ▌ Systemverilog Testbench Patterns · codejunkie99This skill should be used when the user asks to 'write a testbench', 'test this module', 'add assertions', 'create test stimulus', 'verify the design', 'add clock generation', or 'write a self-checking test'. Provides testbench templates, clock/reset patterns, and assertion guidance.
- ▌ Systemverilog Development · codejunkie99This skill should be used when the user asks to 'design a module', 'write SystemVerilog', 'implement an FSM', 'create a pipeline', or works with .sv/.svh/.v/.vh files. Provides modern SV conventions, coding patterns, and synthesizability guidance.
- ▌ Systemverilog Verification · codejunkie99Provides verification methodology, SVA assertion patterns, coverage techniques, and testbench templates. Use when the user mentions 'testbench', 'assertion', 'SVA', 'property', 'sequence', 'coverage', 'covergroup', 'coverpoint', 'bins', 'cross coverage', 'constrained random', 'randomize', 'constraint', 'simulate', 'waveform', 'VCD', '$display', '$finish', or 'self-checking'.
- ▌ Gateflow Behavior · codejunkie99This skill should be used when the user is working on any SystemVerilog, Verilog, HDL, RTL, FPGA, or ASIC development task. Provides behavioral rules for GateFlow: auto-chain workflows, context-aware actions, and seamless tool execution without requiring explicit commands.
- ▌ Company Dashboard · codejunkie99Build an inspectable operational dashboard with metric definitions, data lineage, freshness, permissions, states, and verification evidence.
- ▌ Model Route Record · codejunkie99Record an eligible model tier, rationale, and fallback for a bounded company work packet.
- ▌ Company UI Artifact · codejunkie99Turn a company work packet into a usable UI with explicit users, tasks, data contracts, states, implementation details, and verification evidence.
- ▌ Company Work Packet · codejunkie99Convert a company request into a bounded packet with explicit outcome, scope, authority, inputs, outputs, and checks.
- ▌ Company Code Delivery · codejunkie99Deliver a scoped code or app change with repository evidence, focused verification, reviewable artifacts, and explicit release authority.
- ▌ Company Harness · codejunkie99Build or operate a company-specific harness using bounded work packets, evidence-led artifacts, model-route records, UI artifacts, and dashboards.
- ▌ Company Artifact Review · codejunkie99Package company work as a reviewable artifact with provenance, evidence, authority, unresolved questions, and a recorded review state.
- ▌ Customer Evidence Research · codejunkie99Produce a source-led customer research artifact that separates evidence, claims, inference, uncertainty, and next actions.
- ▌ X Article Hooks · codejunkie99 bundleWrite a short launch caption, quote-post hook, or agent handoff for an existing article. Use for concise copy that communicates the payoff without rewriting the full article.
- ▌ X Article Ideas · codejunkie99 bundleFind article ideas at the intersection of audience questions, current discussion, and the author's actual experience. Use for topic research, angle selection, or developing a thesis from notes and sources.
- ▌ X Article Write · codejunkie99 bundleDraft, condense, or format an original X article from the author's notes, voice transcripts, and evidence. Use for full articles, early TLDRs, reproducible explanations, or numbered and arrow-list formatting.
- ▌ X Article Review · codejunkie99 bundleReview an article, title, thumbnail, and supporting files for factual support, reader usefulness, and consistency. Use for a publication-readiness check or a focused critique of a draft.
- ▌ X Article Studio · codejunkie99 bundleTurn an author's experience into an original, useful X article with a coordinated title and thumbnail. Use for the full workflow from an idea or voice dump to a reviewed draft and reusable files.
- ▌ X Article Titles · codejunkie99 bundleWrite or refine X article titles, opening promises, and accessible positioning. Use when choosing a reader outcome, comparing titles, or aligning the title with an outline and thumbnail.
- ▌ X Article Package · codejunkie99 bundlePackage an article and its supporting prompts, diagrams, or project files into a documented, reusable folder or GitHub repository. Use when readers need downloadable material or an agent-readable handoff.
- ▌ X Article Thumbnails · codejunkie99 bundleDesign article thumbnail concepts, generation prompts, and precise image revisions. Use for reference selection, readable workflow diagrams, visual style extraction, or coordinated title and thumbnail packaging.
- ▌
- ▌
- ▌ Caveman · codejunkie99 bundleUltra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".
- ▌
- ▌
- ▌ Cavecrew · codejunkie99 bundleWhen to delegate to `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit) or `cavecrew-reviewer` (diff review) instead of working inline or using `Explore`. Their output is compressed, so main context lasts longer.
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌ Agentic Context · codejunkie99Search and attach agent or subagent context across Claude Code, Codex, OpenCode, and Cursor when the user types @ or a tool mention.
- ▌ Agentic Stack Context · codejunkie99Use Agentic Stack to find agent or subagent context across Claude Code, Codex, OpenCode, and Cursor when the user types @ or a tool mention.
- ▌ Style Mimic · codejunkie99Use when the user wants to analyze an author's voice from samples and then write new content in that exact voice. Triggers include "write in my voice", "match this author's style", "ghostwrite in their style".
- ▌ Okr Builder · codejunkie99Use when the user wants to draft Objectives and Key Results for a team, individual, or company with measurable targets and confidence levels. Triggers include "write OKRs", "OKR planning", "set quarterly goals".
- ▌ Survey Analyzer · codejunkie99Use when the user wants to analyze survey results for findings, consensus, division, surprises, and actionable recommendations. Triggers include "analyze survey", "survey results", "what does this survey show".
- ▌ Data Interpreter · codejunkie99Use when the user wants plain-English interpretation of a dataset including patterns, surprises, and misleading aspects. Triggers include "analyze this data", "interpret these numbers", "what does this data mean".
- ▌ Email Drafter · codejunkie99Use when the user wants to draft a focused, action-oriented email and compare two tonal versions. Triggers include "draft an email", "write an email to", "compose an email".