mattpocock-skills
claudeMatt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
See where a project stands, set it up by interviewing the engineer, read and write requirements, turn specs and designs into requirements, prove them with tests, review diffs against them, and run design review gates.
Plugin rqtk-skills from marketplace rqtk in wdoppenberg/rqtk. Commands read from the repo's manifest — yesterday.
rqtk-decomposeTurn a design into derived requirements in `.rqtk/`: a category per component, child requirements for one requirement and the level below it, interfaces and allocation. Run only when the user asks for it by name.
rqtk-design-reviewRun a design review gate (requirements review, PDR, CDR or readiness review) over the requirements in `.rqtk/`, for the whole set or one requirement and everything below it, and record the outcome in `.rqtk/reviews/`. Run only when the user asks for it by name.
rqtk-diff-reviewReview the changes since a fixed point against the requirements they touch: what changed, what needs re-verifying, and whether the code does what each statement demands. Run only when the user asks for it by name.
rqtk-initSet up `.rqtk/` for a new or existing project by interviewing the engineer about its stakeholders, needs, user requirements and system requirements, and record the answers with rqtk. Run only when the user asks for it by name.
rqtk-processThe systems engineering process for requirements in `.rqtk/`, from stakeholder needs and user and system requirements through architecture, decomposition, interfaces and allocation to verification, with a review gate closing each step. Use when starting a system, feature or subsystem, when decomposi
rqtk-requirementsRead and write the requirements, needs and stakeholders tracked in `.rqtk/` with the rqtk CLI. Use when a task changes behaviour a requirement governs, when the user mentions a requirement, need, stakeholder, a "shall" statement or an ID such as SYS-0001, when an interface (an `[interface]` table, a
rqtk-to-requirementsTurn the current conversation, a spec or a set of tickets into stakeholder needs and verifiable requirements in `.rqtk/`. Run only when the user asks for it by name.
rqtk-verificationProve requirements with tests. Link tests to verification activities with `verifies`, record test results with `rqtk verify`, and close out with `rqtk coverage --strict`. Use when implementing or changing behaviour a requirement governs, when a requirement is Suspect, Failed or Planned, or when the
rqtkShow where the requirements in `.rqtk/` stand in the systems engineering process, scope by scope, and recommend the next skill to run. Run only when the user asks for it by name.
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
AGENTS.md as project instructions, by one option. Under claude-md-or-agents-md a project with no instruction files of its own gets its AGENTS.md files instead: a prompt.context hook asks $.fs.ancestors for every AGENTS.md and .claude/AGENTS.md from the filesystem root down to the working directory and hands them to the engine as project instruction files, which it renders, announces and withholds from agents exactly as it does CLAUDE.md, skipping any file the engine already loaded by import or link; a tool.call hook on Read attaches the ones under the project root as the engine attaches a nested CLAUDE.md. Under claude-md-and-agents-md every AGENTS.md is loaded beside CLAUDE.md. Under managed-only the project's and the person's instruction files are dropped and the organization's managed ones kept. Under claude-md the engine's walk stands alone. claude-md-or-agents-md is the default.
Production-grade engineering skills covering every phase of software development: spec, plan, build, verify, review, and ship.
25 skills · 4 agents
Binary reverse engineering, malware analysis, firmware security, and software protection research for authorized security research, CTF competitions, and defensive security
4 skills · 3 agents
Long-term semantic memory for Claude Code, powered by OpenViking
5 skills · 1 command · 1 MCP server · hooks
Real-time statusline showing context usage, active tools, running agents, and todo progress. Always visible below your input, zero config required.
1 skill
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.