Prepares for 1:1s with direct reports by pulling recent PR/ticket activity and prior 1:1 history into talking points that go beyond status updates, then logs what was discussed and tracks follow-ups and themes over time.
Plugin one-on-one-prep from marketplace tech-leadership in meaganewaller/tech-leadership-marketplace. Commands read from the repo's manifest — 1 month ago.
one-on-one-historySurfaces patterns across a person's 1:1 history -- follow-ups that have stayed open too long, topics that keep recurring, and growth goals they've stated more than once -- from ~/.tech-leadership/one-on-ones/<person-slug>.json. Use this skill when the user asks "what keeps coming up with [name]," "h
one-on-one-logLogs what was discussed after a 1:1 -- topics covered, follow-ups (open or closed), and any growth goals the person stated themselves -- to ~/.tech-leadership/one-on-ones/<person-slug>.json. Use this skill right after a 1:1 wraps, when the user says "log my 1:1 with [name]," "here's what we talked a
one-on-one-prepPrepares for an upcoming 1:1 with a direct report by pulling their recent PR/ticket activity and prior 1:1 history into a short prep doc with talking points that go beyond "what did you work on this week." Use this skill when the user says they have a 1:1 coming up, asks to "prep for my 1:1 with [na
Breaks a project into chunks and matches each one to a team member on purpose -- by stated skill level, growth fit, and current workload -- instead of defaulting to whoever is most senior or most available. Keeps a roster, flags chunks nobody is ready for, and tracks how assignments actually went.
3 skills
Checks a design doc for structural and completeness gaps before it goes to the team -- whether the problem statement is clear, real alternatives were weighed, failure modes and blast radius are addressed, rollout and rollback are planned, and ownership is named. Produces a findings table with draft questions to raise, not a line edit, and tracks which gaps keep recurring across a team's docs.
3 skills
Structures a blameless postmortem fast while details are still fresh -- capturing an incident timeline live, turning it into a full postmortem whose root causes are framed as system and process gaps rather than individual mistakes, and tracking recurring causes and never-closed action items across incidents.
3 skills
Rewrites a technical update -- a PR summary, an incident, an architecture decision, a sprint status -- for a specific non-technical audience, reframing it around business impact, risk, timeline, and cost without letting severity, uncertainty, or real caveats get smoothed away in the process. Keeps a profile of what each stakeholder cares about and a record of what they have already been told.
3 skills
Ranks technical debt by business impact rather than by how unpleasant the code is -- scoring blast radius, velocity drag, customer impact, cost of delay, and effort into a tiered Now/Next/Later list, then keeping a team-visible register and reporting on what actually gets paid down.
3 skills
TEMPLATE -- not a real plugin. Scaffolding used to validate the marketplace structure and all four tool adapters end to end. Copy this directory when starting a new plugin; don't install it as-is.
1 skill
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.
Design fluency for frontend development. 1 skill with 24 commands (/impeccable polish, /impeccable audit, /impeccable critique, etc.) and curated anti-pattern detection.
1 skill · 4 agents · hooks
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Statically analyze a local JS/Electron app you're authorized to study, with file+line evidence, and build an original reimplementation of what you find. Experimental. Phase 1: JS/Electron static analysis. Phase 2: native ELF/PE/Mach-O container inspection. Phase 3: .NET assembly metadata. Phase 4: EVM bytecode inventory. Phase 5: CUDA fatbin, cubin and PTX inventory. Parses, never executes. Dynamic analysis is a future phase, not yet implemented.
1 skill · 1 command · 1 agent
Data engineering for Apache Airflow and Astronomer. Author DAGs with best practices, debug pipeline failures, trace data lineage, profile tables, migrate Airflow 2 to 3, and manage local and cloud deployments.
35 skills · hooks
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
3 skills
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.