MrBogomips
UserClaude Code plugin marketplace — SOW writing, PERT estimation, devcontainers, and more
Categories
Indexed Skills (23)
devcontainer-generator
Generate devcontainer setups by scanning CWD for tech stack and infra services. Triggers on devcontainer, dev container, devcontainer.json, development container, containerized development, VS Code Remote Containers, GitHub Codespaces. Produces devcontainer.json, Dockerfile, Docker Compose, post-create scripts, firewall rules, and DEVCONTAINER.md summary. Uses an 11-step interactive workflow (Steps 0–9 with Step 1b for host credential sharing).
harness-review
Assess an existing agentic harness — read-only. Use to review, audit, or assess a harness, to judge how well its skills and agents are actually used, to check drift between the files and the CLAUDE.md record, or to validate that skills trigger and agents wire up. It produces a prioritized review context that hands off to harness-setup, and writes nothing. To build or change a harness, use harness-setup. Not for reviewing ordinary code or a pull request (that is code review).
harness-setup
Build, extend, and maintain a project's agentic harness — the agents, skills, and orchestrator under .claude/. This skill writes files. Use it to set up, scaffold, extend, rebuild, or sync a harness, to add or change an agent or skill, or to apply a review context from harness-review; on request it also discovers and registers fitting MCP/plugin tools. For read-only assessment of an existing harness, use harness-review — this skill is the writer, that one is the reader. Not for authoring a single standalone skill or plugin (use plugin-dev or skill-creator), or one-shot automation recommendations (use claude-code-setup). Not for choosing a project's spec-driven development system — use spec-advisor.
spec-advisor
Detect whether a software project lacks a spec-driven development system and, if so, advise which one fits (GitHub Spec Kit, OpenSpec, BMAD-METHOD, Agent OS, Taskmaster, AWS Kiro, ADR tooling) and delegate setup to that system's own installer. Use when setting up a project's spec or planning process, when asked which spec system or SDD framework a project should use, when adopting spec-driven development, or when harness-setup detects a software project with no spec system. Scans first for any existing spec or ADR registry and stays out if one is present. Does NOT author specs itself (the installed system owns that), does NOT build the .claude/ agent harness (that is harness-setup), and does NOT create Claude Code components (that is plugin-dev or skill-creator).
plantuml-authoring
Author PlantUML diagrams (UML, C4, ER, ArchiMate, MindMap, WBS, Gantt, Salt, JSON/YAML, nwdiag family). Use when creating, restructuring, or choosing a type for a .puml/.plantuml/.iuml file, when setting up PlantUML project configuration, or when adapting diagrams to a render target (web/docx/pdf/pptx). For rendering to image, use plantuml-convert.
plantuml-bootstrap
Set up a project for PlantUML authoring — creates `## PlantUML Policy` in CLAUDE.md and materializes `.plantuml/` from the policy. Use when a project has `.puml` work but no policy, or to migrate an existing `.plantuml/` back to a policy (reverse mode). Accepts `mode=bootstrap` (default) or `mode=reverse`.
plantuml-migrate
Apply a Policy change across all `.puml` files in the project (theme switch, target add/remove, brand colors update). Use after editing `## PlantUML Policy` in CLAUDE.md. Detects manual edits to `.plantuml/_*.puml` and halts to prompt before overwriting. Backs up `.plantuml/` before any destructive write.
plantuml-validate
Render or check `.puml` files for all declared targets and verify they produce stable output against committed baselines. Use to catch syntax breakage and rendering regressions. Accepts `mode=check|bless` (default `check`) and `level=checkonly|svg-hash|png-perceptual` (default `checkonly`).
plantuml-advisor
Advise on diagram-type fit for a `.puml` — confirm the current type is right, or suggest a better one with rationale and a migration sketch. Use when an author is unsure whether class, component, sequence, or another type fits the intent best.
plantuml-lint
Check `.puml` files for PlantUML Policy drift, broken includes, and invariant violations (hardcoded colors, missing `_base.puml`, filename≠title, duplicated skinparams). Use when reviewing diagrams for compliance.
plantuml-review
Review a single PlantUML diagram for clarity, type-fit, layout, and readability. Use when an author wants qualitative feedback before merging or sharing.
hr-help
Plugin mentor and HR advisor — explains methodology, guides skill usage, answers HR best practice questions, and references corporate context from memory. Adapts interaction depth to user expertise: direct answers for experts, procedural guidance for practitioners, Socratic coaching for newcomers. Three knowledge rings: Ring 1 (plugin usage — which skill when, pipeline flow, inputs/outputs), Ring 2 (HR best practices — STAR, behavioral interviewing, bias reduction, competency frameworks), Ring 3 (corporate context — memorized templates, matrices, policies). Does NOT generate documents or make hiring decisions. Use when the user says 'how do I use', 'help with interview', 'what skill should I', 'explain the methodology', 'come funziona', 'aiuto colloquio', 'come si usa', 'perche', or asks any question about the HR interview workflow.
interview-close
Produce standardized post-interview evaluations with competency scoring, seniority classification, and hiring recommendations. Guides interviewers through constructive feedback by converting raw impressions into evidence-backed evaluations. Reads interview-notes templates, asks probing questions per competency, detects potential bias patterns, and maps scores to a seniority/skill matrix (corporate or proposed). Supports corporate template adaptation. Invokes compliance-check validation before output. Use when the user says 'close interview for', 'evaluate candidate', 'interview evaluation', 'chiudi colloquio', 'valutazione candidato', 'scheda valutazione', 'fill evaluation', or mentions completing a candidate assessment after an interview.
interview-prep
Prepare technical interviewers and department evaluators for candidate interviews. Produces three output files: a position assessment analyzing candidate fit (strengths, gaps, risks), a question suggestions document with STAR-method behavioral questions (including rationale, good/excellent answer examples, and follow-up probes per competency), and a minimal interview-notes template for capturing impressions during the interview. Performs deep CV-vs-JD analysis across 4-6 competencies. Invokes compliance-check validation before output. Use when the user says 'prepare interview for', 'interview questions for', 'prepare me for interviewing', 'preparazione colloquio', 'domande colloquio per', 'prepara domande per', or mentions preparing for a candidate interview.
job-description
Write professional job descriptions for both technical and non-technical positions. Uses competency-based framework for technical roles (identifying 4-6 core competencies with proficiency levels) and outcome-based framework for non-technical roles (action + object + purpose). Checks inclusive language, flags requirements inflation (>8 requirements), and invokes compliance-check validation before final output. Auto-detects conversation language for Italian/English output. Integrates with **~~knowledge base** for existing JD templates. Use when the user says 'write a job description', 'create a JD', 'job posting for', 'descrizione del lavoro', 'annuncio di lavoro', 'scrivi annuncio', or mentions creating a position listing.
pre-screening
Generate pre-filter questionnaires for HR recruiters to send to candidates or use as scripts during phone/video screening calls. Performs CV-vs-JD gap analysis to identify areas needing clarification. Supports two delivery modes: async (candidate self-service) and live (interviewer script with follow-up probes and note-taking). Covers 5 categories: logistics, experience alignment, motivation, competency probes, and candidate questions. Max 12 questions per questionnaire. Invokes compliance-check validation before output. Use when the user says 'screening questions for', 'pre-filter questions', 'candidate screening', 'phone screen script', 'domande di prescreening', 'domande filtro', or 'prepara screening'.
kaizen-engine
Recursive improvement loop engine inspired by karpathy/autoresearch. Orchestrates continuous improvement via Sequential Thinking MCP with 8-phase iterations (MEASURE, ANALYZE, HYPOTHESIZE, PROPOSE, APPLY, VERIFY, DECIDE, LOG). Supports greedy and multi-objective ratcheting strategies with configurable autonomy levels. Use when the user says 'run kaizen', 'kaizen loop', 'improve', 'optimization loop', 'continuous improvement', 'recursive improvement', 'iterative optimization', 'run improvement profile', or wants to iteratively improve code, configuration, or processes against measurable KPIs. Also activates when user references a specific profile name like 'claude-code-usage', 'code-refactoring', or 'process-improvement'. Requires **~~sequential-thinking** connector.
kaizen-profile-designer
Interactive workflow to create custom kaizen improvement profiles. Guides users through KPI definition, data source identification, mutation scope selection, autonomy configuration, and profile validation. Use when user says 'create kaizen profile', 'design improvement loop', 'new kaizen profile', 'custom profile', 'custom kaizen', 'define improvement target', or wants to create a new improvement loop for a domain not covered by the bundled profiles.
kaizen-report
View improvement history and KPI trends from kaizen runs. Reads .kaizen/runs/ audit trail to show cross-run improvement trajectories, diminishing returns detection, and formatted KPI reports with delta tables. Use when user says 'kaizen report', 'kaizen history', 'improvement history', 'show kaizen results', 'KPI trends', 'how is improvement going', 'kaizen status', or wants to review past improvement loop outcomes.
pmo-pert-estimate
Create PMI-compliant PERT three-point estimation workbooks with WBS, resource plan (role × week PD), risks, and summary sheets. Produces fully automated Excel with live formulas, PD-everywhere effort, PMI-correct Management Reserve, configurable PM/DevOps overhead, and explicit calendar duration. Triggers: 'create PERT estimate', 'generate WBS estimate', 'PMO estimation', 'three-point estimate', 'PERT analysis', 'project estimation', 'stima PERT', 'stima progetto'
sow-estimate
Extract WBS, roles, and risks from a Statement of Work and bridge to PERT three-point estimation. Parses SOW sections into PERT-compatible structures, invokes the pmo-pert-estimate skill for economics and timeline, then backfills the SOW's Economics and Schedule sections with PERT results. Use this skill whenever the user wants to estimate a SOW, generate SOW economics, bridge a SOW to PERT, calculate project costs from a statement of work, or mentions 'stima SoW', 'SOW economics', 'cost estimation from SOW', or 'generate economics for proposal'.
sow-review
Review and score Statement of Work documents across 8 quality dimensions with adversarial analysis. Produces a structured scorecard (1-5 per dimension), critical issues list, improvement recommendations, and adversarial challenges from both client and vendor perspectives. Use this skill whenever the user wants to review a SOW, check SOW quality, do an adversarial review of a statement of work, validate a proposal, audit a capitolato tecnico, or mentions 'revisiona SoW', 'SOW quality check', or 'review proposal document'.
sow-write
Write professional Statements of Work (SOW) in full (15-section enterprise) or summary (9-section contract extraction) mode. Auto-detects language from input documents, supports English and Italian with language packs. Produces structured markdown with optional research subagents for domain gaps. Use this skill whenever the user wants to write a SOW, create a statement of work, draft a proposal, write a capitolato tecnico, prepare an offerta, or mentions 'scrivi SoW'. Also triggers for 'project proposal', 'scope document', 'service agreement draft', or any request to formalize project scope into a deliverable document.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.