bdfinst

Conventions, anti-patterns, and meta-patterns for writing skills (and the shared agent/skill philosophy). Use when creating or editing a SKILL.md file, or when reviewing the agent-vs-skill separation. For the procedural workflow that generates a new agent file, use the agent-create skill (invoked by /agent-add).

Create new Claude Code sub-agent files following the official schema and token-efficiency budgets. Handles both review agents (JSON output, read-only tools, ≤ 40-line body) and team agents (prose output, action tools, ≤ 75-line body). Use when the user says "add an agent", "create a reviewer for X", "new team agent for Y", or when /agent-add is invoked. Validates against /agent-audit before writing. Updates the agent registry and CLAUDE.md after success.

Detect business logic reimplemented in multiple architectural layers. Builds a persistent computation-register.json by annotating non-trivial computation functions with structured semantic descriptions, then clusters entries to surface duplicate domain concepts. Runs in full-scan mode on first use, incremental (git-diff-based) mode on subsequent runs. Use when the user wants to find logical duplication that linters and diff-scoped review agents miss — the same domain calculation independently reimplemented across layers.

Pattern-table mapping from unified findings to regulatory citations (PCI-DSS, GDPR, HIPAA, SOC2). LLM edge annotator invoked only for llm_review_trigger=true rows.

Hybrid FP-reduction — joern when present, LLM fallback when absent. Six-stage rubric (Stage 0 + Stages 1-5) applied to every finding; emits the disposition register.

Declarative phase graph for /security-assessment. Phases run in fixed order with dependency enforcement; per-phase artifacts land in memory/ and feed the next phase.

Collaborative workflow for producing the four specification artifacts (intent, BDD scenarios, architecture notes, acceptance criteria) before any implementation begins. Use when starting any new feature or behavior change — do not write code until artifacts pass the consistency gate.

Initialize a new JavaScript project with ES modules, functional style, prettier, eslint, editorconfig, vitest, and gitignore. Use this skill whenever the user wants to start a new JS project, scaffold a Node.js app, create a new package, bootstrap a JavaScript repo, or says things like "init a new project", "set up a JS project", "create a new node app", "start a new frontend project", or "bootstrap a new package". Also trigger when the user asks to add standard JS tooling (linting, formatting, testing) to an empty or near-empty directory.

Audit and update the curated persona symptom pages (for-developers.md, for-agile-coaches.md, for-managers.md) when symptoms or anti-patterns are added, removed, or moved. Use this skill whenever new symptom or anti-pattern pages are created, when existing pages are deleted or reorganized, after running /cd-symptom-page or /cd-anti-pattern-page, or when the user asks to update the persona reading lists. Also use proactively at the end of any session that added or changed symptom content.

Generate a complete CD migration facilitator chatbot setup from the beyond.minimumcd.org site content. Use this skill whenever a user wants to create a chatbot, assistant, or guide that teams can use to navigate the CD migration journey — especially when they mention facilitating workshops, helping teams self-diagnose delivery problems, or guiding teams through continuous delivery adoption. Also use this when someone asks "how can teams use this site interactively" or "can we make a bot from this". Invoke proactively any time the user is thinking about team enablement, self-service CD coaching, or turning site content into an interactive guide.

Generate SVG diagrams for the CD migration documentation site (beyond.minimumcd.org). Use this skill whenever the user asks for a diagram, visual, workflow illustration, before/after comparison, or any figure to embed in a content page. Also use it when adding a diagram would meaningfully improve a content page being written or edited, even if the user has not explicitly asked for one. This skill is the single source of truth for the site's diagram color palette, layout conventions, and SVG output format.

Compare documentation against CD principles and practices from continuousdelivery.com and minimumcd.org, identifying gaps, misalignments, and improvement opportunities

Validate structure, voice, front matter, and cross-references for CD migration site content pages

Generate guide pages for the Migrate to CD section following the standard template

Generate symptom pages for the CD migration guide following the standard template

Review content files for unlinked glossary terms and add links to the glossary

Scaffold a new review agent from a description or URL. Use this whenever the user wants to add a new review agent, detect a new category of code issue, or says things like "add an agent for X", "create a reviewer for Y", "I want to check for Z in code reviews". Also use when given a URL to a coding standard or best-practices guide that should become a review agent.

Install a Claude Code plugin and register it in plugins.json so the full team can replicate the install. Use this whenever adding a new plugin to the project — it keeps plugins.json in sync with what is actually installed.

Apply correction prompts generated by /code-review. Use this whenever the user wants to apply, fix, or action the results of a code review — phrases like "apply the fixes", "fix the issues", "apply corrections", or after /code-review has run and produced a corrections/ directory.

Run all enabled review agents against target files. Use this whenever the user asks for a code review, wants feedback on their code, says "review my code", "check this before I PR", "what's wrong with this", "run the agents", or has just finished implementing a feature. Use proactively before commits and pull requests.

Audit code-review agents, skills, and hooks for structural compliance. Use this when adding or modifying any agent, skill, or hook file, or for a periodic health check of the toolkit. Trigger phrases: "audit the agents", "check compliance", "validate the skills", "are the agents correct", or any time agent/skill files change.

Run eval fixtures against review agents and grade results. Use this after adding or modifying a review agent, to validate detection accuracy, or when the user says "run the evals", "test the agents", "check for regressions", or "how accurate is the agent".

Run a single named review agent against target files. Use this when the user names a specific agent (e.g. "run security-review", "check for test issues", "run js-fp-review on this file") rather than wanting the full suite. Prefer this over /code-review when only one concern is relevant or speed matters.

Generate a compact summary of the most recent code review results and save it for future sessions. Use this at the end of a coding session after /code-review has run, or when the user says "summarize the review", "save the results", "generate a summary", or wants to preserve review context before closing a session.

Implement an approved feature file using ATDD workflow with test-first development

Analyze code with Semgrep for security vulnerabilities and code quality issues, then create a prioritized fix plan

Add a new calculated metric to the VSM dashboard with test-first development

Create a new React component following project conventions with PropTypes and test attributes

Create a new feature file for ATDD workflow - must be done BEFORE any implementation

Add a new type of process step to the VSM builder with custom visualization

Create or run simulation features for analyzing work flow through value streams