bdfinst

Create and manage Architecture Decision Records using the npryce adr-tools CLI. Use when the user asks to "add an ADR", "record this decision", "create an ADR", "supersede ADR N", "link ADRs", "generate the ADR table of contents", or any request involving the…

Produce a written design document in docs/specs/ with user approval before planning begins. Use this skill during the Research phase when a feature request, architectural change, or non-trivial task enters the pipeline. Ensures misunderstandings are caught…

Collaborative workflow for producing the three specification artifacts (intent, architecture notes, acceptance criteria) that describe a change and its goals before any implementation begins. Its value is resolving ambiguity with a human before build starts —…

Build or refresh the project's ubiquitous language glossary — one markdown file per business concept at `.plans/domain/<Concept>.md` plus a `_index.md`. Mines grep-based signals (class names, enum values, interface names, domain-event names, BDD scenario…

Execute an approved implementation plan in small per-behavior batches. Reads the plan, implements each step one behavior at a time in the Code-First Small Batches cadence with a refactor on every green, runs inline review checkpoints, and produces…

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…

Decide which agents and skills to load for a given task. Use at the start of every task to select the minimum viable context load, calculate the token budget, and stay below the 40% utilization ceiling.

Compress or split off context for another session to pick up. Use to compress conversation history when context utilization approaches 40% (continue mode), or to split off a distinguishable out-of-scope side-task to an independent session (fork mode) — write…

Generate anti-pattern pages for the CD migration guide following the standard template

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, rewrite, or draft content pages applying technical writing principles for clarity, scannability, and reader experience

Audit and improve the CD migration site for discoverability, self-guided learning, and audience-appropriate navigation for developers and managers

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

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…

Run the quality gate (tests, build, lint) then open a pull request. Use when the user says "create a PR" or "open a PR".

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

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

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

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…

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…

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…

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…

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…

Run Semgrep static analysis on target files and return structured findings. Use this when the user wants static analysis, SAST scanning, or security scanning — phrases like "run semgrep", "scan for vulnerabilities", "static analysis on this code", or as a…

Scaffold a new plugin inside an existing marketplace — the shipped dir skeleton, plugin.json, install.sh with the Git-Bash guard, settings.json, and CLAUDE.md; then register it in the catalog and in release-please packages with the catalog extra-files sync.…

Audit a marketplace (or a single plugin) — run the shipping-hygiene sensor, structural checks (every catalog entry has a dir, every dir has a manifest, versions in sync), and the portability sweep. Reports findings and offers fixes. Use to validate a…

Generate the gated SessionStart install hook plus cloud-setup.sh and a "use skills directly" fallback so the marketplace is usable in Claude Code web/cloud sessions. Use to make a marketplace cloud-aware.

Scaffold a new Claude Code plugin-marketplace monorepo — catalog, repo-root tests/scripts/docs trees, CI workflows, release-please config, dev-setup, the hygiene sensor, and a root CLAUDE.md. Use when starting a fresh marketplace repository.

Run shellcheck -x over every shipped and dev shell script, flag bash-4/GNU-only constructs, verify env-bash shebangs, and check that each install.sh has the Git-Bash-on-Windows guard. Use to validate cross-platform portability (macOS bash 3.2 / BSD / Windows…

Wire release-please with one package per plugin and the marketplace.json extra-files jsonpath sync, so plugin.json, the release tag, and the catalog entry can never drift. Use to set up or repair automated versioning + catalog sync.

Run this project's pre-PR quality gate (Vitest, oxlint/ESLint, Prettier, code review) and then create a pull request with a structured summary. Use when the user says "create a PR", "open a PR", "submit for review", or "I'm done with this feature".

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