fpl-skills

Plugin fpl-skills from marketplace ForgePlan-marketplace in ForgePlan/marketplace. Commands read from the repo's manifest — 12 days ago.

Skills (44)

• agent-advisor

  Recommends the right canonical agent (or set of agents) for a described engineering task. Consults the `mm-agent-selection` mental model in Hindsight when available, falls back to embedded knowledge of the 17 forgeplan-aware canonical agents + their CRUD-R-A profile matrix (PRD-026). Returns a struc

• agent-fetcher

  Methodology: Cross-marketplace agent/skill suggestion (suggest-only, NO auto-install). EN: When canonical 17 forgeplan-aware agents don't fit the task, searches installed marketplaces (~/.claude/plugins/marketplaces/) for matching agents/skills. Ranks by keyword overlap + trust tier + specificity. S

• audit

  Multi-expert audit of code, architecture, or a finished feature — at least 4 parallel reviewer agents, each with a specialization (logic, architecture/SOLID, typing, security; optionally tests, backend patterns, frontend, task-completion). Each runs its own checklist. Output is cross-validation, sco

• autorun

  Autonomous orchestrator for green-light / overnight execution. Takes one task and runs the full engineering cycle (research → plan → sprint → audit → report) end-to-end without approval checkpoints. Uses TeamCreate with explicit file-ownership and blockedBy edges between waves, resolves blockers via

• bootstrap

  Deploys the author''s Claude Code starter scaffold into a new or existing project — creates a CLAUDE.md from the template, a guides/ folder with author guides (Git Flow, CLAUDE.md best practices), and guides/INDEX.md. Use when the user starts a new project and wants the standard Claude Code baseline

• briefing

  Morning briefing on tasks and messages — collects overdue, due today, @mentions, unread chats, and project stats from any available task tracker (Orchestra MCP, Linear MCP, Jira MCP, GitHub Issues) or from local TODO files. When forgeplan is reachable, augments with **MCP-first** artifact signals (`

• conformance-vectors

  The OPTIONAL `## Conformance Vectors` enrichment for spec-driven development (ADR-008): a frozen, hash-pinned, language-neutral conformance corpus that is the SOLE behavioral oracle for an implementation, plus a per-language harness and a cross-language equivalence gate. Use when a SPEC targets MORE

• cross-runtime

  Wire this project's Claude Code skills and commands into every other AI runtime installed on the machine — Codex, OpenCode, OMP, and any agents.md client. Detects which runtimes are present, reports what each one can and cannot see, and creates the missing links. Use when a skill or command "does no

• ddd-decompose

  Interview-driven Domain-Driven Design decomposition skill. Walks through identifying bounded contexts, aggregates, ubiquitous language, and domain events for a system or new feature. Outputs a DDD context map (Markdown + Mermaid) plus optional forgeplan artifacts (Epic + per-context PRDs + Spec). Pa

• decay-watch

  Scan all active ADR artifacts for fired Revisit Triggers (Evidence Decay). Reports which triggers fired, which need human verification, which are stale because the ADR uses pre-Sprint-Z2 prose format. Use periodically (weekly + at session start) — keeps decisions from quietly going stale. Triggers:

• decision

  Fast path for recording a routine decision as a light ADR (200-400 words, 6-section DDR shape). Use when you just chose one approach over another and want to capture the why before it slips out of memory. NOT for big architecture — that's `adr-architect` agent territory. Triggers: "record decision",

• diagnose

  Disciplined diagnosis loop for hard bugs and performance regressions. Six phases — build feedback loop → reproduce → hypothesise → instrument → fix + regression test → cleanup + post-mortem. Phase 1 (the feedback loop) is the entire skill — everything else is mechanical once you have a fast determin

• discover-product

  Interview-driven product-discovery skill that bridges JTBD / Lean Startup / Double Diamond discovery into the forgeplan artifact graph (ADR-023 D2, routing-map row 10). Double Diamond (Discover -> Define -> Develop -> Deliver) is the INTERNAL walk the skill performs, not a separate methodology skill

• do

  Meta-orchestrator — takes a natural-language task, classifies it (research / docs / feature / review / bug / refactor / status), builds a pipeline from other skills (research → write-doc → wave-sprint → audit), shows the plan, and executes with approval checkpoints. Use when the user wants "do X" wi

• estimate

  Estimates effort and risk for a named artifact at the `estimate` stage of the canonical pipeline: runs forgeplan estimate for per-item complexity and hours by grade, reports the confidence figure with the reasons behind it, and pairs the number with a current R_eff snapshot so the estimate is read a

• forge-cleanup

  Methodology: 3-tier pipeline self-healing (AUTO / ADI / USER classification per PRD-032 Sprint D; extended with 4 anomaly kinds in Sprint F PRD-034 + 1 anomaly kind in Sprint M PRD-039 = 9 total). EN: Explicit draft sweep skill for marketplace workspaces. Scans all draft artifacts via mcp__forgeplan

• forge-heal

  Methodology: Layer 4 heal-or-task loop (PRD-074 brick 2 / RFC-020) — propose-not-silent 3-tier dispatch (AUTO / ADI / USER per PRD-032) of the Finding[] that /forge-insight + the insight-watchdog already surfaced. Consumes the frozen RFC-019 Finding contract; never re-detects or re-classifies. EN: A

• forge-insight

  Methodology: insight layer over forgeplan anomaly detection (PRD-074 Layer 2 + don't-forget ledger; RFC-019 brick 1). Deterministic known-noise filter + on-demand semantic digest + idempotent NOTE-013 findings-section writer. Complements the silent SessionStart insight-watchdog hook (same filter, au

• forge-report

  Structured report formats for Claude — card-based, human-readable, no ASCII frame noise. Use when finishing a multi-step task (≥5 tool calls, ≥3 files modified, multi-task TaskList, or cross-system effects like git push/PR/deploy). Output-only skill, no forgeplan dependency (per PRD-022 Tier B): rea

• forgeplan-cookbook

  Live reference for the 66 mcp__forgeplan__* MCP tools and the 82 forgeplan CLI subcommands shipped in forgeplan 0.32.1. Agents and humans consult this skill when they know what they want to do (create an artifact, score a graph, dispatch sub-agents, detect anomalies) but don't yet know which tool na

• fpl-init

  One-command project bootstrap for the ForgePlan ecosystem. Probes the forgeplan CLI, runs `forgeplan init`, wires `.mcp.json` and `.claude/settings.json`, then chains `/bootstrap` (universal CLAUDE.md template) and `/setup` (docs/agents/ wizard) so a fresh repo is fully wired in one shot. Recommends

• gate-check

  Runs the quality gate between pipeline stages for a named artifact: reads the depth, loads thresholds from .forgeplan/quality-gates.yaml (falling back to the shipped template), executes validate + score + fgr per-artifact, runs gaps + blindspots as workspace advisories, and returns PASS or FAIL with

• gh-project

  Project-agnostic GitHub Projects v2 integration. Reads per-project config from .forgeplan/state/gh-project.yaml; never hardcodes project numbers. Five operations — init (one-time setup), add-pr (current/given PR → board), link-prd (Standard+ PRD → matching GH issue + board entry with Forgeplan-ID fi

• incident

  Runs a live incident end to end in two phases (ADR-024 wave 2, smith row 12): Phase 1 — the fire, Incident Command System chain with methodology overhead suspended, hotfix under ICS authority, smoke before ship; Phase 2 — the blameless post-mortem, PROBLEM artifact from the post-mortem template, pos

• methodology-check

  For any artifact ID, report which of the EPIC-001 4-layer pipeline layers (S10 FPF design, S11 BMAD quality gate, S12 OpenSpec structure, S13 Forgeplan automation) are satisfied and which need work. Also checks C4 coverage for ≥3-module architectural decisions. Returns a per-layer score 0-2 + aggreg

• migrate-from-dev-toolkit

  One-command migration from dev-toolkit to fpl-skills. Probes installed plugins, scans CLAUDE.md and project docs for /dev-toolkit:* references, offers Mode A (side-by-side, zero risk) or Mode B (clean cut), executes the steps from docs/MIGRATION-DEV-TOOLKIT-TO-FPL-SKILLS.md. **One-time bootstrap, no

• progress-dashboard

  Methodology: Live state renderer (read-only snapshot, no new event system). EN: Renders structured snapshot of running orchestrator state — current sprint, phase, wave, agents in flight (via forgeplan_claims), TaskList progress, forgeplan_health, recent EVID, files modified count, ETA estimate. Read

• project-agent-scaffold

  Methodology: Project-scoped agent generation via tech-stack detection. EN: Detects project tech stack from package manifests (package.json, Cargo.toml, go.mod, pyproject.toml, pom.xml, mix.exs, Gemfile, composer.json, Package.swift, pubspec.yaml) + secondary signals (tailwind.config.*, next.config.*

• refine

  Interview-driven refinement of a plan, design, or proposal. Walks the user down each branch of the design tree one question at a time, sharpening fuzzy terminology, surfacing contradictions against the existing domain model, stress-testing edge cases with concrete scenarios, and updating CONTEXT.md

• research

  Deep multi-agent research on a topic — parallel scout agents cover source code, design docs/RFCs, TODO/status files, reference implementations, persistent memory. Each agent gets a bounded domain and its own context. Use when the topic is large (auth chain, competitor comparison, gap-analysis for a

• restore

  Restores working session context — collects fresh info on the current branch, recent commits, uncommitted changes, stashes, and (if available) decisions from a memory system. When forgeplan is reachable, probes **MCP-first** (`mcp__forgeplan__forgeplan_health` + `forgeplan_list` + `forgeplan_blocked

• rfc

  Creates, reads, and updates RFCs (Request for Comments) / design docs — structured documents for architectural decisions via **MCP-first** path (`mcp__forgeplan__forgeplan_new` + `forgeplan_update` + `forgeplan_link` + `forgeplan_validate`) with CLI fallback when MCP is not connected, or plain markd

• riper

  RIPER methodology orchestrator — Research → Innovate → Plan → Execute → Review — the FOURTH instance of the AD/AID-PDLC sub-cycle contract (ADR-010 / RFC-018). Drives a bug / scoped change / investigation in an EXISTING active system through five modes, MAIN-SESSION-orchestrated (hook-gate=No → no d

• setup

  Interactive wizard that configures CC-templates for the current project. Asks about the issue tracker, build/test commands, docs/RFC/TODO paths, and domain glossary; writes answers to `docs/agents/*.md` and optionally creates a starter `CONTEXT.md` in the project root. All other skills (research, au

• shape

  Interview-from-scratch skill that turns a raw idea into a structured PRD draft. Asks one focused question at a time, sharpens the problem statement and goals, surfaces target users and constraints, and writes the result as a forgeplan PRD draft via **MCP-first** path (`mcp__forgeplan__forgeplan_new`

• smith-bootstrap

  Greenfield-project onboarding skill. For a fresh repo (no CLAUDE.md, no forgeplan, no AGENTS.md), runs an active infrastructure setup (plugin gate → forgeplan MCP auto-wire via `forgeplan mcp install` → Hindsight detection + env-var remap guidance → `.claude/hooks/` baseline bundle → reload + verify

• smith-plan

  Task-planning skill. Takes a SPECIFIC TASK as input (e.g., "refactor auth module", "ship payment service", "audit security of API gateway"), classifies it into one of 14 routing-map contexts, applies the matching methodology, and renders a structured Plan using templates/smith-plan.md. Dispatches th

• smith-routing

  Educational routing skill. Walks the user through smith's methodology routing matrix without committing to a specific task. Use to learn "when do I apply BMAD vs SPARC?", "what methodology for brownfield?", "explain the bug fix workflow". Pulls from routing-map.md (14 contexts + 33 methodology cards

• smith

  Master-orchestrator entry-point. Reads project state (forgeplan_health, memory_recall, git), classifies context (1 of 14: greenfield / brownfield / feature / bug-fix / refactor / decision / audit / discovery / tech-debt / incident), applies methodology routing matrix, returns a structured Plan and r

• spec-author

  Author a forgeplan SPEC in the spec-driven LIGHT pipeline (OpenSpec/SpecKit-style on the SPEC kind) — iterate until "ideal", then freeze for implementation. Produces a SPEC where `## Requirements` (`### Requirement` + `#### Scenario` GIVEN/WHEN/THEN) is the PRIMARY, frozen, reviewed oracle, plus `##

• sprint

  Wave-based execution of a feature/task by a multi-agent team — research → wave plan (5-8 agents in 2-5 waves) → approval → wave-by-wave teammate spawn via TeamCreate. Two modes — full sprint (with research phase) and lightweight wave (uses current chat context). Each wave is independent parallel wor

• supersede

  Walk the complete supersede-ADR workflow with mandatory OpenSpec delta-spec discipline. Reads the old ADR, verifies it is active, computes the user's intended delta, creates the new ADR using the adr-supersede.md template (all four delta sections: ADDED / MODIFIED / REMOVED / UNCHANGED), links super

• team

  Foundational skill for launching multi-agent teams — TeamCreate vs parallel Task() (sub-agents), team-lead vs teammate roles, file ownership, dynamically spawning new agents for additional work, cleanup. Used as the base layer by other multi-agent skills (research, audit, sprint, wave) or directly w

• wrap

  Closes a forgeplan cycle at the `wrap` stage. At Deep and Critical depth it runs the real reconciliation — forgeplan drift, forgeplan stale, forge-heal and a link audit — and records their actual output in a REFRESH artifact with a ready verdict, per ADR-020. At Standard and Tactical it runs the sam

Subagents (1)

• dev-advisor

  EN: Proactive development advisor that monitors your workflow and suggests best practices. HOOK-triggered background agent — surfaces after file edits to recommend audits, tests, security checks, and agent-pack specialists. Non-blocking: all suggestions are optional and session-deduplicated. RU: Про

Hooks (8)

• SessionStart

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/session-start.sh"

• SessionStart

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/forge-report-session-start.sh"

• SessionStart

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/decay-reminder.sh"

• SessionStart

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/insight-watchdog.sh"

• PreToolUse

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/safety-hook.sh"

• PostToolUse

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/test-hint.sh"

• PostToolUse

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/forge-report-counter.sh"

• UserPromptSubmit

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/prompt-router.sh"

Similar plugins