fagemx
UserLocal, tamper-evident ledger for coding agents — decisions that survive sessions, coordination that survives agents. Works with Claude Code, Cursor, Codex, OpenClaw, and any MCP client.
Categories
Indexed Skills (42)
edda-workflow
Post-task notification and draft approval via edda (decision memory). Use when: (1) a coding agent finishes and you need to report results, (2) checking for pending edda drafts that need approval, (3) user says 'approve', 'reject', or asks about draft status. NOT for: recording decisions (use `edda decide` directly), querying past decisions (use `edda ask`), or session context (handled automatically by edda bridge).
edda-conductor
Multi-phase AI plan orchestration via edda-conductor. Use when: (1) user wants to run a multi-phase plan, (2) checking conductor status or progress, (3) handling blocked/failed phases (retry, skip, abort), (4) generating plan.yaml from natural language. NOT for: single-task execution (use coding-agent), decision recording (use edda decide), session context (handled by edda bridge).
agent-browser
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
code-quality
Deep code review and quality analysis for the edda Rust project
commit
Complete pre-commit workflow - run quality checks (format, lint, test) and validate/create conventional commit messages
health-check
Periodic codebase health assessment — 5 dimensions, scorecard, trend tracking
pr-check
Monitor PR CI pipeline, auto-fix issues, and loop until all checks pass
pr-review-loop
self-check before requesting independent review; never a merge verdict
pull-request
PR lifecycle management - create PRs with proper commits, merge with validation, and manage PR comments
regression-guard
Systematic scan → classify → batch fix → add automation to prevent regression
tech-debt
Technical debt management - scan Rust codebase for bad smells and create tracking issues
testing
Comprehensive testing patterns and anti-patterns for writing and reviewing tests
tracking-issue
Analyze complex problems structurally — map actors, find root causes, create tracking issue with parallel task decomposition
skill-alias
Create command aliases for skills with arguments
arch-spec
Use when a concept needs a multi-file design dossier (overview, canonical form, schemas, rules, APIs, slices, demo paths) before it's stable enough for project-plan task decomposition. Not for single-file RFCs, ADRs, or already-stable scopes ready for engineering.
code-review
Review merged code, commit ranges, or codebase paths for correctness, security, architecture, and test risk; use pr-review for open PRs
coord-handoff
Clean handoff when finishing multi-agent work — summarize, decide, unclaim
coord-orchestrate
Use when coordinating two or more sessions on parallel implementation work as the controller — assigning bundles, briefing workers and a verifier, adjudicating mid-flight, and closing with dual review
coord-request
Detect changes affecting peers and send coordination requests
coord-review
Use when auditing multi-session coordination or reviewing a delivery candidate before PR or merge
coord-sync
Sync with peers before starting multi-agent work — see claims, recorded decisions, suggest scope
ground-check
Check if codebase supports a planned task — what's ready, what's close, what's missing
intel-scan
Dual-agent PR intelligence scan — discover contribution opportunities from any repo's PR history
issue-action
Continue working on GitHub issue from conversation context
issue-compact
Consolidate GitHub issue discussion into clean body for handoff
issue-create
Create GitHub issues from conversation context (general, bug reports, or feature requests)
issue-intake
Use when the ready-issue queue is low or a delivery wave is closing, when a defect/finding surfaces mid-session (runtime failure, review discovery, repeated manual step), or when deciding whether an observation deserves a GitHub issue. Also use when authoring any issue body.
issue-pipeline
End-to-end issue pipeline: plan → implement → review → merge. Dispatches parallel sub-agents with worktree isolation. Usage: /issue-pipeline 566 567 568 [--skip-plan] [--no-merge]
issue-plan
Start working on GitHub issue with deep-dive workflow (research, innovate, plan phases)
issue-scan
Scan codebase, discover work, propose well-scoped issues
parallel-wave
Use when two or more ready issues are about to be delivered serially, when authoring or restructuring a conduct wave plan, or when deciding whether concurrent implementation lanes are safe on this workstation (worktree, build lane, review dispatch, merge ordering).
path-forward
Find the most unblocking next step given current codebase state and goals
plan-validate
Validate a plan for gaps by cross-referencing against actual code, call chains, constraints, and test edge cases
project-plan
Generate a structured planning pack (tracks, tasks, contracts, validation) for any project
project-principles
Core architectural and code quality principles that guide all development decisions in the edda project
skill-craft
Create high-quality Claude Code skills following edda patterns
skill-test
Test a Claude Code skill — verify it runs, references exist, output is sane
spec-review-modes
Review architecture specs, RFCs, API docs, design docs, decision-system docs, or any multi-file technical spec stack using three explicit reading modes: (A) quick overview, (B) strict spec audit, and (C) product/architecture critique. Use when the user asks to 看 spec, review docs, 掃一遍架構, 幫我抓矛盾, 做 spec 審查, or wants structured feedback on boundaries, type consistency, lifecycle ownership, API seams, product thickness, or whether a spec feels complete vs actually useful.
verifiable-goal-loop
Convert broad goals, long-running projects, learning plans, research tasks, repo modernization, product builds, writing projects, operations work, portfolio prep, or job-search preparation into a proactive verifiable active goal run operating loop. Use when the user wants goal.md/state.md/backlog.md/verifier.md, external stop conditions, sprint/cycle planning, durable progress across long tasks, skill/tool routing, command prompts, autonomy rules, or a reusable method that prevents passive one-question-at-a-time agent behavior and vague self-graded completion.
edda-release
Release Edda across crates.io, GitHub assets, install.sh, and Homebrew without channel drift
pr-review
PR review: concise, direct, actionable
dispatch
RETIRED (GH-661) — this skill described a dispatch server from another project that does not exist in this repo. Dispatching a lane here is the `edda dispatch` CLI; see docs/guides/operator-runbook.md §三／§四 and the fleet.lane-launch / fleet.lane-dispatch / fleet.codex-dispatch decisions (`edda ask <key>`).
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.