cristoslc
- 63 skills
- 0 followers
- 9 hours ago last updated
- ▌
- ▌ Swain Do 2 · cristoslc bundleBootstrap, install, and operate an external task-management CLI as the source of truth for agent execution tracking (instead of built-in todos). Provides the abstraction layer between swain-design intent (implementation plans and tasks) and concrete CLI commands. MUST be invoked when any implementation-tier artifact (SPEC, STORY, BUG) comes up for implementation — create a tracked plan before writing code. Optional but recommended for complex SPIKEs. For coordination-tier artifacts (EPIC, VISION, JOURNEY), swain-design must decompose into implementable children first — this skill tracks the children, not the container. Also use for standalone tasks that require backend portability, persistent progress across agent runtimes, or external supervision. Use this skill whenever the user asks to track tasks, create an implementation plan, check what to work on next, see task status, manage dependencies between work items, or close/abandon tasks — even if they don't mention "execution tracking" explicitly.
- ▌ Swain Help 2 · cristoslc bundleContextual help and onboarding for the swain skill ecosystem. Use when users ask about swain — what skills exist, how to use them, what artifacts are available, how workflows connect, or when they need a quick reference. Also invoked after swain-init to orient new users. Triggers on: 'how do I...', 'what is...', 'help', 'what can swain do', 'show me the commands', 'I'm confused', 'where do I start', any question about swain skills, artifacts, or workflows, and after project onboarding completes.
- ▌ Swain Init 2 · cristoslcOne-time project onboarding for swain. Migrates existing CLAUDE.md content to AGENTS.md (with the @AGENTS.md include pattern), verifies vendored tk (ticket) for task tracking, and offers to add swain governance rules. Run once when adopting swain in a new project — use swain-doctor for ongoing per-session health checks.
- ▌ Swain Keys 2 · cristoslc bundlePer-project SSH key provisioning for git signing and authentication. Generates ed25519 keys, configures git signing, registers on GitHub, and sets up SSH host aliases to bypass global agents (e.g., 1Password).
- ▌ Swain Push 2 · cristoslcStage all changes, generate a descriptive commit message from the diff, commit, and push to the current branch's upstream.
- ▌ Swain Stage 2 · cristoslc bundleTmux workspace manager — creates layout presets (review, browse, focus), opens editor/browser/shell panes, runs an animated MOTD status panel, and lets the agent directly manage panes during work. Only activates in tmux sessions.
- ▌ Swain Retro 2 · cristoslcAutomated retrospectives — captures learnings at EPIC completion and on manual invocation. Reviews recent work, prompts the user with reflection questions, then distills findings into memory files and retro docs. Triggers on: 'retro', 'retrospective', 'what did we learn', 'reflect', or automatically after EPIC completion.
- ▌ Swain Design 2 · cristoslc bundleCreate, validate, and transition documentation artifacts (Vision, Epic, Story, Spec, Spike, ADR, Persona, Runbook, Design, Journey) through lifecycle phases. Handles spec writing, feature planning, epic creation, user stories, ADR drafting, research spikes, persona definition, runbook creation, design capture, architecture docs, phase transitions, implementation planning, cross-reference validation, and audits. Chains into swain-do for implementation tracking on SPEC/STORY; decomposes EPIC/VISION/JOURNEY into children first.
- ▌ Swain Doctor 2 · cristoslc bundleALWAYS invoke this skill at the START of every session before doing any other work. Validates project health: governance rules, tool availability, memory directory, settings files, script permissions, .agents directory, and .tickets/ validation. Auto-migrates stale .beads/ directories to .tickets/ and removes them. Remediates issues across all swain skills. Idempotent — safe to run every session.
- ▌ Swain Search 2 · cristoslcEvidence pool collection and normalization for swain-design artifacts. Collects sources from the web, local files, and media (video/audio), normalizes them to markdown, and caches them in reusable evidence pools. Use when researching a topic for a spike, ADR, vision, or any artifact that needs structured evidence. Also use to refresh stale pools or extend existing ones with new sources. Triggers on: 'research X', 'gather evidence for', 'build an evidence pool', 'search for sources about', 'refresh the evidence pool', 'what do we know about X', or when swain-design needs research inputs for a spike or ADR.
- ▌ Swain Status 2 · cristoslc bundleCross-cutting project status dashboard. Shows active epics with progress ratios, actionable next steps, blocked items, in-progress tasks, GitHub issues, and session context. Produces rich terminal output with clickable links. Triggers on: 'status', 'progress', 'what's next', 'dashboard', 'overview', 'where are we', 'what should I work on'.
- ▌ Swain Update 2 · cristoslcUpdate swain skills to the latest version. Use when the user says 'update swain', 'upgrade swain', 'pull latest swain', or wants to refresh their swain skills installation. Runs the skills package manager (npx) with a git-clone fallback, then invokes swain-doctor to reconcile governance and validate project health.
- ▌ Swain Search 3 · cristoslc bundleTrove collection and normalization for swain-design artifacts. Collects sources from the web, local files, and media (video/audio), normalizes them to markdown, and caches them in reusable troves. Use when researching a topic for a spike, ADR, vision, or any artifact that needs structured research. Also use to refresh stale troves or extend existing ones with new sources. Triggers on: 'research X', 'gather sources for', 'build a trove', 'search for sources about', 'refresh the trove', 'what do we know about X', or when swain-design needs research inputs for a spike or ADR.
- ▌ Swain Release 2 · cristoslcCut a release — detect versioning context, generate a changelog from conventional commits, bump versions, and create a git tag. Use when the user says "release", "cut a release", "tag a release", "bump the version", "create a changelog", or any variation of shipping/publishing a version. This skill is intentionally generic and works across any repo — it infers context from git history and project structure rather than assuming a specific setup.
- ▌ Swain Session 2 · cristoslc bundleSession management — restores terminal tab name, user preferences, and context bookmarks on session start. Auto-invoked at session start via AGENTS.md. Also invokable manually to change preferences or bookmark context for the next session.
- ▌ Swain Do 3 · cristoslcBootstrap, install, and operate an external task-management CLI as the source of truth for agent execution tracking (instead of built-in todos). Provides the abstraction layer between swain-design intent (implementation plans and tasks) and concrete CLI commands. MUST be invoked when any implementation-tier artifact (SPEC) comes up for implementation — create a tracked plan before writing code. Optional but recommended for complex SPIKEs. For coordination-tier artifacts (EPIC, VISION, JOURNEY), swain-design must decompose into implementable children first — this skill tracks the children, not the container. Also use for standalone tasks that require backend portability, persistent progress across agent runtimes, or external supervision. Use this skill whenever the user asks to track tasks, create an implementation plan, check what to work on next, see task status, manage dependencies between work items, or close/abandon tasks — even if they don't mention "execution tracking" explicitly.
- ▌ Swain Sync 2 · cristoslcFetch upstream, rebase, stage all changes, run ADR compliance check on modified artifacts, generate a descriptive commit message from the diff, commit, and push to the current branch's upstream. Handles merge conflicts by preferring local changes for config/project files and upstream for scaffolding.
- ▌ Swain Retro 3 · cristoslcAutomated retrospectives — captures learnings at EPIC completion and on manual invocation. Reviews recent work, prompts the user with reflection questions, then distills findings into memory files and retro docs. Triggers on: 'retro', 'retrospective', 'what did we learn', 'reflect', or automatically after EPIC completion.
- ▌ Swain Design 3 · cristoslc bundleCreate, validate, and transition documentation artifacts (Vision, Epic, Spec, Spike, ADR, Persona, Runbook, Design, Journey) through lifecycle phases. Handles spec writing, feature planning, epic creation, ADR drafting, research spikes, persona definition, runbook creation, design capture, architecture docs, phase transitions, implementation planning, cross-reference validation, and audits. Chains into swain-do for implementation tracking on SPEC; decomposes EPIC/VISION/JOURNEY into children first.
- ▌ Swain Doctor 3 · cristoslc bundleALWAYS invoke this skill at the START of every session before doing any other work. Validates project health: governance rules, tool availability, memory directory, settings files, script permissions, .agents directory, and .tickets/ validation. Auto-migrates stale .beads/ directories to .tickets/ and removes them. Remediates issues across all swain skills. Idempotent — safe to run every session.
- ▌ Swain Search 4 · cristoslc bundleEvidence pool collection and normalization for swain-design artifacts. Collects sources from the web, local files, and media (video/audio), normalizes them to markdown, and caches them in reusable evidence pools. Use when researching a topic for a spike, ADR, vision, or any artifact that needs structured evidence. Also use to refresh stale pools or extend existing ones with new sources. Triggers on: 'research X', 'gather evidence for', 'build an evidence pool', 'search for sources about', 'refresh the evidence pool', 'what do we know about X', or when swain-design needs research inputs for a spike or ADR.
- ▌ Swain Status 3 · cristoslc bundleCross-cutting project status dashboard. Shows active epics with progress ratios, actionable next steps, blocked items, in-progress tasks, GitHub issues, and session context. Produces rich terminal output with clickable links. Triggers on: 'status', 'progress', 'what's next', 'dashboard', 'overview', 'where are we', 'what should I work on'.
- ▌ Swain Doctor 4 · cristoslc bundleALWAYS invoke this skill at the START of every session before doing any other work. Validates project health: governance rules, tool availability, memory directory, settings files, script permissions, .agents directory, and .tickets/ validation. Auto-migrates stale .beads/ directories to .tickets/ and removes them. Remediates issues across all swain skills. Idempotent — safe to run every session.
- ▌ Swain Session 3 · cristoslcSession management — restores terminal tab name, user preferences, and context bookmarks on session start. Auto-invoked at session start via AGENTS.md. Also invokable manually to change preferences or bookmark context for the next session.
- ▌ Swain Session 4 · cristoslc bundleSession management — restores terminal tab name, user preferences, and context bookmarks on session start. Auto-invoked at session start via AGENTS.md. Also invokable manually to change preferences or bookmark context for the next session.
- ▌ Swain Dispatch 2 · cristoslcDispatch swain artifacts to background agents via GitHub Issues. Creates a GitHub Issue with the artifact content and triggers the Claude Code Action workflow for autonomous implementation. Use when the user wants to offload work to a background agent.
- ▌ AI Output Humanizer · cristoslc bundleAudit and rewrite content to remove AI writing patterns. Three modes (rewrite, detect, edit), voice calibration from sample or named profiles, iterate-to- convergence, context-aware strictness, and explicit ethics framing. Synthesizes the best detection patterns from conorbronsdon/avoid-ai-writing, blader/humanizer, brandonwise/humanizer, stephenturner/skill-deslop, and lguz/humanize-writing-skill.
- ▌ Dispatch Opencode · cristoslc bundleDispatch subagent tasks through opencode (https://opencode.ai) using the async .subagents/ lock-watch protocol. The agent writes a plan YAML, calls run-plan.sh to validate and dispatch, polls lockfiles on its own interval, reads FINAL_OUTPUT.md on completion, and calls subagent-cleanup.sh or subagent-abandon.sh to tear down. Use when you want to hand work off to a background subagent instead of doing it yourself — for example, dispatching a subagent into a worktree, parallelizing independent tasks, or running long-lived investigations. TRIGGER when: the agent would otherwise block on a subagent that could run in the background, or when worktree-isolated subagent dispatch is needed.
- ▌ Media Summary · cristoslc bundleDownloads and summarizes audio/video media, X/Twitter threads, and web articles — podcasts, YouTube videos, Instagram reels, recipe videos, talks, interviews, lectures, conference presentations, multi-post X threads, LinkedIn posts, Medium articles, and any web page. Handles speech-based transcripts, post captions, on-screen text overlays (via vision OCR), X thread unrolling via the fxtwitter API, and generic HTML ingestion via readability/Puppeteer. Saves a structured markdown summary locally, publishes it as a public GitHub Gist, and opens it in the system default application. Use when the user provides a URL to any media content, X/Twitter status, or web article.
- ▌ Session Stash · cristoslc bundleStash and pop portable agent sessions. A session stash is a durable, git-versioned capture of an in-flight session (normalized transcript + session-relevant uncommitted work + reference files) stored at `docs/session-stash/<name>/`. Stash an active session to resume it later in a different harness (Claude, opencode), a different context window, or a fresh model. Pop a stash to have the resuming agent self-orient from the stash folder's own AGENTS.md. Convert a stash to a sashay, musing, or Jira ticket. Use when the operator says "stash this session", "pop session @docs/session-stash/...", "resume the stashed session", or "convert stash to ...". Do NOT use for in-session compression or for sessions you intend to resume in the same harness the same way.
- ▌ Office PDF · cristoslc bundleComprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
- ▌ Office DOCX · cristoslc bundleComprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks
- ▌ Office PPTX · cristoslc bundlePresentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks
- ▌ Office XLSX · cristoslc bundleComprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas
- ▌ Office Install · cristoslc bundleEnvironment setup for office-skills. When Claude needs to verify or install prerequisites before running any office skill workflow — detects platform, checks what's present, acquires what's missing to a local tools/ directory, resolves npm dependencies, and writes a paths.json that other skills read.
- ▌ Swain Helm · cristoslcStart, stop, and monitor the swain-helm bridge system (VISION-006). The watchdog manages project bridges that route Zulip messages to opencode serve, enabling session control from any device. Triggers on: 'helm', 'bridge', 'untethered', 'start bridge', 'stop bridge', 'helm status', 'helm logs', 'is the bridge running'.
- ▌ Swain Test · cristoslc bundleTest gate for swain-sync and swain-release — runs integration tests and emits smoke instructions
- ▌ Swain Security Check · cristoslc bundleRun all security scanners against the project and produce a unified, severity-bucketed report. Orchestrates gitleaks (secrets), osv-scanner/trivy (dependency vulns), semgrep (static analysis), context-file injection scanner (built-in), and repo hygiene checks (built-in). Missing scanners are skipped with install hints — the scan always completes. Triggers on: 'security check', 'security scan', 'run security', 'scan for secrets', 'check for vulnerabilities', 'security audit', 'audit dependencies', 'check secrets', 'find vulnerabilities', 'scan codebase'.
- ▌ Agentrc · cristoslc bundleOrchestrate multiple Claude Code workers in tmux panes. Use when the user wants to run parallel tasks, dispatch workers, or manage a multi-agent workflow.
- ▌ Skills Engineering · cristoslc bundleAuthor, evaluate, and iteratively improve Agent Skills (SKILL.md protocol) using a rigorous TDD lifecycle. Handles spec declaration, BDD behavioral contract authoring, script TDD (red-green per acceptance criterion), SKILL.md authoring, adversarial boundary testing, full eval with subagent-driven grading, improvement loops, and optional refactoring. Use when creating a new skill, evaluating an existing skill, improving a skill from eval feedback, or engineering the SKILL.md structure.
- ▌
- ▌ Swain Roadmap · cristoslcRefresh and display the project roadmap and status dashboard. Regenerates ROADMAP.md from the artifact graph (quadrant chart, Eisenhower tables, Gantt timeline, dependency graph), creates it if missing, and opens it for review. Also serves as the project status dashboard — shows active epics, progress, actionable next steps, blocked items, and recommendations. Use when the user says 'roadmap', 'show roadmap', 'refresh roadmap', 'status', 'dashboard', 'what's next', 'overview', 'where are we', 'what should I work on', 'show me priorities', 'priority matrix', or 'what does the roadmap look like'. Also use when any skill needs to ensure ROADMAP.md is fresh before consuming it.
- ▌ Swain Teardown · cristoslcFull session shutdown — digest, retro, merge worktree branches, worktree cleanup, close session state, and commit handoff. This is the single entry point for ending a session. Triggers on: 'teardown', 'clean up', 'wrap up', 'session end', 'end session', 'close session', 'done', 'log off', 'sign off', or automatically when the decision budget is reached.
- ▌ Push · cristoslcStage all changes, generate a descriptive commit message from the diff, commit, and push to the current branch's upstream. Handles merge conflicts by preferring local changes for config/project files and upstream for scaffolding.
- ▌ Swain · cristoslcMeta-router for swain skills. Invoke when the user types /swain or mentions swain by name. Routes to the matching swain-* sub-skill — only load the one that matches.
- ▌ Swain Do · cristoslc bundleBootstrap, install, and operate an external task-management CLI as the source of truth for agent execution tracking (instead of built-in todos). Provides the abstraction layer between swain-design intent (implementation plans and tasks) and concrete CLI commands. MUST be invoked when any implementation-tier artifact (SPEC) comes up for implementation — create a tracked plan before writing code. Optional but recommended for complex SPIKEs. For coordination-tier artifacts (EPIC, VISION, JOURNEY), swain-design must decompose into implementable children first — this skill tracks the children, not the container. Also use for standalone tasks that require backend portability, persistent progress across agent runtimes, or external supervision. Use this skill whenever the user asks to track tasks, create an implementation plan, check what to work on next, see task status, manage dependencies between work items, or close/abandon tasks — even if they don't mention "execution tracking" explicitly.
- ▌ Swain Help · cristoslc bundleContextual help and onboarding for the swain skill ecosystem. Use when users ask about swain — what skills exist, how to use them, what artifacts are available, how workflows connect, or when they need a quick reference. Also invoked after swain-init to orient new users. Triggers on: 'how do I...', 'what is...', 'help', 'what can swain do', 'show me the commands', 'I'm confused', 'where do I start', any question about swain skills, artifacts, or workflows, and after project onboarding completes.
- ▌ Swain Init · cristoslcOne-time project onboarding for swain. Migrates existing CLAUDE.md content to AGENTS.md (with the @AGENTS.md include pattern), verifies vendored tk (ticket) for task tracking, configures pre-commit security hooks (gitleaks default), and offers to add swain governance rules. Run once when adopting swain in a new project — use swain-doctor for ongoing per-session health checks.
- ▌ Swain Keys · cristoslc bundlePer-project SSH key provisioning for git signing and authentication. Generates ed25519 keys, configures git signing, registers on GitHub, and sets up SSH host aliases to bypass global agents (e.g., 1Password).
- ▌ Swain Push · cristoslcStage all changes, generate a descriptive commit message from the diff, commit, and push to the current branch's upstream.
- ▌ Swain Sync · cristoslcFetch upstream, rebase, stage all changes, run ADR compliance check on modified artifacts, generate a descriptive commit message from the diff, commit, and push to the current branch's upstream. Handles merge conflicts by preferring local changes for config/project files and upstream for scaffolding.
- ▌ Swain Retro · cristoslcAutomated retrospectives — captures learnings at EPIC completion and on manual invocation. EPIC-scoped retros embed a Retrospective section in the EPIC artifact. Cross-epic and time-based retros produce standalone retro docs. Triggers on: 'retro', 'retrospective', 'what did we learn', 'reflect', or automatically after EPIC terminal transitions.
- ▌ Swain Stage · cristoslc bundleTmux workspace manager — creates layout presets (review, browse, focus), opens editor/browser/shell panes, runs an animated MOTD status panel, and lets the agent directly manage panes during work. Only activates in tmux sessions.
- ▌ Swain Design · cristoslc bundleCreate, validate, and transition documentation artifacts (Vision, Initiative, Epic, Spec, Spike, ADR, Persona, Runbook, Design, Journey) through lifecycle phases. Handles spec writing, feature planning, epic creation, initiative creation, ADR drafting, research spikes, persona definition, runbook creation, design capture, architecture docs, phase transitions, implementation planning, cross-reference validation, and audits. Chains into swain-do for implementation tracking on SPEC; decomposes EPIC/VISION/INITIATIVE/JOURNEY into children first.
- ▌ Swain Doctor · cristoslc bundleALWAYS invoke this skill at the START of every session before doing any other work. Validates project health: governance rules, tool availability, memory directory, settings files, script permissions, .agents directory, and .tickets/ validation. Auto-migrates stale .beads/ directories to .tickets/ and removes them. Remediates issues across all swain skills. Idempotent — safe to run every session.
- ▌ Swain Search · cristoslc bundleTrove collection and normalization for swain-design artifacts. Collects sources from the web, local files, and media (video/audio), normalizes them to markdown, and caches them in reusable troves. Use when researching a topic for a spike, ADR, vision, or any artifact that needs structured research. Also use to refresh stale troves or extend existing ones with new sources. Triggers on: 'research X', 'gather sources for', 'build a trove', 'search for sources about', 'refresh the trove', 'what do we know about X', or when swain-design needs research inputs for a spike or ADR.
- ▌ Swain Status · cristoslc bundleCross-cutting project status dashboard. Shows active epics with progress ratios, actionable next steps, blocked items, in-progress tasks, GitHub issues, and session context. Produces rich terminal output with clickable links. Triggers on: 'status', 'progress', 'what's next', 'dashboard', 'overview', 'where are we', 'what should I work on'.
- ▌ Swain Update · cristoslc bundleUpdate swain skills to the latest version. Use when the user says 'update swain', 'upgrade swain', 'pull latest swain', or wants to refresh their swain skills installation. Runs the skills package manager (npx) with a git-clone fallback, then invokes swain-doctor to reconcile governance and validate project health.
- ▌ Swain Release · cristoslcCut a release — detect versioning context, generate a changelog from conventional commits, bump versions, and create a git tag. Use when the user says "release", "cut a release", "tag a release", "bump the version", "create a changelog", or any variation of shipping/publishing a version. This skill is intentionally generic and works across any repo — it infers context from git history and project structure rather than assuming a specific setup.
- ▌ Swain Session · cristoslc bundleSession management — restores terminal tab name, user preferences, and context bookmarks on session start. Auto-invoked at session start via AGENTS.md. Also invokable manually to change preferences or bookmark context for the next session.
- ▌ Swain Dispatch · cristoslcDispatch swain artifacts to background agents via GitHub Issues. Creates a GitHub Issue with the artifact content and triggers the Claude Code Action workflow for autonomous implementation. Use when the user wants to offload work to a background agent.
- ▌ External Task Management · cristoslc bundleUse an external task-management CLI as the source of truth for agent execution tracking (instead of built-in todos), including bootstrap/install flow, status-transition rules, and observer-friendly reporting. Use for tasks that require backend portability, persistent progress across agent runtimes, or external supervision.