All authors
Claude Skills by HiQS-Labs
github.com/HiQS-Labs80 skills0 installs3 views
- 1 INBOX| What was just completed | What's next | |---|---| | Design negotiated with operator and parked 2026-09-08; issue + ledger row live | Awaiting operator go to start the start-task lifecycle (isolated task clone, author `skills/keel/SKILL.md`, relay plan QA, PR) |Votes: 0GitHub stars: 5
- 2 WORKING| What was just completed | What's next | |---|---| | Implemented + impl QA APPROVED round 3 2026-09-09 (round-1 FAIL: 4 Should + 1 Nit; round-2 FAIL: 2 Should + 1 Nit — all fixed) | Push through gate; open PR into development (merge held by operator) |Votes: 0GitHub stars: 5
- 3 COMPLETED| What was just completed | What's next | |---|---| | Implemented `skills/review-xyz/`, `utils/py/review_xyz.py`, regression test suite `test/gh132-review-xyz-skill.sh` (19/19 pass), executed dual dogfood reviews with Qwen 3.8-Max and stealth/ox-alpha, and opened PR #133. | Merge PR #133 into `development` and close out issue #132. |Votes: 0GitHub stars: 5
- 3 COMPLETED| What was just completed | What's next | |---|---| | Issue #436 created and registered. Compliance with `WORKTREE-SAFETY.md` verified across all 6 phases. | Author `skills/merge-cleanup/SKILL.md` and helper scripts (`merge_cleanup.py`, `scan_clones.py`, `toposort_prs.py`). Register in RELEASES DB. Cut fresh full clone, run test suite, QA consult with Qwen 3.8 max, open PR targeting `development`, and tear down clone. |Votes: 0GitHub stars: 5
- 3 COMPLETED| What was just completed | What's next | |---|---| | PR #440 merged; canonical reconciler completed document and ledger transition on 2026-09-05 | No implementation work remains; reconciliation changes await merge |Votes: 0GitHub stars: 5
- 3 COMPLETED| What was just completed | What's next | |---|---| | Five-rung recovery ladder and blocking `/workhorse` interrupt implemented; consult corrections applied; skill, PDDA, RELEASES, and the 351-suite gate are green | Await operator direction on pushing the branch and opening a PR to `development` |Votes: 0GitHub stars: 5
- 3 COMPLETED| What was just completed | What's next | |---|---| | Skill authored; plan and final independent QA Approved; targeted checks passed. | Publication blocked: diagnose gh53 merge fixture duplicate-generation failure; see committed GH-606 evidence. No push or PR. |Votes: 0GitHub stars: 5
- 3 COMPLETED- One preparation entry point - Reuse existing planner and marathon runner - Keep explicit fire gateVotes: 0GitHub stars: 5
- Skill ViewerList every skill in this repo with its name and one-line description, read live from skills/*/SKILL.md frontmatter. Use when the user asks "what skills are here", "list skills", "what can I run", or wants a quick catalog of the repo's skills. Read-only.Votes: 0GitHub stars: 5
- Better OptionsPressure-test an option set before the operator picks. Catches an AI agent — this one included — conflating two separate problems into one menu, or quietly narrowing the field to a false dilemma that skips the boring option. Borrows debug-mantra's falsify-the-hypothesis rigor (disprove each option before trusting it) then ponytail's minimalism bias (of what survives, favor the smallest) to surface the option nobody named because it wasn't impressive enough. Trigger when an agent — this one i...Votes: 0GitHub stars: 5
- ConsultOne-shot cross-model CONSULT — fan the same question out to Codex and agy in parallel (repo-isolated, advisory), then reconcile their answers into one. Use when the user wants a "second opinion", to "ask Codex and agy", a "panel" or "cross-model" check, or an independent gut-check on a decision/design/doc before committing — and does NOT need an iterative build/review loop. NOT a relay: a relay is an iterative 1:1 Producer↔Reviewer loop that converges an artifact; a consult is a parallel 1-sh...Votes: 0GitHub stars: 5
- Debug MantraFour-mantra debugging discipline — reproduce, trace the fail path, falsify the hypothesis, cross-reference every breadcrumb. Recite the mantra block verbatim at the start of any debugging session, then apply the four steps in order before proposing any fix. Trigger on /debug-mantra and proactively whenever debugging starts — user reports a bug, says something is broken/throwing/failing, asks to debug/diagnose/investigate an issue, pastes a stack trace or error log, or asks an attribution ques...Votes: 0GitHub stars: 5
- FiveThe 5-and-5 decision checksum for a plan, feature, or bug fix that is in scope: exactly five load-bearing things the artifact DOES — the decisions and behaviors, especially choices the agent made that nobody explicitly asked for — and five things it explicitly does NOT do, so unwelcome decisions surface before approval instead of after. Use whenever the user asks for a decision checksum of an in-scope plan, spec, PR description, or fix — "five", "/five", "give me the five", "key highlights", ...Votes: 0GitHub stars: 5
- PonytailForces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the added code, abstraction, dependency, or automation needs to exist at all to satisfy the stated requirement (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. It minimizes the implementation, not explicit product or operational requirements. Supports intensity levels: ...Votes: 0GitHub stars: 5
- ReconTrace an existing system end to end — entry points, call paths, every read and write of the state involved, the contracts crossed, the failure and rollback paths — and write it down as a Recon Map before a plan for changing it is drafted. Fires when the user asks to plan, spec, design, refactor, migrate, or size a change to code that already exists: "write a plan", "plan this out", "how should we build X into this", "refactor X", "migrate X", "what would it take to change X", "will this break...Votes: 0GitHub stars: 5
- Relay AutomationTick-backed, self-healing automation for the file-based /relay review loop — a hands-free poll driver (poll.sh), a relay-turn supervisor (relay-drive.sh), a liveness watchdog (watchdog.sh), a verdict-gated runner (runner.sh), and headless cross-model turn-takers (`codex-turn.sh`, `agy-turn.sh`). Sibling to the xyz/tick skill; depends on a tick runtime with handoff-exclusive claims. Use to run a Producer↔Reviewer relay with auto turn-taking, stall recovery, and (Option A) headless Codex or agy...Votes: 0GitHub stars: 5
- Relay XyzDrive an automated /relay review loop on THIS repo with the shipped relay-automation harness (relay-drive.sh + codex-turn.sh / agy-turn.sh / poll.sh) rather than improvising the handoff by hand. Use when the operator wants to "run an automated relay", "have Codex or agy review this end-to-end", "drive a relay to completion headless", "run the relay harness", or set up the all-Claude hands-free poll loop. The skill can start from a foreign repo because its locator selects a separate XYZ-forge ...Votes: 0GitHub stars: 5
- RelayGenerate and run a relay thread file in `relay-system/<date>/<slug>.md` — a turn-based, file-based review loop between two Claude Code agents (a Producer who builds, a Reviewer who critiques and proposes fixes the author applies) so a human stops copy-pasting output between two windows. Use this whenever the user wants to "set up a relay", run a "producer/reviewer" or "worker/reviewer" loop, have "two agents" review each other's work in a shared file, "hand off" between agents without pasting...Votes: 0GitHub stars: 5
- StandupSession-scoped triage: what did I leave open, what is rotting, and is the plan still right — answered in under a screen. Runs in seconds over the session, the working tree, open PRs, and the two ledgers (ROADMAP + RELEASES DB), then emits a ranked list capped at 7 items plus a capped strategic read. Use when the operator says "/standup", "what's open", "what did I leave hanging", "where are we", "what should I do next", or is closing out a long working session. Not for long-window defect anal...Votes: 0GitHub stars: 5
- Start TaskStart one task or a batch of GitHub issues and carry it through fresh full clones, repo-governed intake, grounded recon, surgical DRY planning, Codex relay plan QA, execution, verification, final relay QA, and ready PRs. Use for /start-task, "start these issues", or requests to clone, register, execute, QA, and make a PR. Works across repos. For diagnosis alone use workhorse; for landing existing PRs and retiring clones use merge-cleanup.Votes: 0GitHub stars: 5
- SweApply software-engineering standards when authoring or reviewing project plans, build/spec/PRD documents, architecture RFCs, or agent governance. Use for "write a plan", "review this build doc", "apply our SWE standards", or "is this plan ready to build"; also apply before drafting a project plan. Grades grounded recon, minimal scope, diagnosis, blast radius, and verifiable acceptance. This is a planning rubric, not a debugging or execution pipeline.Votes: 0GitHub stars: 5
- TriangulateApply three lenses to one problem in a fixed order — recon (what is actually there), debug-mantra (is what I believe actually true), ponytail (what is the smallest thing that works) — with an explicit rule for how much evidence to buy before shrinking. Use when a task tempts you toward opposite errors at once: over-building against a blast radius nobody measured, or shipping a confident one-liner into a system nobody read. Trigger on /triangulate, and on "what is the right amount of work here...Votes: 0GitHub stars: 5
- UnstuckInterrupt a stalled AI work session and restore movement toward the original outcome. Use proactively when the agent is passive, trapped in narration, halting on tool exits, or reporting activity without milestone change, as well as when overengineering, inventing machinery around work, or reopening settled decisions. Fires autonomously on self-trigger tripwires (two turns without milestone change, tool exit code inertia, passive waiting narration, false completion, or re-litigating a reviewe...Votes: 0GitHub stars: 5
- Agent ChorusStart or join a local XYZ discussion shared by two or more Claude, Codex, or other agent sessions through a compact six-digit ID. Use when a prompt says “Join XYZ AgentChorus #123456 as agent number two… — use the agent-chorus skill” (older invitations omit the trailing clause, and the legacy phrase “Join XYZ agent2agent #123456…” still refers to this skill — accept all three), when the user asks sessions to talk to each other, or when a participant needs to send, route, inspect, watch, drive...Votes: 0GitHub stars: 5
- Ci DebugDebug failing CI pipelines, pre-push gates, hosted GitHub Actions workflows, and reproduce test failures in safe isolation. Applies debug-mantra ground-truth discipline, recon seam/blast radius mapping, and foundationally sound (non-bandage) ponytail least-mechanism resolutions. Use when an operator says "fix failing CI", "debug this pipeline", "why is CI red", "gate failed", "pre-push gate red", "reconcile failed", "test contention", "container won't start", or "reproduce this CI bug".Votes: 0GitHub stars: 5
- ExpressHotfix fast lane (GH-267/GH-516) for an explicit /express, "express this hotfix", or "express GH-N" request. Carries a critical, risk-bounded fix, registered existing covering suite, releases-ledger updates, born-complete PDDA doc, CHANGELOG, landing, and reconciliation in one operator-authorized motion. Requires a task clone branched from origin/development (carrying <= 2 local commits) with the canonical pre-push gate installed, authenticated gh, and the root releases ledger. The driver com...Votes: 0GitHub stars: 5
- File Xyz BugFile a bug against the xyz-3-agents-swarm harness from ANY repo or session — lands a PDDA-compliant capture in that repo's PROJECT/1-INBOX/ (GH-<n>-*.md), files the tracking GitHub issue, and parks a one-line ROADMAP pointer, without touching the repo you are standing in. Use when the xyz harness misbehaves while you are working somewhere else — a relay/marathon driver fails, `tick` misbehaves, a turn shim exits wrong, a vendored `.xyz/` drifts, an xyz skill (relay-xyz, consult, hq, xyz) brea...Votes: 0GitHub stars: 5
- HqHQ — the multi-repo command center. Turn a single utterance ("For project Acme, do X") into governance-aware action across every repo on this device. Resolves a project name (fuzzily) to a real repo via the registry ladder (Rebalance project_registry → XYZ install registry → Git Pulse PDDA registry → filesystem), reports its governance state as a project card, lands the request on that repo's own PDDA rails (issue → 1-INBOX capture → ROADMAP parking), and prepares dispatch (queue a lane / gat...Votes: 0GitHub stars: 5
- JogImmediate serial task queue execution engine and conversational capture skill. Use when an operator wants to queue, prioritize, inspect, or execute a sequence of tasks one at a time today without marathon wave planning or concurrency overhead. Re-uses the Releases SQLite DB, driver lock, Marathon's reviewed one-phase executor (default since GH-280), and swarm-preflight.Votes: 0GitHub stars: 5
- Merge CleanupConsolidate multiple Git worktrees and clones of a repository into a single clean checkout, safely merge associated PRs in topological dependency order, document landing batches of three or more PRs as a GitHub issue (merge sequence, problems, ad-hoc fixes, regression sweep, post-deployment carry-overs — also echoed in chat), reconcile post-merge governance state (PDDA and RELEASES DB), and safely remove leftover worktrees/clones without data loss or interrupting active sessions. Strictly com...Votes: 0GitHub stars: 5
- Phase QaProject plan enhancement tool. Reads a phased planning doc and appends a QA checklist (DRY, SOLID, observability, and phase-appropriate litmus tests) under each phase, and optionally adds an anti-goals section to give each checklist a scope boundary, and surfaces per phase whether the work needs deploying to a remote environment. Invoke before work begins to bake checks into the plan; invoke mid-project or post-project to also run code-diff reviews on completed phases. Always confirms with th...Votes: 0GitHub stars: 5
- Relay To IssueTurn a finished /relay producer↔reviewer thread into a single checklist-style GitHub issue, filed in the repo the relay was actually about. Reviews the relay transcript, summarizes the conclusion (including agreements AND unresolved disagreements), and synthesizes the actionable findings into a markdown checklist issue body so each box can be spun off into a quick task. Use when the operator says "file this relay as an issue", "turn the relay into a GitHub issue", "open an issue from the rela...Votes: 0GitHub stars: 5
- ReleasesRead, synthesize, diagnose, clean, author, and publish the releases.db planning ledger (or legacy RELEASES.md where retained) through one routed workflow. Use for /releases; release status or health checks; stale-plan review against merged PRs, commits, and CHANGELOG entries; disciplined release creation or updates; ledger cleanup; historical anchors or backfill; publishing a planned GitHub Release; or deciding whether Radar or Finish Line is the better follow-up. Default invocation is read-o...Votes: 0GitHub stars: 5
- Review CodeMeticulous code and pull request review ladder using /recon and /debug-mantra to test out each fix and feature against live ground truth. Supports PR targets under review-PR / --pr <PR#>. Loops through /workhorse and /unstuck ladders to autonomously resolve reversible adaptations and pivots without stopping for operator permission, driving verified forward movement.Votes: 0GitHub stars: 5
- Review XyzDeterministic, multi-model code review system and skill for XYZ. Summon frontier reviewers (Command Code -> Qwen 3.8-Max, GLM-5.3, OpenRouter, Codex, Agy) to perform throwaway-worktree isolated code reviews on local diffs or GitHub PRs. Validates `[Blocker]`/`[Should]`/`[Nit]`/`[Pass]` citations and automatically formats or posts review critiques and follow-up checklists to GitHub PRs (`--post-pr`) and linked issues (`--post-issues`). Use when the operator wants to "review this PR with Qwen",...Votes: 0GitHub stars: 5
- Start MarathonStart marathon preparation from intake through reviewed implementation plans, honest contracts, disjoint lanes, MARATHON.yaml, preflight and dry-run. Use for "start marathon", "marathon", a marathon queue, or a viability check of marathon docs another session prepared. Route an ambiguous bare "marathon" here; ask which arc only if live evidence cannot identify one. Explicit fire/execute requests use the confirmed marathon command after this preparation. Legacy /marathon-triage requests use th...Votes: 0GitHub stars: 5
- WorkhorseEnd-to-end disciplined problem resolution ladder: triages complex multi-task or wall-of-text intake into an atomic priority queue, establishes ground truth via /debug-mantra, engineers the leanest safe solution via /ponytail (reusing and extending existing subsystems with zero code sprawl), enforces AGENTS.md, SOP.md, and GUIDING PRINCIPLES governance, checks cross-repo CHANGELOG cohesion, stress-tests the plan via /consult with Codex and Agy, runs bounded /recon on ambiguous stateful targets...Votes: 0GitHub stars: 5
- XyzCoordinate two (or more) AI coding agents working CONCURRENTLY on non-overlapping, path-scoped lanes of ONE shared repo, via the `tick` CLI — for parallel builds and parallel codebase recon, with collision-free claims, liveness heartbeats, and an honest concurrency metric. Use when the user wants to "run two agents in parallel", "split this build across agents", "have agents recon/profile the codebase concurrently", or "coordinate Codex + Gemini on the same repo". NOT for work that touches sh...Votes: 0GitHub stars: 5
- 10daysSweep GitHub issues opened or updated in an age window (default: last 10 days; adjustable, e.g. an 11-14-day slice), evaluate PRS 4-axis ratings (priority, severity, appeal, effort cheapness; calc sum + ovr overrides) as the prioritization signal, verify each issue is still valid, reproducible, and not already fixed (subagents check issue state, comments, and history), build a marathon plan from the survivors, run swarm-preflight, then cut a branch and execute the marathon end-to-end unattend...Votes: 0GitHub stars: 5
- ConvergeRead two or more Convergence Maps produced by /dry — across repos, or across re-runs of one repo — and find what repeats. Clusters findings by SHAPE rather than by resource, so "a gateway exists and the files that import it bypass it anyway" surfaces as one portable finding rather than four unrelated ones, and tracks whether each target got fixed, ignored, or worse since the last sweep. Output is a fleet verdict plus house rules worth enforcing everywhere, not another per-repo report. Trigger...Votes: 0GitHub stars: 5
- DryFind the subsystems that should be one subsystem. Traces a codebase resource-first instead of subject-first, then reports every place N independent paths reach the same table, file, env var, endpoint, binary, or config key without ever meeting — or where N places define the same decision with different answers — the "we built four of these and none of them know about each other" failure that stays invisible until the bug count spikes. Produces a ranked Convergence Map naming the single gatewa...Votes: 0GitHub stars: 5
- End Of WeekRun a seven-day governance review for an XYZ Forge or XYZ-vendored repository: check GitHub default-branch reconciliation, compare RebalanceOS HiQS and git activity with PDDA/RELEASES/XYZ metadata, file a ranked umbrella issue, correct verified metadata, and refresh the configured project kanban through its canonical writer. Use for End of Week, /end-of-week, or a weekly governance and kanban refresh. Governance script changes are recommendations only.Votes: 0GitHub stars: 5
- HonestProduce an honest, defensible ground-truth read of the current repo — how mature the codebase really is, how far along each feature actually is, and what can be safely claimed about it externally. Reads CHANGELOG, architecture/technical docs, and recent git history; never modifies the repo. Offers an Express (10–15 min) or Deep (30–40 min) scan. Trigger when the user says "baseline", "where do we actually stand", "what's the real state of this repo", "honest assessment of the codebase", "matu...Votes: 0GitHub stars: 5
- Marathon CleanupAudit active PDDA marathon plans and bundles, reconcile every lane against canonical project docs, frontmatter and status tables, GitHub issue and PR state, landed commits, tests, and CHANGELOG evidence, then archive only verified-complete task docs and fully complete marathons. Use when asked to clean up, reconcile, retire, archive, or sweep completed marathon files under PROJECT/2-WORKING, especially after marathon lanes merge. Defaults to report-only and requires explicit confirmation befo...Votes: 0GitHub stars: 5
- Merge Cleanup DeepRead-only, sub-agent-driven triage of the checkouts /merge-cleanup preserved (PRESERVE_UNPUSHED, PRESERVE_DIRTY, PRESERVE_UNVERIFIED_*): zip each clone to a dated backup with a manifest, fan out at most three read-only agents grouped by branch family, and establish per clone — by ancestry, by per-file content against development and open PR heads, and by QA attestation — whether its unlanded work is PR-WORTHY, SUPERSEDED, NEEDS-OWNER, or an ABANDON-CANDIDATE, then hand off (fresh-clone PR, is...Votes: 0GitHub stars: 5
- Push To Skills Army MiniRETIRED 2026-10-01 — do not run. XYZ-skills-army-mini is now the upstream for Skills Army HQ, and publishing from XYZ Forge would overwrite it. Formerly published the Skills Army HQ package from XYZ Forge into HiQS-Labs/XYZ-skills-army-mini.Votes: 0GitHub stars: 5
- Push To Xyz MiniPublish the curated XYZ mini skill subset from this XYZ-forge checkout into the local XYZ-mini repo and push it to origin, using the deterministic embedded-manifest publisher utils/py/xyz_mini_sync.py (GH-589). Trigger on "/push-to-xyz-mini", "publish to mini", "sync XYZ mini", "push the mini repo". Manual, operator-invoked; preview first, then apply and push on one confirmation.Votes: 0GitHub stars: 5
- RadarPer-repo SDLC process coach and strategic compass over the last 2-3 weeks of activity: celebrates high-level wins, evaluates engineering momentum, diagnoses process health, and spots potential regressions alongside recurring defect clusters. Analyzes Run/Grow/Transform flow distribution, checks open-PR collisions, and flags release plan drift; scans RADAR/, docs/radar/, or PROJECT/1-INBOX/ for multi-week trajectory arcs. Read-only analysis; findings persist to two sinks (an immutable dated re...Votes: 0GitHub stars: 5
- Skills Army HqManage a durable local skill collection and global app symlinks through conversation. Use to import, update, list, remove, or deploy skill folders from repositories already on disk, configure deployment targets, or replace skills-sync-trinity. Not for remote downloads, publishing skills, or installing their runtime dependencies.Votes: 0GitHub stars: 5
- SopCatch a repo's SOP (standard operating procedure) and lessons-learned docs up to what actually happened recently. Deep-recons the codebase for existing SOP / runbook / lessons / postmortem / incident docs (any .md, .txt, .rst), mines recent events from every available source (git, PRs, issues, incident files, changelogs, session logs, chat transcripts), grades each finding by evidence strength, then proposes diffs and asks the user which events must be included before applying anything. Works...Votes: 0GitHub stars: 5