backskills.ai Blog · llms.txt · agents.md · Most used by agents · Installs · Suggest · Monitor · Submit your skill ios-sync github:garrytan/gstack · first committed 2026-05-21 · source · badge
|
Skill Health: not yet scored Listed, not yet scored. This skill has no public model test yet. It is in the scoring queue; submitted skills go first, then the most-installed.
Version history 39 commits to this file on GitHub (newest first).
2026-10-27 · commit
3e4240a · v1.91.276.0 feat(preamble): tier 2+ skills load the shared preamble once per session (GSTA-96) (#3434)
2026-10-26 · commit
b9222a5 · v1.91.247.0 fix(plan-eng-review): define the three references its judged text left dangling (GSTA-91) (#3421)
2026-10-26 · commit
021d817 · v1.91.240.0 feat(proactive): default to the four core skills (core | all | off), with docs, prompt and tests (GSTA-99) (#3432)
2026-10-19 · commit
6237994 · v1.91.157.0 perf(gen-skill-docs): drop the "When to invoke" body section from Claude SKILL.md files (port of #3129) (#3305)
2026-10-10 · commit
45a6783 · v1.91.70.0 feat(unattended): artifact contract + validator, `unattended` session kind, findings-derived review log, gate list (multi-agent w
2026-10-10 · commit
5b9b837 · feat: honest work and gate integrity — gate-edit detector, review/ship gate pass, zero-run green, claims-need-evidence kernel (#3114)
2026-10-08 · commit
8bb6d65 · v1.91.66.0 fix: /autoplan without permission prompts after background reviewers, 34 contributor PRs from the backlog triage (#3087)
2026-10-07 · commit
f67c478 · v1.91.34.0 fix: /autoplan on current Claude Code and long sessions, quieter pre-push and sync guards, gstack-post, gstack-doctor (#3069)
2026-10-06 · commit
28f1385 · v1.91.32.0 fix: Codex works from zsh, free text never enters shell commands, honest failures (#3057)
2026-10-03 · commit
ac20ef1 · v1.91.16.0 fix: safe installs and upgrades, skills start everywhere, truthful completion (parallel wave) (#3014)
2026-10-03 · commit
74512c2 · v1.91.15.0 v1.91.15.0: Opus 5.5 prompt cleanup, behavior-level skill tests, transcript consent (#3017)
2026-10-01 · commit
df89475 · v1.91.11.0 refactor: one state-root rule, browse route table, shared shard engine, PTY harness split, MECE review resolvers (#3002)
2026-09-24 · commit
730a101 · v1.89.1.0 fix: remove continuous checkpoint commits (#2970)
2026-09-24 · commit
06ed920 · v1.89.0.0 feat: add shared-code extraction audit (#2925)
2026-09-22 · commit
636175d · v1.87.6.0 fix: make checks reliable and everyday validation faster (#2898)
2026-09-14 · commit
9f81911 · v1.86.0.0 feat: route outside reviews by harness (#2850)
2026-09-01 · commit
702a1a9 · v1.78.0.0 fix: the two-red-lanes wave — AUQ collapse rooted, OSV green from 105, 18 community PRs absorbed, upgrade path can't eat installs
2026-08-31 · commit
253d1df · v1.76.0.0 fix: ship doc-sync survives Conductor — spawned subagent sessions reachable (#2733) (#2741)
2026-08-29 · commit
07b59e3 · v1.75.0.0 feat: ponytail import wave — simplification review lens, arm benchmark, reuse ladder, instruction-tier digest (#2722)
2026-08-27 · commit
394db32 · v1.71.0.0 feat: token-load reduction — preamble runtime scripts, gated onboarding, 20 skill carves, CLAUDE.md trim (#2691)
2026-08-19 · commit
28d59ad · v1.68.0.0 fix: next tracker wave — 16 verified fixes in, 90 stale PRs and 21 issues closed with receipts (#2632)
2026-08-17 · commit
ae8914a · v1.67.0.0 fix: the tracker wave — XProtect self-heal, complete installs, brain-sync integrity, 31 community PRs credited (#2604)
2026-08-15 · commit
2be6c06 · v1.65.0.0 feat: fork port wave 2 — feature fixes, session persistence, Apple releases, supply-chain CI (#2577)
2026-08-15 · commit
008dd65 · v1.64.0.0 fix wave: full tracker audit — 90 fixes, 52 issues closed, ~50 community PRs absorbed (#2571)
2026-08-12 · commit
d078622 · v1.62.0.0 feat: plan-mode auto-select at the review scope gate (#2533)
2026-08-08 · commit
94993f7 · v1.61.0.0 fix wave: guards failing open / silent failures (9 fixes, 4 community PRs absorbed) (#2472)
2026-07-14 · commit
7efb596 · docs(ios-qa): document regeneration and device verification flow
2026-06-25 · commit
11de390 · v1.58.5.0 feat: first-run activation scaffold + gstack router front door (#2078)
2026-06-14 · commit
c7ae632 · v1.58.1.0 feat: hermetic local E2E + Conductor prose AskUserQuestion (#2004)
2026-06-08 · commit
45cc95d · v1.57.5.0 feat: cross-session decision memory + gbrain dream-stage call graph (#1910)
2026-06-08 · commit
41c6d3e · v1.57.4.0 refactor(ethos): rename Boil the Lake principle to Boil the Ocean (#1912)
2026-06-08 · commit
4dfdb7c · v1.57.2.0 feat: AskUserQuestion prose fallback when the tool fails at runtime (#1908)
2026-06-04 · commit
cab774c · v1.56.0.0 Token-reduction Phase B + AUQ paranoid safety net (#1849)
2026-06-03 · commit
c43c850 · v1.55.1.0 fix: telemetry consent accuracy + gstack-slug cache sanitization (#1848)
2026-05-29 · commit
ce5fbfa · v1.52.0.0 feat(plan-tune): explicit consent + first-run setup wizard for contributors (#1741)
2026-05-27 · commit
a6fb317 · v1.48.0.0 feat: AskUserQuestion split rule + runtime AUTO_DECIDE carve-out (#1740)
2026-05-27 · commit
f8bb590 · v1.47.0.0 feat: /spec — author backlog-ready spec in 5 phases + optional agent spawn (#1698) (#1733)
2026-05-26 · commit
22f8c7f · v1.46.0.0 feat: gstack v2 foundation — catalog tokens drop 56%, eval-first floor covers all 51 skills (#1712)
2026-05-21 · commit
1d9b9c4 · v1.43.0.0 feat: iOS device-farm (5 skills, Mac daemon, Tailscale) (#1574)
Archived snapshots