# Gs:skillify > Package a custom developer workflow into a reusable agent skill. (gstack) - **Type:** Skill - **Install:** `agentstack add skill-thanh-abaii-gstack-windows-port-gstack-skillify` - **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior - **Seller:** [thanh-abaii](https://agentstack.voostack.com/s/thanh-abaii) - **Installs:** 0 - **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills) - **Latest version:** 0.1.0 - **License:** MIT - **Upstream author:** [thanh-abaii](https://github.com/thanh-abaii) - **Source:** https://github.com/thanh-abaii/gstack-windows-port/tree/main/skills/gstack-skillify ## Install ```sh agentstack add skill-thanh-abaii-gstack-windows-port-gstack-skillify ``` Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent. ## About ## Preamble (run first) ```bash python "bin/gstack-boot.py" --skill skillify | iex ``` ## When to invoke this skill Use when the user explicitly asks to package, skillify, or automate a series of manual steps or command history into a reusable, structured gstack skill. ## Plan Mode Safe Operations In plan mode, allowed because they inform the plan: `$B`, `$D`, `codex exec`/`codex review`, writes to `$HOME/.gstack/`, writes to the plan file, and `open` (or `Start-Process`) for generated artifacts. ## Skill Invocation During Plan Mode If the user invokes a skill in plan mode, the skill takes precedence over generic plan mode behavior. **Treat the skill file as executable instructions, not reference.** Follow it step by step starting from Step 0; the first AskUserQuestion is the workflow entering plan mode, not a violation of it. AskUserQuestion (any variant — `mcp__*__AskUserQuestion` or native; see "AskUserQuestion Format → Tool resolution") satisfies plan mode's end-of-turn requirement. If no variant is callable, the skill is BLOCKED — stop and report `BLOCKED — AskUserQuestion unavailable` per the AskUserQuestion Format rule. At a STOP point, stop immediately. Do not continue the workflow or call ExitPlanMode there. Commands marked "PLAN MODE EXCEPTION — ALWAYS RUN" execute. Call ExitPlanMode only after the skill workflow completes, or if the user tells you to cancel the skill or leave plan mode. If `PROACTIVE` is `"false"`, do not auto-invoke or proactively suggest skills. If a skill seems useful, ask: "I think /skillname might help here — want me to run it?" If `SKILL_PREFIX` is `"true"`, suggest/invoke `/gstack-*` names. Disk paths stay `$HOME/.claude/skills/gstack/[skill-name]/SKILL.md`. If output shows `UPGRADE_AVAILABLE `: read `$HOME/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If output shows `JUST_UPGRADED `: print "Running gstack v{to} (just updated!)". If `SPAWNED_SESSION` is true, skip feature discovery. Feature discovery, max one prompt per session: - Missing `$HOME/.claude/skills/gstack/.feature-prompted-continuous-checkpoint`: AskUserQuestion for Continuous checkpoint auto-commits. If accepted, run `python "bin/gstack-config.py" set checkpoint_mode continuous`. Always create marker. - Missing `$HOME/.claude/skills/gstack/.feature-prompted-model-overlay`: inform "Model overlays are active. MODEL_OVERLAY shows the patch." Always create marker. After upgrade prompts, continue workflow. If `WRITING_STYLE_PENDING` is `yes`: ask once about writing style: > v1 prompts are simpler: first-use jargon glosses, outcome-framed questions, shorter prose. Keep default or restore terse? Options: - A) Keep the new default (recommended — good writing helps everyone) - B) Restore V0 prose — set `explain_level: terse` If A: leave `explain_level` unset (defaults to `default`). If B: run `python "bin/gstack-config.py" set explain_level terse`. Always run (regardless of choice): ```powershell Remove-Item -Force "$HOME/.gstack/.writing-style-prompt-pending" -ErrorAction SilentlyContinue New-Item -Path "$HOME/.gstack/.writing-style-prompted" -ItemType File -Force ``` Skip if `WRITING_STYLE_PENDING` is `no`. If `LAKE_INTRO` is `no`: say "gstack follows the **Boil the Lake** principle — do the complete thing when AI makes marginal cost near-zero. Read more: https://garryslist.org/posts/boil-the-ocean" Offer to open: ```powershell Start-Process "https://garryslist.org/posts/boil-the-ocean" New-Item -Path "$HOME/.gstack/.completeness-intro-seen" -ItemType File -Force ``` Only run `Start-Process` if yes. Always run `New-Item`. If `TEL_PROMPTED` is `no` AND `LAKE_INTRO` is `yes`: ask telemetry once via AskUserQuestion: > Help gstack get better. Share usage data only: skill, duration, crashes, stable device ID. No code, file paths, or repo names. Options: - A) Help gstack get better! (recommended) - B) No thanks If A: run `python "bin/gstack-config.py" set telemetry community` If B: ask follow-up: > Anonymous mode sends only aggregate usage, no unique ID. Options: - A) Sure, anonymous is fine - B) No thanks, fully off If B→A: run `python "bin/gstack-config.py" set telemetry anonymous` If B→B: run `python "bin/gstack-config.py" set telemetry off` Always run: ```powershell New-Item -Path "$HOME/.gstack/.telemetry-prompted" -ItemType File -Force ``` Skip if `TEL_PROMPTED` is `yes`. If `PROACTIVE_PROMPTED` is `no` AND `TEL_PROMPTED` is `yes`: ask once: > Let gstack proactively suggest skills, like /qa for "does this work?" or /investigate for bugs? Options: - A) Keep it on (recommended) - B) Turn it off — I'll type /commands myself If A: run `python "bin/gstack-config.py" set proactive true` If B: run `python "bin/gstack-config.py" set proactive false` Always run: ```powershell New-Item -Path "$HOME/.gstack/.proactive-prompted" -ItemType File -Force ``` Skip if `PROACTIVE_PROMPTED` is `yes`. If `HAS_ROUTING` is `no` AND `ROUTING_DECLINED` is `false` AND `PROACTIVE_PROMPTED` is `yes`: Check if a CLAUDE.md file exists in the project root. If it does not exist, create it. Use AskUserQuestion: > gstack works best when your project's CLAUDE.md includes skill routing rules. Options: - A) Add routing rules to CLAUDE.md (recommended) - B) No thanks, I'll invoke skills manually If A: Append this section to the end of CLAUDE.md: ```markdown ## Skill routing When the user's request matches an available skill, invoke it via the Skill tool. When in doubt, invoke the skill. Key routing rules: - Product ideas/brainstorming → invoke /office-hours - Strategy/scope → invoke /plan-ceo-review - Architecture → invoke /plan-eng-review - Design system/plan review → invoke /design-consultation or /plan-design-review - Full review pipeline → invoke /autoplan - Bugs/errors → invoke /investigate - QA/testing site behavior → invoke /qa or /qa-only - Code review/diff check → invoke /review - Visual polish → invoke /design-review - Ship/deploy/PR → invoke /ship or /land-and-deploy - Save progress → invoke /context-save - Resume context → invoke /context-restore - Author a backlog-ready spec/issue → invoke /spec ``` Then commit the change: `git add CLAUDE.md && git commit -m "chore: add gstack skill routing rules to CLAUDE.md"` If B: run `python "bin/gstack-config.py" set routing_declined true` and say they can re-enable with `python "bin/gstack-config.py" set routing_declined false`. This only happens once per project. Skip if `HAS_ROUTING` is `yes` or `ROUTING_DECLINED` is `true`. If `VENDORED_GSTACK` is `yes`, warn once via AskUserQuestion unless `$HOME/.gstack/.vendoring-warned-$SLUG` exists: > This project has gstack vendored in `.claude/skills/gstack/`. Vendoring is deprecated. > Migrate to team mode? Options: - A) Yes, migrate to team mode now - B) No, I'll handle it myself If A: 1. Run `git rm -r .claude/skills/gstack/` 2. Run `Add-Content .gitignore '.claude/skills/gstack/'` 3. Run `python "bin/gstack-team-init.py" required` (or `optional`) 4. Run `git add .claude/ .gitignore CLAUDE.md && git commit -m "chore: migrate gstack from vendored to team mode"` 5. Tell the user: "Done. Each developer now runs: `cd $HOME/.claude/skills/gstack ; ./setup --team`" If B: say "OK, you're on your own to keep the vendored copy up to date." Always run (regardless of choice): ```powershell # Get project slug and create warned marker $slug = python "bin/gstack-slug.py" New-Item -Path "$HOME/.gstack/.vendoring-warned-$slug" -ItemType File -Force ``` If marker exists, skip. If `SPAWNED_SESSION` is `"true"`, you are running inside a session spawned by an AI orchestrator (e.g., OpenClaw). In spawned sessions: - Do NOT use AskUserQuestion for interactive prompts. Auto-choose the recommended option. - Do NOT run upgrade checks, telemetry prompts, routing injection, or lake intro. - Focus on completing the task and reporting results via prose output. - End with a completion report: what shipped, decisions made, anything uncertain. ## AskUserQuestion Format ### Tool resolution (read first) "AskUserQuestion" can resolve to two tools at runtime: the **host MCP variant** (e.g. `mcp__conductor__AskUserQuestion` — appears in your tool list when the host registers it) or the **native** Claude Code tool. **Rule:** if any `mcp__*__AskUserQuestion` variant is in your tool list, prefer it. Hosts may disable native AUQ via `--disallowedTools AskUserQuestion` (Conductor does, by default) and route through their MCP variant; calling native there silently fails. Same questions/options shape; same decision-brief format applies. **If no AskUserQuestion variant appears in your tool list, this skill is BLOCKED.** Stop, report `BLOCKED — AskUserQuestion unavailable`, and wait for the user. Do not write decisions to the plan file as a substitute, do not emit them as prose and stop, and do not silently auto-decide (only `/plan-tune` AUTO_DECIDE opt-ins authorize auto-picking). ### Format Every AskUserQuestion is a decision brief and must be sent as tool_use, not prose. ``` D — Project/branch/task: ELI10: Stakes if we pick wrong: Recommendation: because Completeness: A=X/10, B=Y/10 (or: Note: options differ in kind, not coverage — no completeness score) Pros / cons: A) (recommended) ✅ ❌ B) ✅ ❌ Net: ``` D-numbering: first question in a skill invocation is `D1`; increment yourself. This is a model-level instruction, not a runtime counter. ELI10 is always present, in plain English, not function names. Recommendation is ALWAYS present. Keep the `(recommended)` label; AUTO_DECIDE depends on it. Completeness: use `Completeness: N/10` only when options differ in coverage. 10 = complete, 7 = happy path, 3 = shortcut. If options differ in kind, write: `Note: options differ in kind, not coverage — no completeness score.` Pros / cons: use ✅ and ❌. Minimum 2 pros and 1 con per option when the choice is real; Minimum 40 characters per bullet. Hard-stop escape for one-way/destructive confirmations: `✅ No cons — this is a hard-stop choice`. Neutral posture: `Recommendation: — this is a taste call, no strong preference either way`; `(recommended)` STAYS on the default option for AUTO_DECIDE. Effort both-scales: when an option involves effort, label both human-team and CC+gstack time, e.g. `(human: ~2 days / CC: ~15 min)`. Makes AI compression visible at decision time. Net line closes the tradeoff. Per-skill instructions may add stricter rules. ### Handling 5+ options — split, never drop AskUserQuestion caps every call at **4 options**. With 5+ real options, NEVER drop, merge, or silently defer one to fit. Pick a compliant shape: - **Batch into ≤4-groups** — for coherent alternatives (e.g. version bumps, layout variants). One call, 5th surfaced only if first 4 don't fit. - **Split per-option** — for independent scope items (e.g. "ship E1..E6?"). Fire N sequential calls, one per option. Default to this when unsure. Per-option call shape: `D.k` header (e.g. D3.1..D3.5), ELI10 per option, Recommendation, kind-note (no completeness score — Include/Defer/Cut/Hold are decision actions), and 4 buckets: **A) Include**, **B) Defer**, **C) Cut**, **D) Hold** (stop chain, discuss). After the chain, fire `D.final` to validate the assembled set (reprompt dependency conflicts) and confirm shipping it. Use `D.revise-` to revise one option without re-running the chain. For N>6, fire a `D.0` meta-AskUserQuestion first (proceed / narrow / batch). question_ids for split chains: `-split-` (kebab-case ASCII, ≤64 chars, `-2`/`-3` suffix on collision). The runtime checker (`bin/gstack-question-preference.py`) refuses `never-ask` on any `*-split-*` id, so split chains are never AUTO_DECIDE-eligible — the user's option set is sacred. Full rule + worked examples + Hold/dependency semantics: see `docs/askuserquestion-split.md` in the gstack repo. Read on demand when N>4. Non-ASCII characters — write directly, never \u-escape. When any string field (question, option label, option description) contains Chinese (繁體/簡體), Japanese, Korean, or other non-ASCII text, emit the literal UTF-8 characters in the JSON string. **Never escape them as `\uXXXX`.** Claude Code's tool parameter pipe is UTF-8 native and passes characters through unchanged. Manually escaping requires recalling each codepoint from training, which is unreliable for long CJK strings — the model regularly emits the wrong codepoint (e.g. writes `\u3103` thinking it is 管 U+7BA1, but `\u3103` is actually ㄃, so the user sees `管理工具` rendered as `㄃3用箱`). The trigger is long, multi-line questions with hundreds of CJK characters: that is exactly when reflexive escaping kicks in and exactly when miscoding is most damaging. Long ≠ escape. Keep characters literal. Wrong: `"question": "請選擇\uXXXX\uXXXX\uXXXX\uXXXX"` Right: `"question": "請選擇管理工具"` Only JSON-mandatory escapes remain allowed: `\n`, `\t`, `\"`, `\\`. ### Self-check before emitting Before calling AskUserQuestion, verify: - [ ] D header present - [ ] ELI10 paragraph present (stakes line too) - [ ] Recommendation line present with concrete reason - [ ] Completeness scored (coverage) OR kind-note present (kind) - [ ] Every option has ≥2 ✅ and ≥1 ❌, each ≥40 chars (or hard-stop escape) - [ ] (recommended) label on one option (even for neutral-posture) - [ ] Dual-scale effort labels on effort-bearing options (human / CC) - [ ] Net line closes the decision - [ ] You are calling the tool, not writing prose - [ ] Non-ASCII characters (CJK / accents) written directly, NOT \u-escaped - [ ] If you had 5+ options, you split (or batched into ≤4-groups) — did NOT drop any - [ ] If you split, you checked dependencies between options before firing the chain - [ ] If a per-option Hold fires, you stopped the chain immediately (didn't queue) ## Artifacts Sync (skill start) ```powershell $gstackHome = $env:GSTACK_HOME if (!$gstackHome) { $gstackHome = "$HOME/.gstack" } # Prefer the v1.27.0.0 artifacts file; fall back to brain file for users # upgrading mid-stream before the migration script runs. $brainRemoteFile = "$HOME/.gstack-artifacts-remote.txt" if (!(Test-Path $brainRemoteFile)) { $brainRemoteFile = "$HOME/.gstack-brain-remote.txt" } # Teach the agent to use gbrain when it's available. $gbrainConfig = "$HOME/.gbrain/config.json" $hasGBrain = Get-Command gbrain -ErrorAction SilentlyContinue if ((Test-Path $gbrainConfig) -and $hasGBrain) { # GBrain logic Write-Host "GBrain configured. Prefer 'gbrain search'/'gbrain query' over Grep" } ``` Privacy stop-gate: if output shows sync is off, ask once via AskUserQuestion options. At skill END before telemetry: ```powershell python "bin/gstack-brain-sync.py" --discover-new python "bin/gstack-brain-sync.py" --once ``` ## Model-Specific Behavioral Patch (claude) The following nudges are tuned for the claude model family. They are **subordinate** to skill workflow, STOP points, AskUserQuestion gates, plan-mode safety, and /ship review gates. If a nudge below conflicts with skill instructions, the skill wins. Treat these as preferences, not rules. **Todo-list discipline.** When working through a multi-step plan, mark each task complete individually as you finish it. Do not batch-complete at the end. If a task turns out to be unnecessary, mark it skipped with a one-line reason. **Think before heavy actions.** For complex operations (refactors, migrations, non-trivial new features), briefly state your approach before executing. This lets the user course-correct cheaply instead of mid-flight. **Dedicated tools over Bash.** Prefer Read, Edit, Write, Glob, Grep over shell equivalents (cat, sed, find, grep). The dedicated tools are cheaper and clearer. ## Voice GStack voice: Garry-shaped product and engineering judgment, compressed for runtime. - … ## Source & license This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code. - **Author:** [thanh-abaii](https://github.com/thanh-abaii) - **Source:** [thanh-abaii/gstack-windows-port](https://github.com/thanh-abaii/gstack-windows-port) - **License:** MIT Install and usage instructions live in the source repository linked above. ## Pricing - **Free** — Free ## Security capabilities Automated source analysis of v0.1.0 — what this tool can access: - **Network access:** no - **Filesystem access:** yes - **Shell / process execution:** no - **Environment & secrets:** no - **Dynamic code execution:** no *"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.* ## Versions - **0.1.0** — security scan: passed — Imported from the upstream source. ## Links - Listing page: https://agentstack.voostack.com/l/skill-thanh-abaii-gstack-windows-port-gstack-skillify - Seller: https://agentstack.voostack.com/s/thanh-abaii - Browse the marketplace: https://agentstack.voostack.com/browse --- Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.