Review
golbin/agent-skills
Review software designs and implementations for user experience, simplicity, and maintainability; apply fixes when requested.
Define user flows, screens, states, copy, and accessibility in ux.md.
Install Spectre UX
$ npx skills add joenandez/spectre --skill spectre-ux -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install joenandez/spectre spectre-ux --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/joenandez/spectre.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/spectre/skills/spectre-ux .claude/skills/spectre-ux && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "spectre-ux" agent skill from https://github.com/joenandez/spectre/tree/main/plugins/spectre/skills/spectre-ux into .claude/skills/spectre-ux/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spectre-ux", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/joenandez/spectre/tree/main/plugins/spectre/skills/spectre-uxType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add joenandez/spectre --skill spectre-ux -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install joenandez/spectre spectre-ux --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/joenandez/spectre.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/spectre/skills/spectre-ux .agents/skills/spectre-ux && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "spectre-ux" agent skill from https://github.com/joenandez/spectre/tree/main/plugins/spectre/skills/spectre-ux into .agents/skills/spectre-ux/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spectre-ux", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add joenandez/spectre --skill spectre-ux -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install joenandez/spectre spectre-ux --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/joenandez/spectre.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/spectre/skills/spectre-ux .cursor/skills/spectre-ux && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "spectre-ux" agent skill from https://github.com/joenandez/spectre/tree/main/plugins/spectre/skills/spectre-ux into .cursor/skills/spectre-ux/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spectre-ux", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/joenandez/spectre.git --path plugins/spectre/skills/spectre-ux--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add joenandez/spectre --skill spectre-ux -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install joenandez/spectre spectre-ux --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/joenandez/spectre.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/spectre/skills/spectre-ux .gemini/skills/spectre-ux && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "spectre-ux" agent skill from https://github.com/joenandez/spectre/tree/main/plugins/spectre/skills/spectre-ux into .gemini/skills/spectre-ux/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spectre-ux", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install joenandez/spectre spectre-uxInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add joenandez/spectre --skill spectre-ux -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/joenandez/spectre.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/spectre/skills/spectre-ux .github/skills/spectre-ux && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "spectre-ux" agent skill from https://github.com/joenandez/spectre/tree/main/plugins/spectre/skills/spectre-ux into .github/skills/spectre-ux/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spectre-ux", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add joenandez/spectre --skill spectre-ux -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install joenandez/spectre spectre-ux --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/joenandez/spectre.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/spectre/skills/spectre-ux .opencode/skills/spectre-ux && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "spectre-ux" agent skill from https://github.com/joenandez/spectre/tree/main/plugins/spectre/skills/spectre-ux into .opencode/skills/spectre-ux/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spectre-ux", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
spectre-ux- GitHub stars
- 164
- Token cost
- ~1.5k tokens
- SKILL.md length
- 657 words
- Files
- 1
- Skills in repo
- 26
- Repo updated
- First seen
- Licence
- MIT
At a glance
Define user flows, screens, states, copy, and accessibility in ux.md.
- Works in 3 steps: {OUT_DIR}/concepts/scope.md (canonical,… → {OUT_DIR}/specs/prd.md → {OUT_DIR}/task_summary.md
- Tasks that involve PRD writing
- SKILL.md covers Inputs, Working Set (late-bound — read…, Method / guardrails and Outputs + DONE, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Spectre UX is an agent skill from joenandez/spectre. Define user flows, screens, states, copy, and accessibility in ux.md. Two stages: align flows, then specify. Use after scope/PRD for behavioral UX; not backend, scope, or architecture.
Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Product & Project Management, covering PRD writing and UX design. The repository describes itself as: Spectre is a battle-tested 6 stage agentic engineering workflow for building complex, production-ready features. You stay in the loop for the decisions that matter. Your agents…. The licence is MIT.
When your agent uses it
- Tasks that involve PRD writing
- Tasks that involve UX design
Example prompts
- “/spectre-ux”
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- {OUT_DIR}/concepts/scope.md (canonical, preferred)
- {OUT_DIR}/specs/prd.md
- {OUT_DIR}/task_summary.md
What it can do on your machine
Read from SKILL.md and the folder at commit 931c9e8. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Spectre UX loads about 1.5k tokens when it runs. Until then it costs about 49 tokens; SKILL.md has 657 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from joenandez/spectre at commit 931c9e8, republished under its MIT licence (© joenandez). 657 words, ~1,512 tokens.
Download SKILL.mdSave it as
.claude/skills/spectre-ux/SKILL.md (or your agent's skills folder).- name
- spectre-ux
- description
- Define user flows, screens, states, copy, and accessibility in ux.md. Two stages: align flows, then specify. Use after scope/PRD for behavioral UX; not backend, scope, or architecture.
- user-invocable
- true
- disable-model-invocation
- true
ux
Turn requirements into a behavioral spec — what users see/do and the system response, not visual taste. Align flows, then write ux.md.
Inputs
$ARGUMENTS— explicit feature name/root or descendant requirements artifact.- Requirements — first present, read fully:
{OUT_DIR}/concepts/scope.md(canonical, preferred){OUT_DIR}/specs/prd.md{OUT_DIR}/task_summary.md
- If none exist → ask for scope context or recommend
/spectre:spectre-scopefirst; do not invent scope.
Working Set (late-bound — read at run-time, never inline)
- Reuse a managed
FEATURE_ROOTonly when explicit/current-thread evidence ties it to this work (physical directory wins; never branch/recency/lifecycle/scans); distinct work ignores ambient roots. Otherwise, including on collision, standalone MUST first load and follow@skill-spectre:spectre-feature-rootthrough DONE; orchestrated calls escalate. Keep writes beneath it and pass it unchanged. - Repair stale feature/root metadata in artifacts this workflow touches.
OUT_DIR = FEATURE_ROOT.- Existing UI: one Stage-1
@spectre:patternsdispatch for similar screens/tokens — ≤~2K in-thread, no files.
Method / guardrails
Stage 1 — Flow discovery & alignment (align before specifying).
- Identify user segments: first-time/returning, anon/signed-in, free/paid, role-based.
- Identify goals, entry points, and completion states.
- Narrate each flow: Goal · Entry · User sees → User does → System responds · branches · success · Questions; call out segment divergence.
- Present a take and ask for pushback. Every initial or feedback-revised flow presentation ends with the compact handoff table:
| Handoff | Details |
|---|---|
| 🧭 Current phase | Flow approval. |
| 📦 What was just done | Initial or revised flows. |
| ▶️ Proposed next step | Render resolved action. |
CONTINUATION: Prototype when interaction, layout, visual validation, or stakeholder review materially matters; otherwise Plan when Scope + flows suffice. Render/spectre:spectre-prototype {FEATURE_ROOT} FROM_UX=trueor/spectre:spectre-plan {FEATURE_ROOT}; at most one explicit conditional alternative.- Flows approved: complete {OUT_DIR}/ux.md, then Prototype or Plan with resolved values.
- GATE: Never write
{OUT_DIR}/ux.mdbefore explicit flow approval + selected continuation. Feedback without approval → revise and re-present. Ambiguous approval or missing route authority → ask only the unresolved choice.
Stage 2 — Detailed spec (only after explicit flow approval + selected continuation).
- That reply clears Stage 1: complete
{OUT_DIR}/ux.md, then invoke the selected workflow in the same run with no second gate. Resolve from approved flows; ask only for missing irreversible authority.
Show full SKILL.md (328 more words)Show less
Outputs + DONE
Write {FEATURE_ROOT}/ux.md with all 11 sections. Below its title:
Feature: <feature-name>
Feature Root: .spectre/features/<feature-name>Derive both values from the physical feature directory.
- Overview — problem and primary goal (1 para)
- User Segments — served segments and UX differences
- Screens — name, purpose, navigation
- Flows — Stage 1 plus validation-fail, cancel, network-error, and segment branches
- Layouts — header/main/footer and responsive behavior (desktop >1024 · tablet 768–1024 · mobile <768)
- Components — interactive purpose, location, applicable State Vocabulary
- Interactions — table: Element | Action | Result (exhaustive)
- States — table: State | Trigger | Appearance | Available Actions. For externally driven states, tie triggers to observed events when available; flag assumptions and common observed events with no state for Execute's probe.
- Content — exact titles, buttons, empty/error/confirmation copy
- Edge Cases — limits, data, permission, network, segments
- Accessibility — tab order, Enter/Space/Escape, announcements, focus
State Vocabulary — pick relevant states:
- Visual: default, hover, focus, active/pressed, disabled; Data: empty, loading, partial-loaded, loaded, error, stale/refreshing
- Form: pristine, dirty, touched, submitting, submitted-success, submitted-error, per-field validation-error; Selection: none, single, multi, partial-selection, all-selected
- Sync: optimistic, pending, conflict, resolved; Network: online, offline, reconnecting
DONE when: the Stage-1 flow gate was cleared (user approved flows); ux.md exists with all 11 sections; segments addressed; flows carry alternate paths; Interactions and States tables use the exact column formats above; component states are drawn from the State Vocabulary; layouts state the responsive breakpoints; accessibility and edge cases covered.
Handoff
| Handoff | Details |
|---|---|
| 🧭 Current phase | Done |
| 📦 What was just done | Result |
| ▶️ Proposed next step | Render resolved action; no placeholders. |
Confirm UX/doc path. Material visual/interaction/stakeholder/prose-limit → Prototype (apply assumptions to ux.md); otherwise confirmed repository-changing work → /spectre:spectre-plan. One route/conditional; read-only may stop/Handoff.
Escalate-If
- No scope/PRD/summary found → stop; get scope context or route to
/spectre:spectre-scopebefore specifying. - User pushes for implementation/architecture decisions → note them, defer to
/spectre:spectre-plan; keep this pass on behavior. - Flows won't converge after iterating → surface the specific unresolved divergence (usually a segment conflict) and ask the user to decide before Stage 2.
- Feature has no user-facing surface → this spec adds nothing; route back to
/spectre:spectre-plan.
© joenandez, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in plugins/spectre/skills/spectre-ux of joenandez/spectre.
Open the folder on GitHubat commit 931c9e8
Compare with similar skills
Spectre UX next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Spectre UX this skilljoenandez/spectre | 164 | — | ~1.5k | Automated safety check: Pass | MIT | |
| Reviewgolbin/agent-skills | 214 | — | ~706 | Automated safety check: Pass | None | |
| Prd UX DesignOfficeDev/microsoft-365-agents-toolkit | 780 | — | ~8.1k | Automated safety check: Pass | Custom licence | |
| Product Developmentgustavscirulis/snapgrid | 116 | 1 repos | ~1.1k | Automated safety check: Pass | Custom licence | |
| Vscuse Scenario AuthoringOfficeDev/microsoft-365-agents-toolkit | 780 | — | ~4.3k | Automated safety check: Pass | Custom licence | |
| Write Product Specbholmesdev/hubble.md | 1.5k | — | ~966 | Automated safety check: Pass | MIT |
Similar skills
Prd UX Design
OfficeDev/microsoft-365-agents-toolkit
A skill your agent uses when adding or changing product requirements, scenarios, user flows, surface behavior, or design artifacts before specs or implementation.
Product Development
gustavscirulis/snapgrid
End-to-end product development for iOS/macOS apps. An agent skill from gustavscirulis/snapgrid.
Vscuse Scenario Authoring
OfficeDev/microsoft-365-agents-toolkit
A skill your agent uses when: reading a docs scenario, PRD, mockup, or user flow and using vscuse-ui/noVNC as the primary authoring surface to record, generate, replace, or update vscuse test plans…
Write Product Spec
bholmesdev/hubble.md
Write a PRODUCT.md spec for a significant Hubble user-facing feature, focused only on user experience and observable behavior.
Opportunity Assessment
andreaskelm/pm-brain
Assess whether an idea, feature request, or opportunity is worth pursuing before anyone writes a PRD.
More from joenandez/spectre
All 26 skills in this repoVerify Spectre
joenandez/spectre
A skill your agent uses when validating that the Spectre plugin itself still works after ANY change to this repo — skills, prompts, agents, hooks, the CLI, the Codex mirror, or a release.
Feature Codex Spectre Implementation
joenandez/spectre
A skill your agent uses when modifying the Codex SPECTRE install flow, SessionStart continuity, project skill syncing, registry injection, or Codex-specific runtime files.
Spectre Handoff
joenandez/spectre
Save a quiet, branch-keyed session snapshot with continuity, active work, and optional task/todo state for automatic resume.
Spectre Learn
joenandez/spectre
User-invoked front door for durable capture. An agent skill from joenandez/spectre.
Spectre Rewrite Skill
joenandez/spectre
Rewrite a verbose SPECTRE skill into a compact, contract-form Spectre skill proposal — clear on WHAT, silent on HOW — grounded in the spectre-light distillation and freedom-tier budget.
Spectre Rewrite Subagent
joenandez/spectre
Rewrite Spectre subagent definitions into compact, contract-driven agents with clear routing, least-privilege tools, output schemas, and an auditable rewrite trail.
Related
Questions about Spectre UX
What does Spectre UX do?
Define user flows, screens, states, copy, and accessibility in ux.md. Spectre UX is an agent skill from joenandez/spectre.md.
When should I use Spectre UX?
Spectre UX fits situations like: tasks that involve PRD writing; tasks that involve UX design.
How do I install Spectre UX in Claude Code?
Run `npx skills add joenandez/spectre --skill spectre-ux -a claude-code`. Or copy the skill folder (plugins/spectre/skills/spectre-ux in joenandez/spectre) into .claude/skills/spectre-ux in your project. Claude Code loads it when a task matches its description.
How do I install Spectre UX in Codex?
Run `npx skills add joenandez/spectre --skill spectre-ux -a codex`. Or copy the skill folder (plugins/spectre/skills/spectre-ux in joenandez/spectre) into .agents/skills/spectre-ux in your project. Codex loads it when a task matches its description.
Can I use Spectre UX in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add joenandez/spectre --skill spectre-ux -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/spectre-ux, .gemini/skills/spectre-ux, .github/skills/spectre-ux and .opencode/skills/spectre-ux in your project.
What does Spectre UX need to run?
SKILL.md names no scripts, command-line tools or credentials: Spectre UX is instructions for the agent only.
Does Spectre UX access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Spectre UX safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Spectre UX use?
Spectre UX is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Spectre UX use?
About 1.5k tokens (SKILL.md is roughly 6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Spectre UX?
Skills that share tags, products or a category with Spectre UX: Review (golbin/agent-skills, 214 stars), Prd UX Design (OfficeDev/microsoft-365-agents-toolkit, 780 stars), Product Development (gustavscirulis/snapgrid, 116 stars) and Vscuse Scenario Authoring (OfficeDev/microsoft-365-agents-toolkit, 780 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Spectre UX?
joenandez (a GitHub user) maintains it in joenandez/spectre, which has 164 GitHub stars. The repository holds 26 skills in this directory. The repository was last updated on October 2, 2026.
Source: joenandez/spectre on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.