New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Show Spec Working

by LIDR-academy in LIDR-academy/AI4Devs-LTI-extended

A skill your agent uses when the user asks "show me X", "demo X", "walk me through X", "how X works" or requests a live feature demonstration from a spec, feature or ticket.

MITAuto-check passedProduct & Project Management

Install Show Spec Working

skills CLI
$ npx skills add LIDR-academy/AI4Devs-LTI-extended --skill show-spec-working -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install LIDR-academy/AI4Devs-LTI-extended show-spec-working --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/LIDR-academy/AI4Devs-LTI-extended.git skills-src && mkdir -p .claude/skills && cp -r skills-src/ai-specs/skills/show-spec-working .claude/skills/show-spec-working && rm -rf skills-src

Use ~/.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/

Facts

Skill name
show-spec-working
GitHub stars
278
Token cost
~1.1k tokens
SKILL.md length
570 words
Files
1
Skills in repo
9
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when the user asks "show me X", "demo X", "walk me through X", "how X works" or requests a live feature demonstration from a spec, feature or ticket.

  • Works in 4 steps: Resolve target spec and scope → 1 - Anti-report guardrail → Frontend demonstration path → …
  • The user asks show me X
  • SKILL.md covers Trigger phrases (high priority), Inputs, Workflow and Browser MCP requirements, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Show Spec Working is an agent skill from LIDR-academy/AI4Devs-LTI-extended. Use when the user asks "show me X", "demo X", "walk me through X", "how X works" or requests a live feature demonstration from a spec, feature or ticket.

Its SKILL.md is about 1.1k 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. The repository describes itself as: Repository with several experiments from live sessions. The licence is MIT.

When your agent uses it

  • The user asks show me X
  • Walk me through X
  • Requests a live feature demonstration from a spec

Example prompts

  • “show me X”
  • “demo X”
  • “walk me through X”
  • “/show-spec-working”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Resolve target spec and scope
  2. 1 - Anti-report guardrail
  3. Frontend demonstration path
  4. Backend API demonstration path

What it can do on your machine

Read from SKILL.md and the folder at commit 9ff9a80. 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 (its code samples are markdown).

    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

Show Spec Working loads about 1.1k tokens when it runs. Until then it costs about 43 tokens; SKILL.md has 570 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~43
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

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 LIDR-academy/AI4Devs-LTI-extended at commit 9ff9a80, republished under its MIT licence (© LIDR-academy). 570 words, ~1,121 tokens.

Download SKILL.mdSave it as .claude/skills/show-spec-working/SKILL.md (or your agent's skills folder).
name
show-spec-working
description
Use when the user asks "show me X", "demo X", "walk me through X", "how X works" or requests a live feature demonstration from a spec, feature or ticket.
author
LIDR.co
version
1.0.0

show-spec-working Skill

Demonstrate a spec in a runnable way.

If the user does not provide explicit context, use the spec/change currently being worked on in this session.

Always end by reporting completion in chat.

Trigger phrases (high priority)

Treat these expressions as execution commands, not analysis requests:

  • show me X
  • demo X
  • walk me through X
  • show X working
  • how X works
  • prove X works

When any of these appear, run the demonstration workflow directly. Do not stop at a feature summary or quick report.

Inputs

  • Optional spec context from user:
    • Direct ticket id in text (for example: SCRUM-10)
    • Feature name
    • Endpoint
    • Frontend route
  • If missing, infer from current session context and currently active work.

Workflow

Step 1 - Resolve target spec and scope
  1. Identify the target spec/change:
    • Prefer explicit user-provided context.
    • If user text contains a ticket id pattern like [A-Z]+-[0-9]+, use it as primary context (example: show me SCRUM-10).
    • Otherwise, infer the spec currently being worked on.
  2. Determine modality:
    • frontend when the spec includes UI behavior.
    • backend-only when it only defines API behavior.
    • mixed when both exist.
  3. List concrete scenarios to demo from the spec acceptance criteria.
Step 1.1 - Anti-report guardrail

Before continuing, enforce this rule:

  • Never finish after only analyzing requirements.
  • Never return only a quick report when the user asked to "show" or "demo".
  • If execution is blocked, explicitly report the blocker and ask for exactly what is needed to continue the live demo.
Step 2 - Frontend demonstration path

Run this path when modality is frontend or mixed.

  1. Start required local services if needed.
  2. Use browser automation to open the app and navigate to the target feature.
  3. Demonstrate feature behavior from the spec, one interaction at a time.
    • Example sequence for list/table features:
      • Open listing page
      • Verify table data appears
      • Use search box
      • Apply filters
      • Change sorting
      • Open details view
  4. After each meaningful action:
    • Verify visible result matches spec expectations.
  5. Stop on a stable end state and let the user continue manual exploration or close the window.
  6. Keep the browser open unless the user asks to close it.
Show full SKILL.md (220 more words)Show less
Step 3 - Backend API demonstration path

Run this path when modality is backend-only or mixed.

  1. Identify the endpoint(s) and sample payload(s) defined by the spec.
  2. Execute curl command(s) that show real response behavior.
  3. If any call changes data state (CREATE/UPDATE/DELETE):
    • Execute the paired restore/reset curl command (or equivalent restore action) immediately after demonstrating the behavior.
  4. Confirm restored state so repeated demos remain deterministic.
  5. Include command and key response evidence in chat (concise).

Browser MCP requirements

Before calling any MCP browser tool:

  1. Read the MCP tool descriptor JSON first.
  2. Follow the server instructions for lock/unlock and snapshot-refresh workflow.
  3. Avoid repeated blind retries; if blocked, report blocker and best next action.

API demo requirements

  • Use explicit curl commands (not pseudocode) whenever environment data is available.
  • Mask sensitive values in chat output.
  • Keep commands idempotent when possible.
  • Include restore commands for any state-changing operation.

Completion contract

Always send a final chat message containing:

  1. Target spec/change demonstrated.
  2. What was executed:
    • Frontend flows shown.
    • Backend curl commands executed.
  3. Verification result per demonstrated scenario (pass/fail with short note).
  4. Data restore status (if applicable).
  5. Final handoff:
    • "Demo complete. You can continue checking in the open browser window or ask me to close it."

Output format

Use this concise structure in the final chat response:

markdown
Spec demo completed for: <spec/change>

Frontend walkthrough:
- <step/result>

Backend API walkthrough:
- <curl + key response note>

Data restore:
- <restored / not needed / failed + reason>

Next:
- You can continue in the open browser window, or ask me to close it.

© LIDR-academy, 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 ai-specs/skills/show-spec-working of LIDR-academy/AI4Devs-LTI-extended.

Open the folder on GitHubat commit 9ff9a80

Compare with similar skills

Show Spec Working 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.

Show Spec Working compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Show Spec Working this skillLIDR-academy/AI4Devs-LTI-extended278—~1.1kAutomated safety check: PassMIT
User Story Writerdeanpeters/Product-Manager-Skills7.2k2 repos~2.9kAutomated safety check: PassCustom licence
Game Changing FeaturesopenstatusHQ/data-table-filters2.3k3 repos~2.1kAutomated safety check: PassMIT
CCPM Project Managementautomazeio/ccpm8.4k—~1.1kAutomated safety check: PassMIT
Convex Create Componentspokvulcan/poker-planning1158 repos~2.6kAutomated safety check: PassMIT
Self Improving Agentfarm-fe/farm5.6k2 repos~3.3kAutomated safety check: NotesMIT

Similar skills

  • User Story Writer

    deanpeters/Product-Manager-Skills

    Writes user stories in Mike Cohn's format with Gherkin acceptance criteria, turning user needs into development-ready work with testable conditions.

    7.2k GitHub starsUsed in 2 repos~2.9k tokens
    Product & Project ManagementAuto-check passed

  • Game Changing Features

    openstatusHQ/data-table-filters

    Find 10x product opportunities and high-leverage improvements.

    2.3k GitHub starsUsed in 3 repos~2.1k tokens
    Product & Project ManagementAuto-check passed

  • CCPM Project Management

    automazeio/ccpm

    Runs a spec-driven workflow from PRD to epic to GitHub issues to parallel agents, with status, standup and blocked-work reports from bundled scripts.

    8.4k GitHub stars~1.1k tokensUpdated 6 mo ago
    Product & Project ManagementAuto-check passed

  • Convex Create Component

    spokvulcan/poker-planning

    Builds reusable Convex components with isolated tables and app-facing APIs.

    115 GitHub starsUsed in 8 repos~2.6k tokens
    Product & Project ManagementAuto-check passed

  • Self Improving Agent

    farm-fe/farm

    A universal self-improving agent that learns from ALL skill experiences.

    5.6k GitHub starsUsed in 2 repos~3.3k tokens
    Product & Project ManagementAuto-check: notes

  • Weekly Engineering Retro

    garrytan/gstack

    Builds a weekly engineering retrospective from git history: commit counts, per-person contributions, work patterns and code quality numbers over a chosen window.

    136k GitHub stars~2.4k tokensUpdated today
    Product & Project ManagementAuto-check passed

More from LIDR-academy/AI4Devs-LTI-extended

All 9 skills in this repo

  • Owasp Security Audit

    LIDR-academy/AI4Devs-LTI-extended

    A skill your agent uses when performing a cybersecurity audit, security review, OWASP Top 10 compliance check, vulnerability assessment, or preparing for a penetration test on a…

    278 GitHub stars~4.3k tokensUpdated 4 mo ago
    Auto-check: notes

  • Sync Agent Symlinks

    LIDR-academy/AI4Devs-LTI-extended

    Analyze and synchronize agent skill exposure after ai-specs skill changes (additions, removals, renames).

    278 GitHub stars~1k tokensUpdated 4 mo ago
    Auto-check passed

  • Run Parallel Tasks

    LIDR-academy/AI4Devs-LTI-extended

    Run N feature tasks in parallel, each in its own worktree, following the full specboot pipeline (enrich → new → ff → apply → verify).

    278 GitHub stars~1.5k tokensUpdated 4 mo ago
    Auto-check passed

  • Commit

    LIDR-academy/AI4Devs-LTI-extended

    Create focused commits and pull requests following repository standards.

    278 GitHub stars~1.5k tokensUpdated 4 mo ago
    Auto-check: notes

  • Explain

    LIDR-academy/AI4Devs-LTI-extended

    Teach underlying concepts with clear mental models to close skill gaps behind user questions.

    278 GitHub stars~1.3k tokensUpdated 4 mo ago
    Auto-check passed

  • Enrich Us

    LIDR-academy/AI4Devs-LTI-extended

    Analyze and enhance Jira user stories with complete, implementation-ready technical detail.

    278 GitHub stars~521 tokensUpdated 4 mo ago
    Auto-check passed

Categories

Questions about Show Spec Working

What does Show Spec Working do?

A skill your agent uses when the user asks "show me X", "demo X", "walk me through X", "how X works" or requests a live feature demonstration from a spec, feature or ticket. Show Spec Working is an agent skill from LIDR-academy/AI4Devs-LTI-extended. Use when the user asks "show me X", "demo X", "walk me through X", "how X works" or requests a live feature demonstration from a spec, feature or ticket.

When should I use Show Spec Working?

Show Spec Working fits situations like: the user asks show me X; walk me through X; requests a live feature demonstration from a spec.

How do I install Show Spec Working in Claude Code?

Run `npx skills add LIDR-academy/AI4Devs-LTI-extended --skill show-spec-working -a claude-code`. Or copy the skill folder (ai-specs/skills/show-spec-working in LIDR-academy/AI4Devs-LTI-extended) into .claude/skills/show-spec-working in your project. Claude Code loads it when a task matches its description.

How do I install Show Spec Working in Codex?

Run `npx skills add LIDR-academy/AI4Devs-LTI-extended --skill show-spec-working -a codex`. Or copy the skill folder (ai-specs/skills/show-spec-working in LIDR-academy/AI4Devs-LTI-extended) into .agents/skills/show-spec-working in your project. Codex loads it when a task matches its description.

Can I use Show Spec Working 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 LIDR-academy/AI4Devs-LTI-extended --skill show-spec-working -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/show-spec-working, .gemini/skills/show-spec-working, .github/skills/show-spec-working and .opencode/skills/show-spec-working in your project.

What does Show Spec Working need to run?

SKILL.md names no scripts, command-line tools or credentials: Show Spec Working is instructions for the agent only.

Does Show Spec Working 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 Show Spec Working 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 Show Spec Working use?

Show Spec Working 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 Show Spec Working use?

About 1.1k tokens (SKILL.md is roughly 4.5k 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 Show Spec Working?

Skills that share tags, products or a category with Show Spec Working: User Story Writer (deanpeters/Product-Manager-Skills, 7.2k stars), Game Changing Features (openstatusHQ/data-table-filters, 2.3k stars), CCPM Project Management (automazeio/ccpm, 8.4k stars) and Convex Create Component (spokvulcan/poker-planning, 115 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Show Spec Working?

LIDR-academy (a GitHub organization) maintains it in LIDR-academy/AI4Devs-LTI-extended, which has 278 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on June 9, 2026.

Source: LIDR-academy/AI4Devs-LTI-extended on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.