Qwen Code E2E Testing
QwenLM/qwen-code
Guides end-to-end testing of the Qwen Code CLI in headless mode with real model calls, MCP test servers and inspection of raw API traffic.
Checks a Suede AI MCP server release against a live process: the full JSON-RPC lifecycle, schemas, annotations, malformed input, catalog agreement and install docs.
Install Suede MCP Release QA
$ npx skills add JasonColapietro/suede-creator-skills --skill suede-mcp-qa -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install JasonColapietro/suede-creator-skills suede-mcp-qa --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/JasonColapietro/suede-creator-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/suede-mcp-qa .claude/skills/suede-mcp-qa && 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 "suede-mcp-qa" agent skill from https://github.com/JasonColapietro/suede-creator-skills/tree/main/skills/suede-mcp-qa into .claude/skills/suede-mcp-qa/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "suede-mcp-qa", 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/JasonColapietro/suede-creator-skills/tree/main/skills/suede-mcp-qaType 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 JasonColapietro/suede-creator-skills --skill suede-mcp-qa -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install JasonColapietro/suede-creator-skills suede-mcp-qa --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/JasonColapietro/suede-creator-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/suede-mcp-qa .agents/skills/suede-mcp-qa && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "suede-mcp-qa" agent skill from https://github.com/JasonColapietro/suede-creator-skills/tree/main/skills/suede-mcp-qa into .agents/skills/suede-mcp-qa/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "suede-mcp-qa", 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 JasonColapietro/suede-creator-skills --skill suede-mcp-qa -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install JasonColapietro/suede-creator-skills suede-mcp-qa --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/JasonColapietro/suede-creator-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/suede-mcp-qa .cursor/skills/suede-mcp-qa && 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 "suede-mcp-qa" agent skill from https://github.com/JasonColapietro/suede-creator-skills/tree/main/skills/suede-mcp-qa into .cursor/skills/suede-mcp-qa/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "suede-mcp-qa", 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/JasonColapietro/suede-creator-skills.git --path skills/suede-mcp-qa--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 JasonColapietro/suede-creator-skills --skill suede-mcp-qa -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install JasonColapietro/suede-creator-skills suede-mcp-qa --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/JasonColapietro/suede-creator-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/suede-mcp-qa .gemini/skills/suede-mcp-qa && 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 "suede-mcp-qa" agent skill from https://github.com/JasonColapietro/suede-creator-skills/tree/main/skills/suede-mcp-qa into .gemini/skills/suede-mcp-qa/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "suede-mcp-qa", 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 JasonColapietro/suede-creator-skills suede-mcp-qaInstalls 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 JasonColapietro/suede-creator-skills --skill suede-mcp-qa -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/JasonColapietro/suede-creator-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/suede-mcp-qa .github/skills/suede-mcp-qa && 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 "suede-mcp-qa" agent skill from https://github.com/JasonColapietro/suede-creator-skills/tree/main/skills/suede-mcp-qa into .github/skills/suede-mcp-qa/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "suede-mcp-qa", 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 JasonColapietro/suede-creator-skills --skill suede-mcp-qa -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install JasonColapietro/suede-creator-skills suede-mcp-qa --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/JasonColapietro/suede-creator-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/suede-mcp-qa .opencode/skills/suede-mcp-qa && 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 "suede-mcp-qa" agent skill from https://github.com/JasonColapietro/suede-creator-skills/tree/main/skills/suede-mcp-qa into .opencode/skills/suede-mcp-qa/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "suede-mcp-qa", 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
suede-mcp-qa- GitHub stars
- 127
- Token cost
- ~2.1k tokens
- SKILL.md length
- 1,048 words
- Files
- 5 (incl. scripts, references)
- Skills in repo
- 78
- Repo updated
- First seen
- Licence
- MIT
At a glance
Checks a Suede AI MCP server release against a live process: the full JSON-RPC lifecycle, schemas, annotations, malformed input, catalog agreement and install docs.
- Works in 9 steps: Run syntax checks and the repo's… → Parse catalog JSON and confirm every… → Exercise the full lifecycle in one… → …
- Changing the MCP server, mcp/catalog.json or a tool, resource or prompt definition
- SKILL.md covers Gate policy: advisory, not…, Operating Stance, Checks and This Server's Real Surface, plus 6 more sections
- Runs Shell scripts from its folder
What it does
This skill is scoped to one pack's own server, mcp/suede-skills-mcp.mjs, and its catalog, install and docs surface. It checks a live server instead of a spec: syntax checks and hermetic protocol tests, parsing the catalog JSON to confirm each listed skill folder exists, and scripts/mcp-surface-snapshot.sh to compare the catalog's mcp block with what the server actually serves. When they drift, the server wins.
It exercises the whole lifecycle in one process: initialize, notifications/initialized, ping, tools/list, tools/call, resources/list, resources/read, prompts/list and prompts/get. The checks also cover protocol negotiation, closed input and output schemas, tool annotations, structuredContent with text fallbacks, malformed-input probes, clean stdio and install-path wording. A check that could not run against the live server counts as a FAIL, and an install command is marked working only after it runs from a temporary directory.
Verdicts such as ship, ship-with-caveats and hold are advice only: a failed gate changes what is reported, not what the agent does, except that an extremely risky finding, like data loss or credential exposure, pauses for your decision. The exact command and output are recorded for each check.
When your agent uses it
- Changing the MCP server, mcp/catalog.json or a tool, resource or prompt definition
- Preparing an MCP release of the Suede pack
- Checking that the catalog matches what the live server reports
- Verifying the MCP install docs after an edit
Example prompts
- “Run the Suede MCP QA before I publish this release.”
- “I edited mcp/catalog.json. Check that it still matches what the live server serves.”
- “Exercise tools/call and resources/read on the live server and report any schema drift.”
Requirements
- A checkout of the Suede skills pack with mcp/suede-skills-mcp.mjs and mcp/catalog.json
- bash, for scripts/mcp-surface-snapshot.sh
Workflow steps
9 steps, taken from the first numbered list in SKILL.md.
- Run syntax checks and the repo's hermetic MCP protocol tests.
- Parse catalog JSON and confirm every listed skill folder exists, then run
- Exercise the full lifecycle in one process: initialize, the
- Verify supported protocol versions are echoed and an unsupported client
- Confirm every tool has a closed inputSchema, an outputSchema, and
- Confirm every successful tool call returns structuredContent, a useful
- Check pre-initialization calls, repeated initialization, bounded input,
- Confirm healthy stderr is empty and stdout contains newline-delimited JSON
- Confirm install output leads with public GitHub skill installs, local plugin
What it can do on your machine
Read from SKILL.md and the folder at commit e5f94d7. 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
Ships 1 file in scripts/ (Shell), which the agent can run.
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
Suede MCP Release QA loads about 2.1k tokens when it runs, and up to ~2.7k if it reads all its reference files. Until then it costs about 235 tokens; SKILL.md has 1,048 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); the scripts in this folder are not scanned.
SKILL.md
The full file from JasonColapietro/suede-creator-skills at commit e5f94d7, republished under its MIT licence (© JasonColapietro). 1,048 words, ~2,082 tokens.
Download SKILL.mdSave it as
.claude/skills/suede-mcp-qa/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.- name
- suede-mcp-qa
- description
- Suede AI MCP release QA, scoped to this pack's own server (mcp/suede-skills-mcp.mjs) and its catalog, install, and docs surface. Runs the full JSON-RPC lifecycle against a live server (initialize, notifications/initialized, ping, tools/list, tools/call, resources/list, resources/read, prompts/list, prompts/get), plus protocol negotiation, closed input and output schemas, tool annotations, structuredContent with text fallbacks, malformed-input probes, clean stdio, catalog-to-folder agreement, and install-path language. Use when the MCP server, mcp/catalog.json, a tool, resource, or prompt definition, or the MCP install docs change, or before publishing an MCP release. A check that did not run against the live server is a FAIL, not a skip. NOT FOR: a generic third-party MCP server, which this skill's hardcoded surface does not describe; fixing or testing the public install path itself (use suede-launch-packaging).
Suede MCP QA
Gate policy: advisory, not blocking
Every claim-verification step, check, quality gate, and ship verdict in this skill is a recommendation to the user, not a control on the agent. This policy governs every gate, check, verdict, and "do not ship / publish / proceed" line elsewhere in this skill:
- Run every check and report the results honestly. Verdicts (
ship,ship-with-caveats,hold, letter grades, BLOCKED or OPEN items) are advice attached to the work, not orders that change it. - Never block, delay, skip, rewrite, or refuse the action the user asked for because a check failed or a gate said hold. Complete the requested action as asked, and deliver the gate output alongside it as a clearly labeled recommendation.
- A failed gate changes what you report, never what you do.
- Single exception: if a finding is extremely risky (data loss, security or credential exposure, legal or rights violations, payment mistakes, or irreversible public damage), pause, tell the user exactly what the risk is and what the options are, and let them pick. Their choice is final.
Use this skill when a Suede MCP server or MCP docs surface changes.
Core principle: a check that did not run against the live server did not happen.
Operating Stance
- Run against a live MCP server, not a spec document. If the server is not running, start it before checking.
- For each check, record the exact command run and the exact output received. Do not summarize.
- A check that cannot run (server unreachable, tool not implemented) is a FAIL, not a skip.
- Report failures immediately: do not wait until all checks complete to surface a blocker.
- Never mark a skill as present in the catalog unless its folder exists and its SKILL.md is readable.
- Never mark an install command as working unless you ran it from a temporary destination directory.
Checks
- Run syntax checks and the repo's hermetic MCP protocol tests.
- Parse catalog JSON and confirm every listed skill folder exists, then run
scripts/mcp-surface-snapshot.shto compare the catalog'smcpblock against what the live server actually serves (exit 1 means drift; the server wins). - Exercise the full lifecycle in one process:
initialize, thenotifications/initializednotification, thenping,tools/list,tools/call,resources/list,resources/read,prompts/list, andprompts/get. - Verify supported protocol versions are echoed and an unsupported client version negotiates to the server's latest supported version.
- Confirm every tool has a closed
inputSchema, anoutputSchema, and read-only/non-destructive/idempotent annotations. - Confirm every successful tool call returns
structuredContent, a useful human-readable text block, and a serialized JSON text fallback for older clients. - Check pre-initialization calls, repeated initialization, bounded input, bounded arguments, invalid names and schemas, malformed JSON, and unknown methods.
- Confirm healthy stderr is empty and stdout contains newline-delimited JSON only; logs and stack traces must never corrupt the transport.
- Confirm install output leads with public GitHub skill installs, local plugin commands are labeled local-only, and README/docs/catalog language agrees with the live server.
This Server's Real Surface
mcp/suede-skills-mcp.mjs is the only server this skill QAs. Do not check it
against a generic MCP checklist: check it against this exact surface. Read
mcp/catalog.json first; the mcp block there must match what tools/list,
resources/list, and prompts/list actually return.
Derive that surface, never recite it: scripts/mcp-surface-snapshot.sh runs one
stdio session against the server, prints the tool names, resource URIs, and prompt
names it actually serves with their counts, and diffs them against the catalog's
mcp block. Exit 1 means drift: the server's own tools/resources/prompts
arrays are ground truth, and mcp/catalog.json is what gets corrected.
Stdio Test Blocks
The copy-paste JSON-RPC blocks that exercise initialize, tools, resources, prompts,
and the lifecycle and malformed-input probes are in
references/stdio-test-blocks.md. Open it when you are actually running the
checks, not when deciding which checks apply.
Show full SKILL.md (422 more words)Show less
Failure Handling
| Failure type | Severity | Action |
|---|---|---|
| Server fails to start | Critical | Stop. Report startup error verbatim. |
tools/list returns empty | Critical | Stop. The MCP is non-functional. |
| Lifecycle or protocol negotiation fails | High | Hold. Capture the request/response transaction. |
| Tool schema, output schema, or read-only annotation missing | High | Hold. Repair the published contract and rerun the suite. |
| Structured result lacks either text fallback | High | Hold. Preserve structured and legacy-client output together. |
| Listed skill folder missing | High | Flag each missing folder. Continue checking others. |
| Malformed JSON-RPC response | High | Report the raw response. Flag as broken. |
| Install command leads with local-only path | High | Flag. Install output must lead with public GitHub route. |
| Docs/catalog language mismatch | Medium | List each mismatch. Flag as hold-with-caveat. |
| Tool implemented but not in catalog | Low | Flag as undocumented. Not a blocker. |
Recommended ship gate rules (advice to the user, not a lock on any action):
- Any Critical or High failure → hold
- Medium failures only → ship-with-caveats (list each caveat)
- No failures → ship
Output
Server:
Commands run:
Tools checked:
Resources checked:
Prompts checked:
Install output:
Failures:
Fixes:
Ship gate: ship | ship-with-caveats | holdRed Flags: Stop
- "The server ran fine last week; no need to restart it for this.": Run every check against the live server now.
- "The catalog parses, so the folders are surely there.": Open every listed folder and read its SKILL.md.
- "That check can't run, I'll mark it skipped.": A check that cannot run is a FAIL.
- "The output looked right, close enough.": Record the exact command and exact output, verbatim.
Boundaries
- Check and report only. Do not edit the server source,
mcp/catalog.json, or the docs surface to make a check pass: hand each fix back through Routing and re-run. - Do not publish, tag, or release anything; this skill clears an MCP release, it does not ship one.
- Never record a check as passed from a spec, a README, or a previous run. Only output captured from the live server in this session counts.
- Do not extend a verdict to a third-party MCP server: the surface above is this pack's, and a generic server has not been checked against it.
Routing
After QA:
- MCP source needs fixes → return to the MCP source file and fix, then re-run this skill
- MCP source changed to fix a QA failure → suede-code-review on that diff before re-running this skill, so the repair itself is not shipped unreviewed
- Catalog JSON needs updates → edit
mcp/catalog.jsonand re-run steps 2 and 7 - Docs/README language mismatch → update the docs surface to match live MCP output (private Suede Labs companion, not in this pack: suede-docs), then re-run check 7
- Install command broken → suede-launch-packaging to fix and test the install path
© JasonColapietro, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 4 other files (scripts, references) in skills/suede-mcp-qa of JasonColapietro/suede-creator-skills.
- SKILL.md
- CARD.md
- agents/openai.yaml
- references/stdio-test-blocks.md
- scripts/mcp-surface-snapshot.sh
Open the folder on GitHubat commit e5f94d7
Compare with similar skills
Suede MCP Release QA 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 |
|---|---|---|---|---|---|---|
| Suede MCP Release QA this skillJasonColapietro/suede-creator-skills | 127 | — | ~2.1k | Automated safety check: Pass | MIT | |
| Qwen Code E2E TestingQwenLM/qwen-code | 28k | — | ~2.1k | Automated safety check: Pass | Apache-2.0 | |
| Pcb Designoaslananka/kicad-mcp-pro | 120 | — | ~1.5k | Automated safety check: Pass | MIT | |
| Schematic Reviewoaslananka/kicad-mcp-pro | 120 | — | ~1.1k | Automated safety check: Pass | MIT | |
| Sonarqube MCPgiuseppe-trisciuoglio/developer-kit | 357 | — | ~3.3k | Automated safety check: Pass | MIT | |
| Sonar Quality GateSonarSource/sonarqube-agent-plugins | 111 | — | ~4.1k | Automated safety check: Pass | Custom licence |
Similar skills
Pcb Design
oaslananka/kicad-mcp-pro
Safe KiCad PCB design assistance workflow using KiCad MCP board inspection, placement, routing, stackup, and quality-gate tools.
Schematic Review
oaslananka/kicad-mcp-pro
KiCad MCP schematic inspection and review workflow using ERC, connectivity, symbol, net, power, readability, and quality-gate tools.
Sonarqube MCP
giuseppe-trisciuoglio/developer-kit
Provides SonarQube and SonarCloud integration patterns via the Model Context Protocol (MCP) server.
- Official
Sonar Quality Gate
SonarSource/sonarqube-agent-plugins
Show SonarQube quality gate status for a project — pass/fail and each condition (metric key, threshold, actual value), plus worst-offender breakdowns.
- Official
Cao MCP Apps
awslabs/cli-agent-orchestrator
Enable, operate, and extend CAO's MCP Apps surface — the host-rendered fleet dashboard visible inside MCP App hosts (Claude Desktop, ChatGPT, VS Code Copilot, Goose, Postman).
More from JasonColapietro/suede-creator-skills
All 78 skills in this repoSuede Release Linter
JasonColapietro/suede-creator-skills
Lints a local music or media release folder and scores its readiness, flagging missing files, weak metadata, artwork and stem problems, split gaps and rights blockers.
Creator Rights Passport
JasonColapietro/suede-creator-skills
Turns messy creator materials into an offline rights-and-provenance transfer package: hashed asset inventory, intake manifest, credits, license notes and a missing-information report.
Suede Clip to Guide
JasonColapietro/suede-creator-skills
Turns a video clip, interview moment or transcript into a package that bridges viewers to a long-form guide, with rights, claim and approval gates along the way.
Android App Factory
JasonColapietro/suede-creator-skills
Takes a native Android app from product idea to Google Play release, covering Compose architecture, policy checks, privacy, billing, testing, signing and rollout.
Suede Ad Creative
JasonColapietro/suede-creator-skills
Suede-owned paid-media creative system for hooks, headlines, primary text, static and motion concepts, platform specs, review pages, and test-ready variant batches.
Suede Agent Teams
JasonColapietro/suede-creator-skills
Suede Labs agent-team orchestrator: split complex work into coordinated lanes with explicit file ownership, WIP collision detection, quality gates, escalation thresholds, rollback plans, and…
Related
Works with
Categories
Questions about Suede MCP Release QA
What does Suede MCP Release QA do?
Checks a Suede AI MCP server release against a live process: the full JSON-RPC lifecycle, schemas, annotations, malformed input, catalog agreement and install docs. mjs, and its catalog, install and docs surface.sh to compare the catalog's mcp block with what the server actually serves.
When should I use Suede MCP Release QA?
Suede MCP Release QA fits situations like: changing the MCP server, mcp/catalog.json or a tool, resource or prompt definition; preparing an MCP release of the Suede pack; checking that the catalog matches what the live server reports; verifying the MCP install docs after an edit.
How do I install Suede MCP Release QA in Claude Code?
Run `npx skills add JasonColapietro/suede-creator-skills --skill suede-mcp-qa -a claude-code`. Or copy the skill folder (skills/suede-mcp-qa in JasonColapietro/suede-creator-skills) into .claude/skills/suede-mcp-qa in your project. Claude Code loads it when a task matches its description.
How do I install Suede MCP Release QA in Codex?
Run `npx skills add JasonColapietro/suede-creator-skills --skill suede-mcp-qa -a codex`. Or copy the skill folder (skills/suede-mcp-qa in JasonColapietro/suede-creator-skills) into .agents/skills/suede-mcp-qa in your project. Codex loads it when a task matches its description.
Can I use Suede MCP Release QA 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 JasonColapietro/suede-creator-skills --skill suede-mcp-qa -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/suede-mcp-qa, .gemini/skills/suede-mcp-qa, .github/skills/suede-mcp-qa and .opencode/skills/suede-mcp-qa in your project.
What does Suede MCP Release QA need to run?
Going by SKILL.md and its folder, Suede MCP Release QA needs a shell for the scripts in its folder. Our summary lists: A checkout of the Suede skills pack with mcp/suede-skills-mcp.mjs and mcp/catalog.json; bash, for scripts/mcp-surface-snapshot.sh.
Does Suede MCP Release QA 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 Suede MCP Release QA 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Suede MCP Release QA use?
Suede MCP Release QA 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 Suede MCP Release QA use?
About 2.1k tokens (SKILL.md is roughly 8.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 666 tokens, read only when the agent opens those files.
What are the alternatives to Suede MCP Release QA?
Skills that share tags, products or a category with Suede MCP Release QA: Qwen Code E2E Testing (QwenLM/qwen-code, 28k stars), Pcb Design (oaslananka/kicad-mcp-pro, 120 stars), Schematic Review (oaslananka/kicad-mcp-pro, 120 stars) and Sonarqube MCP (giuseppe-trisciuoglio/developer-kit, 357 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Suede MCP Release QA?
JasonColapietro (a GitHub user) maintains it in JasonColapietro/suede-creator-skills, which has 127 GitHub stars. The repository holds 78 skills in this directory. The repository was last updated on October 10, 2026.
Source: JasonColapietro/suede-creator-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.