Feature Planner
serendipity1004/cc-feature-implementer
Creates phase-based feature plans with quality gates and incremental delivery structure.
Quality gate protocol between implementation and handoff. An agent skill from maxim-saplin/llm_chess.
Install QA Handoff
$ npx skills add maxim-saplin/llm_chess --skill qa-handoff -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install maxim-saplin/llm_chess qa-handoff --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/maxim-saplin/llm_chess.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/qa-handoff .claude/skills/qa-handoff && 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 "qa-handoff" agent skill from https://github.com/maxim-saplin/llm_chess/tree/main/.agents/skills/qa-handoff into .claude/skills/qa-handoff/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qa-handoff", 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/maxim-saplin/llm_chess/tree/main/.agents/skills/qa-handoffType 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 maxim-saplin/llm_chess --skill qa-handoff -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install maxim-saplin/llm_chess qa-handoff --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/maxim-saplin/llm_chess.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/qa-handoff .agents/skills/qa-handoff && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "qa-handoff" agent skill from https://github.com/maxim-saplin/llm_chess/tree/main/.agents/skills/qa-handoff into .agents/skills/qa-handoff/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qa-handoff", 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 maxim-saplin/llm_chess --skill qa-handoff -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install maxim-saplin/llm_chess qa-handoff --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/maxim-saplin/llm_chess.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/qa-handoff .cursor/skills/qa-handoff && 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 "qa-handoff" agent skill from https://github.com/maxim-saplin/llm_chess/tree/main/.agents/skills/qa-handoff into .cursor/skills/qa-handoff/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qa-handoff", 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/maxim-saplin/llm_chess.git --path .agents/skills/qa-handoff--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 maxim-saplin/llm_chess --skill qa-handoff -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install maxim-saplin/llm_chess qa-handoff --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/maxim-saplin/llm_chess.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/qa-handoff .gemini/skills/qa-handoff && 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 "qa-handoff" agent skill from https://github.com/maxim-saplin/llm_chess/tree/main/.agents/skills/qa-handoff into .gemini/skills/qa-handoff/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qa-handoff", 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 maxim-saplin/llm_chess qa-handoffInstalls 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 maxim-saplin/llm_chess --skill qa-handoff -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/maxim-saplin/llm_chess.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/qa-handoff .github/skills/qa-handoff && 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 "qa-handoff" agent skill from https://github.com/maxim-saplin/llm_chess/tree/main/.agents/skills/qa-handoff into .github/skills/qa-handoff/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qa-handoff", 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 maxim-saplin/llm_chess --skill qa-handoff -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install maxim-saplin/llm_chess qa-handoff --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/maxim-saplin/llm_chess.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/qa-handoff .opencode/skills/qa-handoff && 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 "qa-handoff" agent skill from https://github.com/maxim-saplin/llm_chess/tree/main/.agents/skills/qa-handoff into .opencode/skills/qa-handoff/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qa-handoff", 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
qa-handoff- GitHub stars
- 136
- Token cost
- ~354 tokens
- SKILL.md length
- 191 words
- Files
- 4 (incl. references)
- Skills in repo
- 2
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Quality gate protocol between implementation and handoff. An agent skill from maxim-saplin/llm_chess.
- Tasks that involve Quality gates
- SKILL.md covers Do Not Use When, Shared Invariants and Choose the Mode
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
QA Handoff is an agent skill from maxim-saplin/llm_chess. Quality gate protocol between implementation and handoff.
Its SKILL.md is about 350 tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `references/default-qa-mode.md`, `references/evidence-taxonomy.md` and `references/two-qa-mode.md`).
It sits in Testing & QA, covering Quality gates. The repository describes itself as: LLM Chess - evaluating Large Language Models' reasoning and instruction-following abilities by simulating chess games. The licence is Apache-2.0.
When your agent uses it
- Tasks that involve Quality gates
Example prompts
- “/qa-handoff”
What it can do on your machine
Read from SKILL.md and the folder at commit 3413b66. 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
QA Handoff loads about 354 tokens when it runs, and up to ~2.1k if it reads all its reference files. Until then it costs about 17 tokens; SKILL.md has 191 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 maxim-saplin/llm_chess at commit 3413b66, republished under its Apache-2.0 licence (© maxim-saplin). 191 words, ~354 tokens.
Download SKILL.mdSave it as
.claude/skills/qa-handoff/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.- name
- qa-handoff
- description
- Quality gate protocol between implementation and handoff.
QA Handoff
Use this skill after implementation work and before reporting results to the user. This file is the entrypoint: keep it for overview, routing, and shared invariants, then use the mode docs in references/ for the actual review flow.
!!! WHEN APPLICABLE PREFFER RUNTIME EVIDENCE, live checks, any real-world verfication scenarious OVER static file analysis !!!
Do Not Use When
- The task is still mid-implementation.
- You are only exploring or planning and have not produced work to verify yet.
- There is nothing substantive to hand off for review.
Shared Invariants
- Work is not reported to the user until it passes QA or 3 rounds are exhausted.
- Ambiguous verdict (neither clear PASS nor FAIL) counts as FAIL.
- The QA reviewer has no conversation history. Reconstruct the needed context in the handoff package.
- Only the user can waive a requirement.
- Before assembling or reviewing evidence, read
references/evidence-taxonomy.md. - QA validates deliverable readiness, not only internal correctness.
Choose the Mode
- Default to
references/default-qa-mode.md. - Use
references/two-qa-mode.mdonly when the user asks for a stronger gate or when you intentionally want bothqa-1andqa-2. - In two-QA mode, both reviewers must PASS on the same round before handoff.
© maxim-saplin, Apache-2.0. 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 3 other files (references) in .agents/skills/qa-handoff of maxim-saplin/llm_chess.
- SKILL.md
- references/default-qa-mode.md
- references/evidence-taxonomy.md
- references/two-qa-mode.md
Open the folder on GitHubat commit 3413b66
Compare with similar skills
QA Handoff 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 |
|---|---|---|---|---|---|---|
| QA Handoff this skillmaxim-saplin/llm_chess | 136 | — | ~354 | Automated safety check: Pass | Apache-2.0 | |
| Feature Plannerserendipity1004/cc-feature-implementer | 176 | — | ~2.4k | Automated safety check: Pass | None | |
| Ccg Workflowfengshao1227/ccg-workflow | 5.9k | — | ~2.3k | Automated safety check: Pass | MIT | |
| Conducty Checkpointrobertbarclayy/conducty | 176 | — | ~1.5k | Automated safety check: Pass | MIT | |
| Mission Plannerjdforsythe/forge | 151 | — | ~3.5k | Automated safety check: Pass | MIT | |
| Quality Gate0xNyk/lacp | 305 | — | ~382 | Automated safety check: Pass | MIT |
Similar skills
Ccg Workflow
fengshao1227/ccg-workflow
How to run a non-trivial change end to end with the CCG role tools (ccganalyze / ccgdesign / ccgbuild / ccgdebug / ccgoptimize / ccgreview / ccgtest) and the verify- quality gates.
Conducty Checkpoint
robertbarclayy/conducty
Quality gate between parallelization groups. An agent skill from robertbarclayy/conducty.
Mission Planner
jdforsythe/forge
Decomposes goals into team blueprints using evidence-based scaling laws, topology selection, and role design.
Quality Gate
0xNyk/lacp
Production quality gate for agent sessions. An agent skill from 0xNyk/lacp.
Deploy Workflow
nwiizo/ccswarm
Release deployment process for ccswarm. An agent skill from nwiizo/ccswarm.
More from maxim-saplin/llm_chess
Cross Ref Research
maxim-saplin/llm_chess
A skill your agent uses when implementing, extending, auditing, or QAing LLM Chess data/cross-ref workflows: external eval source snapshots, conservative model mapping, runcrossref.py commands…
Related
Categories
Questions about QA Handoff
What does QA Handoff do?
Quality gate protocol between implementation and handoff. An agent skill from maxim-saplin/llm_chess. QA Handoff is an agent skill from maxim-saplin/llm_chess. Quality gate protocol between implementation and handoff.
When should I use QA Handoff?
QA Handoff fits situations like: tasks that involve Quality gates.
How do I install QA Handoff in Claude Code?
Run `npx skills add maxim-saplin/llm_chess --skill qa-handoff -a claude-code`. Or copy the skill folder (.agents/skills/qa-handoff in maxim-saplin/llm_chess) into .claude/skills/qa-handoff in your project. Claude Code loads it when a task matches its description.
How do I install QA Handoff in Codex?
Run `npx skills add maxim-saplin/llm_chess --skill qa-handoff -a codex`. Or copy the skill folder (.agents/skills/qa-handoff in maxim-saplin/llm_chess) into .agents/skills/qa-handoff in your project. Codex loads it when a task matches its description.
Can I use QA Handoff 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 maxim-saplin/llm_chess --skill qa-handoff -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/qa-handoff, .gemini/skills/qa-handoff, .github/skills/qa-handoff and .opencode/skills/qa-handoff in your project.
What does QA Handoff need to run?
SKILL.md names no scripts, command-line tools or credentials: QA Handoff is instructions for the agent only.
Does QA Handoff 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 QA Handoff 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 QA Handoff use?
QA Handoff is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does QA Handoff use?
About 354 tokens (SKILL.md is roughly 1.4k 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 1.8k tokens, read only when the agent opens those files.
What are the alternatives to QA Handoff?
Skills that share tags, products or a category with QA Handoff: Feature Planner (serendipity1004/cc-feature-implementer, 176 stars), Ccg Workflow (fengshao1227/ccg-workflow, 5.9k stars), Conducty Checkpoint (robertbarclayy/conducty, 176 stars) and Mission Planner (jdforsythe/forge, 151 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains QA Handoff?
maxim-saplin (a GitHub user) maintains it in maxim-saplin/llm_chess, which has 136 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 10, 2026.
Source: maxim-saplin/llm_chess on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.