Finishing a Development Branch
obra/superpowers
Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.
Prepare or update an FLA pull request with one concrete purpose, a concise description, verified tests and benchmarks, and justified size exceptions.
Install Fla PR Readiness
$ npx skills add fla-org/flash-linear-attention --skill fla-pr-readiness -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install fla-org/flash-linear-attention fla-pr-readiness --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/fla-org/flash-linear-attention.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/fla-pr-readiness .claude/skills/fla-pr-readiness && 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 "fla-pr-readiness" agent skill from https://github.com/fla-org/flash-linear-attention/tree/main/.agents/skills/fla-pr-readiness into .claude/skills/fla-pr-readiness/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fla-pr-readiness", 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/fla-org/flash-linear-attention/tree/main/.agents/skills/fla-pr-readinessType 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 fla-org/flash-linear-attention --skill fla-pr-readiness -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install fla-org/flash-linear-attention fla-pr-readiness --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/fla-org/flash-linear-attention.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/fla-pr-readiness .agents/skills/fla-pr-readiness && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "fla-pr-readiness" agent skill from https://github.com/fla-org/flash-linear-attention/tree/main/.agents/skills/fla-pr-readiness into .agents/skills/fla-pr-readiness/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fla-pr-readiness", 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 fla-org/flash-linear-attention --skill fla-pr-readiness -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install fla-org/flash-linear-attention fla-pr-readiness --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/fla-org/flash-linear-attention.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/fla-pr-readiness .cursor/skills/fla-pr-readiness && 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 "fla-pr-readiness" agent skill from https://github.com/fla-org/flash-linear-attention/tree/main/.agents/skills/fla-pr-readiness into .cursor/skills/fla-pr-readiness/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fla-pr-readiness", 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/fla-org/flash-linear-attention.git --path .agents/skills/fla-pr-readiness--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 fla-org/flash-linear-attention --skill fla-pr-readiness -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install fla-org/flash-linear-attention fla-pr-readiness --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/fla-org/flash-linear-attention.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/fla-pr-readiness .gemini/skills/fla-pr-readiness && 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 "fla-pr-readiness" agent skill from https://github.com/fla-org/flash-linear-attention/tree/main/.agents/skills/fla-pr-readiness into .gemini/skills/fla-pr-readiness/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fla-pr-readiness", 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 fla-org/flash-linear-attention fla-pr-readinessInstalls 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 fla-org/flash-linear-attention --skill fla-pr-readiness -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/fla-org/flash-linear-attention.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/fla-pr-readiness .github/skills/fla-pr-readiness && 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 "fla-pr-readiness" agent skill from https://github.com/fla-org/flash-linear-attention/tree/main/.agents/skills/fla-pr-readiness into .github/skills/fla-pr-readiness/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fla-pr-readiness", 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 fla-org/flash-linear-attention --skill fla-pr-readiness -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install fla-org/flash-linear-attention fla-pr-readiness --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/fla-org/flash-linear-attention.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/fla-pr-readiness .opencode/skills/fla-pr-readiness && 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 "fla-pr-readiness" agent skill from https://github.com/fla-org/flash-linear-attention/tree/main/.agents/skills/fla-pr-readiness into .opencode/skills/fla-pr-readiness/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fla-pr-readiness", 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
fla-pr-readiness- GitHub stars
- 5.8k
- Token cost
- ~1.2k tokens
- SKILL.md length
- 576 words
- Files
- 1
- Skills in repo
- 9
- Repo updated
- First seen
- Licence
- MIT
At a glance
Prepare or update an FLA pull request with one concrete purpose, a concise description, verified tests and benchmarks, and justified size exceptions.
- Works in 4 steps: Discover affected tests with python… → Run applicable tests and record the… → For kernel or performance-relevant… → …
- Tasks that involve Pull requests
- SKILL.md covers Establish scope, Collect evidence, Write and check the description and Publishing and follow-up
- Calls gh and python
What it does
Fla PR Readiness is an agent skill from fla-org/flash-linear-attention. Prepare or update an FLA pull request with one concrete purpose, a concise description, verified tests and benchmarks, and justified size exceptions.
Its SKILL.md is about 1.2k 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 Development, covering Pull requests. The repository describes itself as: 🚀 Efficient implementations for emerging model architectures. The licence is MIT.
When your agent uses it
- Tasks that involve Pull requests
Example prompts
- “/fla-pr-readiness”
Requirements
- Python 3
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Discover affected tests with python scripts/find_dependent_tests.py [more_files.py ...]. Add or update the matching test for kernel/module…
- Run applicable tests and record the command, tested commit, environment, and results. Use strict local numerical validation…
- For kernel or performance-relevant changes, collect same-hardware before/after results following CONTRIBUTING.md#benchmarking. Select the…
- Run pre-commit on changed files and inspect the final diff. Audit affected comments, public callers, checkpoint compatibility, and the…
What it can do on your machine
Read from SKILL.md and the folder at commit 1b79e83. 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
Shell commands in SKILL.md call:
ghpython
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use gh, which can reach the network depending on how they are called.
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
Fla PR Readiness loads about 1.2k tokens when it runs. Until then it costs about 42 tokens; SKILL.md has 576 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 fla-org/flash-linear-attention at commit 1b79e83, republished under its MIT licence (© fla-org). 576 words, ~1,162 tokens.
Download SKILL.mdSave it as
.claude/skills/fla-pr-readiness/SKILL.md (or your agent's skills folder).- name
- fla-pr-readiness
- description
- Prepare or update an FLA pull request with one concrete purpose, a concise description, verified tests and benchmarks, and justified size exceptions.
FLA PR Readiness Skill
Use this skill before opening a PR or updating its scope and evidence during review. Read CONTRIBUTING.md first; it defines the contribution rules. AGENTS.md defines operational constraints. The PR template is the source for headings and checkboxes; do not maintain a second copy here.
Establish scope
- Read the complete diff against the PR base, including tests, documentation, and all shared callers. Express its single outcome in one sentence; separate independent fixes or optimizations.
- Search open issues and PRs before starting, for example
gh pr list --repo fla-org/flash-linear-attention --state open --search "<keywords>". Check matching discussions before duplicating work. - Follow the design/RFC requirements in
AGENTS.mdbefore implementation. Use the skill index to choose contract, operator, backend, and performance workflows relevant to the change. - Inspect the full diff size. Above 500 additions plus deletions, verify that it is one cohesive change before filling the template's large-PR acknowledgement and justification. Explain why it should stay together and suggest a review order; a size exception does not justify unrelated work.
Collect evidence
- Discover affected tests with
python scripts/find_dependent_tests.py <changed_file.py> [more_files.py ...]. Add or update the matching test for kernel/module changes, and check that a regression test actually exercises the modified path. - Run applicable tests and record the command, tested commit, environment, and results. Use strict local numerical validation (
FLA_CI_ENV=0), retaining reference outputs, supported gradients, and existing tolerances. Separate failed, skipped, and unrun checks from passes; investigate failures and reproduce them on the baseline before calling them pre-existing. - For kernel or performance-relevant changes, collect same-hardware before/after results following
CONTRIBUTING.md#benchmarking. Select the relevant hardware skill for profiling and workload coverage. A measured neutral result still needs numbers; useN/Aonly with an applicable reason. - Run pre-commit on changed files and inspect the final diff. Audit affected comments, public callers, checkpoint compatibility, and the supported shapes, dtypes, and backends. Keep scratch logs and raw profiles outside the PR.
Show full SKILL.md (259 more words)Show less
Write and check the description
Follow PR Description and Evidence by Change Type:
- Open
Summarywith one or two sentences naming the problem or capability and the observable result. Include only the rationale, compatibility effects, or limitations needed to evaluate it. - Remove variable inventories, file-by-file narration, repeated claims, and the history of attempted approaches. Keep reproducible commands and compact evidence tables; link or collapse long logs.
- Make every correctness or performance claim traceable to evidence for the relevant path. Describe the final implementation and re-run affected validation when review changes invalidate earlier results.
- Preserve the template checklist wording. Tick the first four items only when complete or inapplicable, recording the reason in the relevant section. The minor/cosmetic box and large-PR box are conditional; do not tick every box automatically.
- Keep incomplete work in draft and state missing validation. A failing metadata check on an unfinished draft is not a reason to claim tests passed.
Publishing and follow-up
The check-pr-title workflow validates the title, checklist, and size exception, including on body edits. It checks the presence of an explanation; reviewers judge whether the stated purpose, evidence, and exception are sound. Use an outcome-based [Tag] title and the current template.
gh pr edit fails on this repository because of its classic-Projects integration. Write the complete body to a temporary file and update it with the REST API:
gh api -X PATCH repos/fla-org/flash-linear-attention/pulls/<N> -F body=@<body-file>Confirm the published title/body, head commit, and check results. Follow repository git safety rules and the user's authorization for publishing; this skill does not grant permission to post unrelated comments or rewrite pushed commits.
© fla-org, 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 .agents/skills/fla-pr-readiness of fla-org/flash-linear-attention.
Open the folder on GitHubat commit 1b79e83
Compare with similar skills
Fla PR Readiness 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 |
|---|---|---|---|---|---|---|
| Fla PR Readiness this skillfla-org/flash-linear-attention | 5.8k | — | ~1.2k | Automated safety check: Pass | MIT | |
| Finishing a Development Branchobra/superpowers | 297k | 5 repos | ~1.9k | Automated safety check: Pass | MIT | |
| PR Babysitteropeninterpreter/openinterpreter | 69k | 3 repos | ~4.2k | Automated safety check: Pass | Apache-2.0 | |
| Check PRonyx-dot-app/onyx | 32k | 2 repos | ~2.3k | Automated safety check: Pass | MIT | |
| PR Design DocOpenHands/OpenHands | 90k | — | ~2.4k | Automated safety check: Pass | MIT | |
| WooCommerce Code Reviewwoocommerce/woocommerce | 11k | 3 repos | ~1.1k | Automated safety check: Pass | Custom licence |
Similar skills
PR Babysitter
openinterpreter/openinterpreter
Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.
Check PR
onyx-dot-app/onyx
Checks a GitHub, GitLab, or Perforce (p4) pull request (or merge request, or shelved changelist) for unresolved review comments, failing status checks, and incomplete PR descriptions.
PR Design Doc
OpenHands/OpenHands
For a non-trivial pull request, write a self-contained HTML design doc under the temporary .pr/ directory and link a visibility-appropriate preview in the PR description, so maintainers grasp the…
WooCommerce Code Review
woocommerce/woocommerce
Reviews WooCommerce code changes against the project's standards, flagging backend PHP architecture, naming, documentation, data integrity and testing violations.
Record PR Demo
payloadcms/payload
A skill your agent uses when a Payload pull request needs a concise visual walkthrough for reviewers.
More from fla-org/flash-linear-attention
All 9 skills in this repoFla Ascend Performance
fla-org/flash-linear-attention
Guidelines for Ascend NPU kernel / Triton-Ascend backend performance work in the FLA repo.
Fla Optimization Loop
fla-org/flash-linear-attention
Disciplined, reproducible loop for making an FLA kernel faster (Triton, Gluon, TileLang, CuTe) without ever breaking or gaming correctness.
Fla Triton To Gluon
fla-org/flash-linear-attention
Workflow for porting an existing Triton kernel in fla/ops/ to Gluon (triton.experimental.gluon) to gain explicit control over tensor layouts, shared memory, async data movement (cp.async / TMA), MMA…
Fla Correctness Coverage
fla-org/flash-linear-attention
Guidelines for kernel correctness testing and coverage in fla/ops/ and related modules, including common Triton grid/addressing pitfalls.
Fla Design Coverage
fla-org/flash-linear-attention
Contract-first design and coverage discipline for FLA kernel and numerical changes.
Fla Kda
fla-org/flash-linear-attention
FLA KDA kernel workflow and public technical notes. An agent skill from fla-org/flash-linear-attention.
Related
Categories
Questions about Fla PR Readiness
What does Fla PR Readiness do?
Prepare or update an FLA pull request with one concrete purpose, a concise description, verified tests and benchmarks, and justified size exceptions. Fla PR Readiness is an agent skill from fla-org/flash-linear-attention. Prepare or update an FLA pull request with one concrete purpose, a concise description, verified tests and benchmarks, and justified size exceptions.
When should I use Fla PR Readiness?
Fla PR Readiness fits situations like: tasks that involve Pull requests.
How do I install Fla PR Readiness in Claude Code?
Run `npx skills add fla-org/flash-linear-attention --skill fla-pr-readiness -a claude-code`. Or copy the skill folder (.agents/skills/fla-pr-readiness in fla-org/flash-linear-attention) into .claude/skills/fla-pr-readiness in your project. Claude Code loads it when a task matches its description.
How do I install Fla PR Readiness in Codex?
Run `npx skills add fla-org/flash-linear-attention --skill fla-pr-readiness -a codex`. Or copy the skill folder (.agents/skills/fla-pr-readiness in fla-org/flash-linear-attention) into .agents/skills/fla-pr-readiness in your project. Codex loads it when a task matches its description.
Can I use Fla PR Readiness 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 fla-org/flash-linear-attention --skill fla-pr-readiness -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/fla-pr-readiness, .gemini/skills/fla-pr-readiness, .github/skills/fla-pr-readiness and .opencode/skills/fla-pr-readiness in your project.
What does Fla PR Readiness need to run?
Going by SKILL.md and its folder, Fla PR Readiness needs the command-line tools its instructions call (gh and python). Our summary lists: Python 3.
Does Fla PR Readiness access the network?
SKILL.md contains no URLs. Its commands use gh, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Fla PR Readiness 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 Fla PR Readiness use?
Fla PR Readiness 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 Fla PR Readiness use?
About 1.2k tokens (SKILL.md is roughly 4.6k 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 Fla PR Readiness?
Skills that share tags, products or a category with Fla PR Readiness: Finishing a Development Branch (obra/superpowers, 297k stars), PR Babysitter (openinterpreter/openinterpreter, 69k stars), Check PR (onyx-dot-app/onyx, 32k stars) and PR Design Doc (OpenHands/OpenHands, 90k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Fla PR Readiness?
fla-org (a GitHub organization) maintains it in fla-org/flash-linear-attention, which has 5,837 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on October 9, 2026.
Source: fla-org/flash-linear-attention on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.