Oleafly Response Letter

What it does

When your agent uses it

• Preparing a rebuttal
• An author response
• A revision cover letter for a journal
• Mapping each reviewer point to the passage that changed

Example prompts

• “/oleafly-response-letter”

Requirements

• Compatibility (from SKILL.md): Any LaTeX or Typst project. Finding what changed works best when the project is a git repository, which Oleafly projects are by default. The bundled templates compile on the app engines with no extra packages.
• Pre-approved tools (allowed-tools): read_file, list_files, search_project, create_file, write_file, replace_in_file, compile, get_log, set_main_doc, run_command, read_skill_file, show_location, update_todos

Workflow steps

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

1. 1Capture the comments verbatim
2. 2Find out what actually changed
3. 3Map each point to the manuscript
4. 4Draft both versions
5. 5Compile the letter
6. 6Check it before you hand it over

What it can do on your machine

Read from SKILL.md and the folder at commit dc582ef. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • read_file
  • list_files
  • search_project
  • create_file
  • write_file
  • replace_in_file
  • compile
  • get_log
  • set_main_doc
  • run_command

  …and 3 more on the same allowed-tools line.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • git

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use git, 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.

• Compatibility

  Any LaTeX or Typst project. Finding what changed works best when the project is a git repository, which Oleafly projects are by default. The bundled templates compile on the app engines with no extra packages.

  From compatibility in the SKILL.md frontmatter.

Context cost

Oleafly Response Letter loads about 2.3k tokens when it runs, and up to ~3.4k if it reads all its reference files. Until then it costs about 108 tokens; SKILL.md has 1,147 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~108

When it runs · the whole SKILL.md, loaded when a task matches

~2.3k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~3.4k

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

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 Oleafly/Oleafly at commit dc582ef, republished under its MIT licence (© Oleafly). 1,147 words, ~2,309 tokens.

name

oleafly-response-letter

description

Turn reviewer comments and the changes already made into a point-by-point response letter, in LaTeX or Typst and in plain text. Use when preparing a rebuttal, an author response, or a revision cover letter for a journal or conference, when mapping each reviewer point to the passage that changed, when a resubmission needs every comment answered, or when a response letter has to compile alongside the paper.

allowed-tools

read_file, list_files, search_project, create_file, write_file, replace_in_file, compile, get_log, set_main_doc, run_command, read_skill_file, show_location, update_todos

compatibility

Any LaTeX or Typst project. Finding what changed works best when the project is a git repository, which Oleafly projects are by default. The bundled templates compile on the app engines with no extra packages.

license

MIT

metadata.version

1.1.0

metadata.skill-author

Oleafly

## Reviewer 1

R1.1 The sample size justification is missing.
R1.2 Table 2 reports means without dispersion.
R1.3 The related work section omits the closest prior method.

## Reviewer 2

R2.1 ...

run_command  git log --oneline -40
run_command  git diff <revision> -- <path>
run_command  git diff --stat <revision>

\reviewer{1}
\point{R1.1}{The sample size justification is missing.}
\reply{We have added the power calculation that determined the group size.}
\changed{sections/methods.tex, line 84}{With 80\% power at alpha = 0.05 to detect a difference of 0.4 SD, each arm required 99 participants.}

#reviewer(1)
#point[R1.1][The sample size justification is missing.]
#reply[We have added the power calculation that determined the group size.]
#changed("sections/methods.typ, line 84")[With 80% power at alpha = 0.05 to detect a difference of 0.4 SD, each arm required 99 participants.]

© Oleafly, 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 (references, assets) in src-tauri/resources/skills/oleafly-response-letter of Oleafly/Oleafly.

• SKILL.md
• assets/response-outline.md
• assets/response-template.tex
• assets/response-template.typ
• references/tone-and-structure.md

Open the folder on GitHubat commit dc582ef