add-figure
Insert a verified mathematical graphic into the declared LaTeX manuscript at the passage it explains, with a substantive caption, unique label, prose…
Skill by tdupu
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/tdupu-add-figure
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/add-figure
What's inside
- Skill name
add-figure- Description
- Insert a verified mathematical graphic into the declared LaTeX manuscript at the passage it explains, with a substantive caption, unique label, prose reference, provenance, and an optional linked example. Preserve human annotations and the shared writer gates.
- License
- GPL-3.0
- Instructions
- 58 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# add-figure
Parent: [mathcity-latex](../../README.md).
Run [WRITERS.md](../../WRITERS.md) preamble and postamble in full. This is a
manuscript-writing leaf, not a graph generator. Reuse the active plan.
## Preflight
Verify the declared TeX root, its graphic paths, build command, and supported
image formats. Confirm the asset exists and inspect it before editing. Read
its source/provenance and the nearby definitions, claims, and human markers.
Missing asset or build tool: stop that operation with a named missing
resource, a concrete recovery action, and what it enables; do not insert a
broken include or report an unrun build as successful.
For a computed figure, require evidence identifying inputs and validating its
mathematical meaning. If source or provenance is missing, try to recover it
or route to `generate-graphics`. An explicitly identified schematic or
attributed illustration may still be used when it explains a construction,
but it cannot serve as evidence for unverified numerical claims. Preserve
uncertainty in the caption and agent-side ledger.
## Placement and writing
- Choose the first substantive passage that explains the depicted phenomenon,
after the notation/objects it needs. Include useful figures selectively;
do not make an unexplained gallery from a talk's asset directory.
- Reuse the repository's figure environment and label convention. Normally
use `figure`, `\centering`, `\includegraphics[width=...\linewidth]{...}`,
`\caption{...}`, then `\label{fig:...}`. TeX chooses the float's final
page; verify the compiled placement. Do not invent a `graphics` environment.
- Explain the figure's lesson with a precise `\ref`/`\cref`. Caption objects,
parameters, axes or vertices/edges, colors, normalization and scope.
Patterns are not theorems; approximations are not equalities. Explain
non-invariant layout choices that readers could misinterpret.
- For a worked case, reuse a supplied/existing example label. If absent,
request `write-example` once with figure insertion disabled, then resume.
Insert once, link both ways, return without redispatch. Keep the derivation
in the example; definitions precede results (LX10).
- Follow WRITERS' edit tags, preserve superseded prose as comments, and leave
every human annotation untouched. Answer a human question with an adjacent
`\agentreply{...}`, never by replacing its marker. Add verified pinpoint
citations for imported mathematics and attribution for reused images.
- Put source/script and manifest pointers in TeX comments and the durable
ledger. Use portable project-relative paths; keep hashes and process
status in the manifest/ledger rather than the printed caption.
## Verify and return
Run the declared full TeX build, label/reference and citation checks, and
inspect the actual PDF page at reading size. Check the caption, prose, and
image agree; report stale or missing provenance. A passing compile alone
cannot certify the graph. Return the inserted region, figure/example labels,
asset/manifest paths, and build/render-review evidence through the shared
writer postamble. Do not declare human acceptance on the user's behalf.From tdupu/agent-skills-public, GPL-3.0.
More from tdupu/agent-skills-public
- 0.570score
assemble-recording-series
tdupu
Assemble one lecture or talk video from a folder of raw takes, whatever the capture tool wrote - flat screen-capture files, or per-session folders with the…
SkillAFreshness: AClaude Code +9 - 0.570score
check-paragraph
tdupu
Judge ONE paragraph of prose (LaTeX allowed) as its stated reader and return a fixed six-line verdict — topic sentence, one idea, reader can follow, claim…
SkillAFreshness: AClaude Code +9 - 0.565score
check-documentation-policy
tdupu
Audit mathcity documentation against POLICY-documentation.md.
SkillAFreshness: AClaude Code +9 - 0.565score
behavior-verify
tdupu
Use when an edit to a skill, an instruction file, or a prompt has to be shown to have changed the agent behavior it was meant to fix.
SkillAFreshness: AClaude Code +9 - 0.565score
check-citations
tdupu
Read-only citation audit for .tex files.
SkillAFreshness: AClaude Code +9 - 0.565score
check-grant-format
tdupu
Audit an NSF proposal folder against Grants/GRANT-FORMAT.md (page limits, fonts, margins, required headings, no URLs in the description, prior-support items…
SkillAFreshness: AClaude Code +9 - 0.565score
check-grant-style
tdupu
Audit an NSF Project Description and Summary against Grants/GRANT-STYLE.md (every project has a plan and names what is new; results in prose with citations…
SkillAFreshness: AClaude Code +9 - 0.565score
check-latex
tdupu
Produce the evidence block the human adjudicator needs to approve or reject a notes.tex (or any notes-tier .tex) change before push/merge.
SkillAFreshness: AClaude Code +9 - 0.565score
check-latex-hygiene
tdupu
Audit LaTeX beads, branches, or .tex diffs against the LaTeX Subdomain Policy (mathcity/subdomains/latex/POLICY.md, LX-rules).
SkillAFreshness: AClaude Code +9 - 0.565score
check-lmfdb-hygiene
tdupu
Audit an LMFDB-type bead, diff, experiment proposal, or live type against the LMFDB Subdomain Policy (mathcity/subdomains/lmfdb/POLICY.md) — labels valid…
SkillAFreshness: AClaude Code +9 - 0.564score
behavior-cause
tdupu
Use when a reproduced agent behavior has to be traced to the artifacts whose text produced it.
SkillAFreshness: AClaude Code +9 - 0.561score
behavior-repro
tdupu
Use as step 1 when a complaint about an agent's behavior has to become evidence, before any cause is diagnosed or any artifact edited.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 14, 2026 (14 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- GPL-3.0
- Repository
- github.com/tdupu/agent-skills-public
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from tdupu
- 0.570score
assemble-recording-series
tdupu
Assemble one lecture or talk video from a folder of raw takes, whatever the capture tool wrote - flat screen-capture files, or per-session folders with the…
SkillAFreshness: AClaude Code +9 - 0.570score
check-paragraph
tdupu
Judge ONE paragraph of prose (LaTeX allowed) as its stated reader and return a fixed six-line verdict — topic sentence, one idea, reader can follow, claim…
SkillAFreshness: AClaude Code +9 - 0.565score
check-citations
tdupu
Read-only citation audit for .tex files.
SkillAFreshness: AClaude Code +9 - 0.565score
behavior-verify
tdupu
Use when an edit to a skill, an instruction file, or a prompt has to be shown to have changed the agent behavior it was meant to fix.
SkillAFreshness: AClaude Code +9 - 0.565score
check-documentation-policy
tdupu
Audit mathcity documentation against POLICY-documentation.md.
SkillAFreshness: AClaude Code +9 - 0.565score
check-grant-format
tdupu
Audit an NSF proposal folder against Grants/GRANT-FORMAT.md (page limits, fonts, margins, required headings, no URLs in the description, prior-support items…
SkillAFreshness: AClaude Code +9
Cite this page
add-figure skill. Agent Mart. https://agentmart.dev/skills/tdupu-add-figure (last updated 2026-10-24)