Grant Proposal Assistant
aipoch/medical-research-skills
Assist with biomedical grant proposal drafting, structure, and revision; use when preparing fundable proposal sections, aligning aims and methods, or improving reviewer-facing clarity.
Analyze failed or stuck proofs and propose auxiliary lemmas to help complete the proof in Isabelle/HOL or Coq.
$ npx skills add ArabelaTso/Skills-4-SE --skill lemma-discovery-assistant -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ArabelaTso/Skills-4-SE lemma-discovery-assistant --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/ArabelaTso/Skills-4-SE.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/lemma-discovery-assistant .claude/skills/lemma-discovery-assistant && 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 "lemma-discovery-assistant" agent skill from https://github.com/ArabelaTso/Skills-4-SE/tree/main/skills/lemma-discovery-assistant into .claude/skills/lemma-discovery-assistant/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lemma-discovery-assistant", 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/ArabelaTso/Skills-4-SE/tree/main/skills/lemma-discovery-assistantType 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 ArabelaTso/Skills-4-SE --skill lemma-discovery-assistant -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ArabelaTso/Skills-4-SE lemma-discovery-assistant --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ArabelaTso/Skills-4-SE.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/lemma-discovery-assistant .agents/skills/lemma-discovery-assistant && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "lemma-discovery-assistant" agent skill from https://github.com/ArabelaTso/Skills-4-SE/tree/main/skills/lemma-discovery-assistant into .agents/skills/lemma-discovery-assistant/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lemma-discovery-assistant", 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 ArabelaTso/Skills-4-SE --skill lemma-discovery-assistant -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ArabelaTso/Skills-4-SE lemma-discovery-assistant --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ArabelaTso/Skills-4-SE.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/lemma-discovery-assistant .cursor/skills/lemma-discovery-assistant && 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 "lemma-discovery-assistant" agent skill from https://github.com/ArabelaTso/Skills-4-SE/tree/main/skills/lemma-discovery-assistant into .cursor/skills/lemma-discovery-assistant/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lemma-discovery-assistant", 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/ArabelaTso/Skills-4-SE.git --path skills/lemma-discovery-assistant--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 ArabelaTso/Skills-4-SE --skill lemma-discovery-assistant -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ArabelaTso/Skills-4-SE lemma-discovery-assistant --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ArabelaTso/Skills-4-SE.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/lemma-discovery-assistant .gemini/skills/lemma-discovery-assistant && 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 "lemma-discovery-assistant" agent skill from https://github.com/ArabelaTso/Skills-4-SE/tree/main/skills/lemma-discovery-assistant into .gemini/skills/lemma-discovery-assistant/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lemma-discovery-assistant", 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 ArabelaTso/Skills-4-SE lemma-discovery-assistantInstalls 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 ArabelaTso/Skills-4-SE --skill lemma-discovery-assistant -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/ArabelaTso/Skills-4-SE.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/lemma-discovery-assistant .github/skills/lemma-discovery-assistant && 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 "lemma-discovery-assistant" agent skill from https://github.com/ArabelaTso/Skills-4-SE/tree/main/skills/lemma-discovery-assistant into .github/skills/lemma-discovery-assistant/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lemma-discovery-assistant", 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 ArabelaTso/Skills-4-SE --skill lemma-discovery-assistant -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install ArabelaTso/Skills-4-SE lemma-discovery-assistant --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ArabelaTso/Skills-4-SE.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/lemma-discovery-assistant .opencode/skills/lemma-discovery-assistant && 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 "lemma-discovery-assistant" agent skill from https://github.com/ArabelaTso/Skills-4-SE/tree/main/skills/lemma-discovery-assistant into .opencode/skills/lemma-discovery-assistant/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lemma-discovery-assistant", 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.
lemma-discovery-assistantAnalyze failed or stuck proofs and propose auxiliary lemmas to help complete the proof in Isabelle/HOL or Coq.
Lemma Discovery Assistant is an agent skill from ArabelaTso/Skills-4-SE. Analyze failed or stuck proofs and propose auxiliary lemmas to help complete the proof in Isabelle/HOL or Coq. Use when encountering proof failures, stuck proof states, unprovable subgoals, or when needing to strengthen induction hypotheses. Identifies missing lemmas, suggests proof strategies, and generates helper lemmas with appropriate statements and proof sketches. Supports inductive proofs, case analysis, rewriting, and complex proof obligations.
Its SKILL.md is about 2.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `references/coq_lemmas.md`, `references/isabelle_lemmas.md` and `references/proof_patterns.md`).
The repository describes itself as: A curated list of 180+ useful Claude Skills for Software Engineering and resources for customizing AI for SE workflows. The licence is Apache-2.0.
5 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 4f38503. It shows what the files ask for, not the result of running them.
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.
No scripts in the folder and no shell commands in SKILL.md (its code samples are isabelle and coq).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Lemma Discovery Assistant loads about 2.7k tokens when it runs, and up to ~10k if it reads all its reference files. Until then it costs about 120 tokens; SKILL.md has 843 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.
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.
The full file from ArabelaTso/Skills-4-SE at commit 4f38503, republished under its Apache-2.0 licence (© ArabelaTso). 843 words, ~2,731 tokens.
.claude/skills/lemma-discovery-assistant/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.Analyze stuck or failed proofs and propose auxiliary lemmas that can help complete the proof.
When proofs fail or get stuck, the issue is often a missing auxiliary lemma. This skill helps identify what lemmas are needed by:
Unprovable subgoal:
Weak induction hypothesis:
Missing intermediate steps:
Insufficient rewrite rules:
Examine the current proof context:
What to look for:
Questions to ask:
Determine what's preventing progress:
Gap types:
Formulate precise lemma statement:
Lemma characteristics:
Example patterns:
(* Isabelle *)
lemma helper_name: "⟦ assumptions ⟧ ⟹ conclusion"
(* Coq *)
Lemma helper_name : assumptions → conclusion.Provide guidance on proving the lemma:
Strategy types:
Show how the lemma helps the main proof:
Problem: Induction hypothesis too weak.
Solution: Strengthen the induction hypothesis.
Example (Isabelle):
Stuck proof:
lemma "length (reverse xs) = length xs"
proof (induction xs)
case Nil
then show ?case by simp
next
case (Cons x xs)
(* Stuck: reverse (x # xs) = reverse xs @ [x]
but we don't have a lemma about length of append *)
then show ?case sorry
qedProposed lemma:
lemma length_append: "length (xs @ ys) = length xs + length ys"
proof (induction xs)
case Nil
then show ?case by simp
next
case (Cons x xs)
then show ?case by simp
qedUsage: Apply length_append in the induction step.
Problem: Statement too specific to prove by induction.
Solution: Generalize with accumulator or additional parameter.
Example (Coq):
Stuck proof:
Fixpoint reverse {A} (l : list A) : list A :=
match l with
| [] => []
| x :: xs => reverse xs ++ [x]
end.
Lemma reverse_involutive : forall A (l : list A),
reverse (reverse l) = l.
Proof.
induction l.
- reflexivity.
- simpl. (* Stuck: need reverse (reverse l ++ [a]) = a :: l *)
Abort.Proposed lemma:
Lemma reverse_append : forall A (l1 l2 : list A),
reverse (l1 ++ l2) = reverse l2 ++ reverse l1.
Proof.
induction l1; intros; simpl.
- rewrite app_nil_r. reflexivity.
- rewrite IHl1. rewrite app_assoc. reflexivity.
Qed.Usage: Use reverse_append to handle the append in the goal.
Problem: Simplification doesn't reach desired form.
Solution: Add rewrite rules for specific patterns.
Example (Isabelle):
Stuck proof:
lemma "map f (map g xs) = map (f ∘ g) xs"
proof (induction xs)
case Nil
then show ?case by simp
next
case (Cons x xs)
(* Need: (f ∘ g) x = f (g x) *)
then show ?case sorry
qedProposed lemma:
lemma comp_apply: "(f ∘ g) x = f (g x)"
by (simp add: comp_def)Usage: Add to simplification set or apply explicitly.
Problem: Need properties about data structure operations.
Solution: Prove fundamental properties of the structure.
Example (Coq):
Stuck proof:
Fixpoint insert (x : nat) (t : tree) : tree := (* ... *)
Lemma insert_member : forall x t,
member x (insert x t) = true.
Proof.
induction t.
- (* Stuck: need properties of member and insert *)
Abort.Proposed lemmas:
Lemma member_insert_eq : forall x y t,
x = y → member x (insert y t) = true.
Lemma member_insert_neq : forall x y t,
x ≠ y → member x (insert y t) = member x t.
Lemma member_insert : forall x y t,
member x (insert y t) = (x =? y) || member x t.Usage: Case split on x = y and apply appropriate lemma.
For Isabelle-specific lemma patterns, tactics, and the sledgehammer tool, see references/isabelle_lemmas.md.
Key features:
try and try0 for tactic explorationFor Coq-specific lemma patterns, tactics, and proof search, see references/coq_lemmas.md.
Key features:
Search and SearchAbout for finding lemmasauto, eauto for proof searchLtacFor detailed lemma patterns organized by category, see references/proof_patterns.md.
Categories include:
Scenario: Proving correctness of insertion sort.
Main theorem (Isabelle):
lemma insertion_sort_correct:
"sorted (insertion_sort xs) ∧ mset (insertion_sort xs) = mset xs"Stuck proof:
proof (induction xs)
case Nil
then show ?case by simp
next
case (Cons x xs)
(* Need to show:
sorted (insert x (insertion_sort xs))
mset (insert x (insertion_sort xs)) = mset (x # xs) *)
then show ?case sorry
qedAnalysis:
insert functioninsert preserves sortinginsert preserves multisetProposed lemmas:
(* Lemma 1: insert preserves sorting *)
lemma insert_sorted:
"sorted xs ⟹ sorted (insert x xs)"
proof (induction xs)
case Nil
then show ?case by simp
next
case (Cons y ys)
then show ?case
by (auto simp: sorted_Cons)
qed
(* Lemma 2: insert preserves multiset *)
lemma mset_insert:
"mset (insert x xs) = {#x#} + mset xs"
proof (induction xs)
case Nil
then show ?case by simp
next
case (Cons y ys)
then show ?case by (auto simp: ac_simps)
qed
(* Lemma 3: sorted definition for cons *)
lemma sorted_Cons:
"sorted (x # xs) = (sorted xs ∧ (∀y ∈ set xs. x ≤ y))"
by (auto simp: sorted_append)Revised main proof:
lemma insertion_sort_correct:
"sorted (insertion_sort xs) ∧ mset (insertion_sort xs) = mset xs"
proof (induction xs)
case Nil
then show ?case by simp
next
case (Cons x xs)
have "sorted (insertion_sort xs)" using Cons by simp
then have "sorted (insert x (insertion_sort xs))"
by (rule insert_sorted)
moreover have "mset (insert x (insertion_sort xs)) = {#x#} + mset (insertion_sort xs)"
by (rule mset_insert)
moreover have "mset (insertion_sort xs) = mset xs"
using Cons by simp
ultimately show ?case by (auto simp: ac_simps)
qedPossible issues:
Solutions:
Possible issues:
Solutions:
For detailed guidance on specific aspects:
© ArabelaTso, 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
SKILL.md and 3 other files (references) in skills/lemma-discovery-assistant of ArabelaTso/Skills-4-SE.
Open the folder on GitHubat commit 4f38503
Lemma Discovery Assistant 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 |
|---|---|---|---|---|---|---|
| Lemma Discovery Assistant this skillArabelaTso/Skills-4-SE | 253 | — | ~2.7k | Automated safety check: Pass | Apache-2.0 | |
| Grant Proposal Assistantaipoch/medical-research-skills | 1.9k | — | ~2.6k | Automated safety check: Pass | MIT | |
| Geo Proposalsickn33/agentic-awesome-skills | 47k | 1 repos | ~3.2k | Automated safety check: Notes | MIT | |
| Better Proposals AutomationComposioHQ/awesome-claude-skills | 77k | 3 repos | ~764 | Automated safety check: Pass | None | |
| Proof Videoopenclaw/openclaw | 392k | — | ~2.4k | Automated safety check: Pass | MIT | |
| Contract And Proposal Writeralirezarezvani/claude-skills | 28k | 2 repos | ~3.4k | Automated safety check: Pass | MIT |
aipoch/medical-research-skills
Assist with biomedical grant proposal drafting, structure, and revision; use when preparing fundable proposal sections, aligning aims and methods, or improving reviewer-facing clarity.
sickn33/agentic-awesome-skills
Auto-generate a professional, client-ready GEO service proposal from audit data.
ComposioHQ/awesome-claude-skills
Automate Better Proposals tasks via Rube MCP (Composio). An agent skill from ComposioHQ/awesome-claude-skills.
openclaw/openclaw
Add subtitles, captions, narration cues, or zoom to a proof video or PR recording using repo-local capture helpers and a system ffmpeg renderer.
alirezarezvani/claude-skills
Generate professional, jurisdiction-aware business documents: freelance contracts, project proposals, SOWs, NDAs, and MSAs.
Chorus-AIDLC/Chorus
Chorus Proposal workflow on Hermes — create proposals with document and task drafts, manage dependency DAG, validate, submit, and run the read-only proposal reviewer via delegatetask.
ArabelaTso/Skills-4-SE
Generate prioritized CVE watchlists and actionable security recommendations for repositories.
ArabelaTso/Skills-4-SE
Automatically migrate Python web applications between frameworks (Flask → FastAPI, Django → FastAPI).
ArabelaTso/Skills-4-SE
Generate test cases using metamorphic testing by applying transformations based on metamorphic properties.
ArabelaTso/Skills-4-SE
Instruments programs to capture execution traces specifically for reproducing reported bugs, enabling consistent replay and diagnosis of failures.
ArabelaTso/Skills-4-SE
Automatically migrate Spring MVC applications to Spring Boot.
ArabelaTso/Skills-4-SE
Instrument programs (Python, C/C++, Java) to capture snapshots of key program states at runtime, including variables, memory, and call stacks.
Analyze failed or stuck proofs and propose auxiliary lemmas to help complete the proof in Isabelle/HOL or Coq. Lemma Discovery Assistant is an agent skill from ArabelaTso/Skills-4-SE. Analyze failed or stuck proofs and propose auxiliary lemmas to help complete the proof in Isabelle/HOL or Coq.
Lemma Discovery Assistant fits situations like: encountering proof failures; stuck proof states; unprovable subgoals; needing to strengthen induction hypotheses.
Run `npx skills add ArabelaTso/Skills-4-SE --skill lemma-discovery-assistant -a claude-code`. Or copy the skill folder (skills/lemma-discovery-assistant in ArabelaTso/Skills-4-SE) into .claude/skills/lemma-discovery-assistant in your project. Claude Code loads it when a task matches its description.
Run `npx skills add ArabelaTso/Skills-4-SE --skill lemma-discovery-assistant -a codex`. Or copy the skill folder (skills/lemma-discovery-assistant in ArabelaTso/Skills-4-SE) into .agents/skills/lemma-discovery-assistant in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ArabelaTso/Skills-4-SE --skill lemma-discovery-assistant -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/lemma-discovery-assistant, .gemini/skills/lemma-discovery-assistant, .github/skills/lemma-discovery-assistant and .opencode/skills/lemma-discovery-assistant in your project.
SKILL.md names no scripts, command-line tools or credentials: Lemma Discovery Assistant is instructions for the agent only.
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.
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.
Lemma Discovery Assistant 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.
About 2.7k tokens (SKILL.md is roughly 11k 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 7.4k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Lemma Discovery Assistant: Grant Proposal Assistant (aipoch/medical-research-skills, 1.9k stars), Geo Proposal (sickn33/agentic-awesome-skills, 47k stars), Better Proposals Automation (ComposioHQ/awesome-claude-skills, 77k stars) and Proof Video (openclaw/openclaw, 392k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
ArabelaTso (a GitHub user) maintains it in ArabelaTso/Skills-4-SE, which has 253 GitHub stars. The repository holds 170 skills in this directory. The repository was last updated on August 21, 2026.
Source: ArabelaTso/Skills-4-SE on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.