proof-skeleton-generator

Generate structured proof skeletons with tactics, strategies, and intermediate lemmas for theorems in Isabelle/HOL or Coq. Use when users need to: (1) Create proof outlines for theorem statements, (2) Generate proof structure with tactic placeholders, (3) Identify key lemmas needed for a proof, (4) Plan proof strategies (induction, case analysis, forward/backward reasoning), (5) Scaffold proofs with intermediate steps and subgoals, or (6) Convert theorem statements into detailed proof templates. Supports both Isabelle/HOL and Coq equally.

1.24x

Quality

76%

Does it follow best practices?

Impact

92%

1.24x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/proof-skeleton-generator/SKILL.md

Quality

Content

61%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is well-structured with a clear workflow and genuinely actionable Isabelle/Coq skeleton templates, but it is padded with re-explanations of basic proof techniques and generic advice, and lacks explicit validation checkpoints embedded in the workflow. Tightening the conceptual re-teaching and adding a validate-step would raise the weaker dimensions.

Suggestions

Trim the 'Proof Strategy Selection Guide', 'Key Principles', and 'Tips' sections to remove re-explanations of basic proof concepts (induction, case analysis, direct proof) that Claude already knows, keeping only domain-specific decision guidance.

Add an explicit validation checkpoint to the workflow (e.g., 'Verify case analysis is exhaustive and induction is on the right variable before finalizing; fix and re-check if not') so exhaustiveness checks become a retry loop rather than implicit principles.

Move the detailed 'Common Patterns' code blocks and strategy-selection tables into the existing references (examples.md, isabelle_tactics.md, coq_tactics.md) so SKILL.md reads as a leaner overview that delegates depth to the bundle files.

Dimension	Reasoning	Score
Conciseness	The body re-teaches basic proof concepts Claude already knows ('List induction for list properties', 'When to Use Induction/Case Analysis/Direct Proof/Lemmas') and includes generic 'Key Principles' and 'Tips' sections that pad the token budget, though the structure and skeleton templates carry genuine value.	3 / 5
Actionability	Provides concrete copy-paste-ready Isabelle and Coq skeleton templates plus executable 'Common Patterns' code blocks (induction with simplification, forward reasoning chain, backward reasoning with rules), with named tactics (simp, auto, blast, sledgehammer); minor gaps remain in a few generic placeholders like 'method' and 'case_name'.	4 / 5
Workflow Clarity	A clear six-step sequence is present (Analyze -> Choose Target -> Determine Strategy -> Identify Lemmas -> Generate Skeleton -> Structure Output), but validation checkpoints and feedback loops are not embedded in the workflow; exhaustiveness/variable checks live only as implicit 'Correctness' principles rather than explicit validate-and-retry steps.	3 / 5
Progressive Disclosure	References three real one-level-deep bundle files with clearly signaled links (isabelle_tactics.md, coq_tactics.md, examples.md) in the Generate step, but the body also inlines a fair amount of strategy-selection and pattern detail that could live in those references, so the overview/detail split is good but not pristine.	4 / 5
	Total	14 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is strong: it clearly states what the skill does and when to use it, with comprehensive concrete actions and a distinctive proof-assistant niche. Its only mild weakness is trigger phrasing that reads as a task checklist rather than natural user language, with a few synonyms missing.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions including the headline 'Generate structured proof skeletons with tactics, strategies, and intermediate lemmas' plus six enumerated actions (create outlines, generate tactic placeholders, identify lemmas, plan strategies, scaffold subgoals, convert statements to templates), giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both 'what' ('Generate structured proof skeletons with tactics, strategies, and intermediate lemmas for theorems in Isabelle/HOL or Coq') and 'when' ('Use when users need to: (1)...(6)...') with concrete numbered trigger phrases.	5 / 5
Trigger Term Quality	Good keyword coverage with natural terms ('proof outlines', 'tactic placeholders', 'induction, case analysis, forward/backward reasoning') and system names Isabelle/HOL and Coq, but phrasing leans toward a task checklist ('Use when users need to: (1)...(6)') rather than mirroring casual user speech, and synonyms like 'proof sketch'/'prove' are only partially covered.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (proof-skeleton scaffolding for Isabelle/HOL and Coq) with distinctive triggers like 'tactic placeholders' and 'proof strategies (induction, case analysis)' that would not fire for unrelated skills; minimal conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: ArabelaTso/Skills-4-SE
Path: skills/proof-skeleton-generator/SKILL.md
Commit: 4f38503

Reviewed: 19 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.