CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

proof-checker

Rigorous mathematical proof verification and fixing workflow. Reads a LaTeX proof, identifies gaps via fresh-agent Codex GPT-6-Astra ultra review, fixes each gap with full derivations, re-reviews, and generates an audit report. Base review is same-family provisional. Use when user says "检查证明", "verify proof", "proof check", "审证明", "check this proof", or wants rigorous mathematical verification of a theory paper.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

77%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.

An exceptionally actionable and well-sequenced deep-audit workflow with exemplary validation gates and feedback loops. Its weaknesses are token efficiency (heavily duplicated reviewer-protocol rules) and structure (reference-grade content inlined while all cross-file links point outside the bundle and are unresolvable as shipped).

Suggestions

Deduplicate the review-independence and reviewer-tier rules — currently restated in the opening blockquote, Key Rules, Phase 3, and the Submission Artifact section — into a single 'Reviewer protocol' section.

Move the 20-category issue taxonomy and the side-condition checklists to a references/ file (e.g. references/issue-taxonomy.md), keeping only a one-line summary per group in SKILL.md.

Normalize reference paths (some use ../shared-references/, others shared-references/) and either ship the referenced files with the skill bundle or remove the links.

DimensionReasoningScore

Conciseness

Mostly dense, non-obvious operational content, but reviewer-independence and model-tier rules ("same-family/provisional", "never use send_input", "always ultra") are repeated across the opening blockquote, Key Rules, Phase 3, and the Submission section, and Phase 5.5 embeds a padded shell fallback-resolution chain. Not 4: the duplication is substantive enough that the body could be tightened by roughly a quarter without losing information.

3 / 5

Actionability

Provides exact copy-paste-ready artifacts: full spawn_agent prompt blocks with model/effort parameters, pdflatex compile commands, the complete PROOF_AUDIT.json schema, structured per-issue output formats, and a concrete python3 add_claim invocation. Not 4: the common cases (review prompt, fix record, compile check, artifact emission) are all fully executable with no gaps.

5 / 5

Workflow Clarity

Phases 0–5.5 are explicitly sequenced with an objective acceptance gate, per-fix compile checks, re-review loops with MAX_REVIEW_ROUNDS, blind second review that re-enters Phase 2 on failure, a regression audit, and an honest unrecoverable-proof protocol. Not 4: validation checkpoints and error-recovery feedback loops are explicit at every stage, matching the anchor-5 example.

5 / 5

Progressive Disclosure

The body is well-sectioned with clearly signaled links, but the ~100-line issue taxonomy, severity system, and side-condition checklists are fully inlined, and every referenced file (../shared-references/reviewer-backends.md, shared-references/reviewer-routing.md, ../shared-references/fan-out-pattern.md, ../lean-formalize/SKILL.md, shared-references/assurance-contract.md) lives outside the bundle with inconsistent path styles — none ship alongside SKILL.md. Not 4: the dangling, inconsistently-pathed external references and the heavy inline reference-grade content are more than minor organization gaps; not 2 because the section structure is real and navigation within the file is easy.

3 / 5

Total

16

/

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.

A strong description: concrete end-to-end action coverage plus an explicit bilingual trigger clause. The only weakness is the internal assurance jargon ("Base review is same-family provisional"), which reads as implementation detail and adds noise without aiding user triggering.

DimensionReasoningScore

Specificity

"Reads a LaTeX proof, identifies gaps via fresh-agent… review, fixes each gap with full derivations, re-reviews, and generates an audit report" lists multiple concrete actions comprehensively covering the verify→fix→re-review→report workflow. Not 4: the action coverage is complete end-to-end, with no gaps; the only blemish is the opaque trailing sentence, which is noise rather than a missing capability.

5 / 5

Completeness

Explicitly answers both 'what' (a multi-phase verify/fix/re-review/audit-report workflow with concrete actions) and 'when' ("Use when user says…" with concrete trigger phrases). Not 4: the 'when' clause is fully explicit with quoted trigger phrases, matching the anchor-5 example pattern exactly.

5 / 5

Trigger Term Quality

"Use when user says '检查证明', 'verify proof', 'proof check', '审证明', 'check this proof'" provides good natural trigger coverage including bilingual variants. Not 5: common synonyms such as "review the proof", "check the math", or file-extension triggers like ".tex" are missing.

4 / 5

Distinctiveness Conflict Risk

A clear niche — rigorous mathematical proof verification of LaTeX theory papers — with proof-specific triggers that no general document or paper-review skill would claim. Not 4: the "proof"-centric phrasing and theory-paper scoping leave virtually no overlap risk with related skills.

5 / 5

Total

19

/

20

Passed

Validation

75%

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

Validation — 12 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (606 lines); consider splitting into references/ and linking

Warning

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 3 suspicious

Warning

Total

12

/

16

Passed

Repository

wanshuiyin/Auto-claude-code-research-in-sleep

Path

skills/skills-codex/proof-checker/SKILL.md

Reviewed

Table of Contents

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.