CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

integrity-forensics

Run the Anti-Autoresearch integrity-forensics sweep (span-anchored evidence ledger → GPT auditors propose findings → a rules-only reporter that lists every proposal with what the auditor said about it) against a paper via a SHA-pinned thin launcher — then convert the verdict into a typed policy gate (BLOCK/WARN/NO_NEW_BLOCKER) and an append-only obligations ledger. Use when user says "integrity forensics", "forensic audit this paper", "投稿前自查诚信", "审这篇论文的诚信", or says "anti-autoresearch" when the upstream repo's own skills are not installed. Also invoked by /paper-writing (submission self-forensics, default ON), /peer-review (forensic appendix), /resubmit-pipeline.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

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.

The body is a dense, well-sequenced protocol with strong validation and feedback loops and concrete executable commands, scoring high on workflow clarity and actionability. Its main weakness is progressive disclosure: it is a long monolithic file with maintainer and host-specific notes inlined that could be split into bundled reference files, and several command placeholders remain unresolved.

Suggestions

Move the maintainer-facing 'Pin-bump checklist' and the 'Codex-native note (mirror)' into bundled reference files (e.g. references/pin-bump.md, references/codex-native.md) and link to them one level deep, keeping SKILL.md an overview.

Resolve or pre-fill the placeholders in the executable commands ($PAPER_DIR, $GATE_HELPER, <this pipeline's executor>, <id>) with concrete resolution guidance — e.g. show how $GATE_HELPER resolves via the canonical chain in the command itself — to reach copy-paste-ready actionability.

Trim discursive asides that don't drive action (the unused ~/.claude clone cleanup note, the trust-boundary philosophy paragraph) to tighten conciseness toward the lean ideal.

DimensionReasoningScore

Conciseness

Mostly efficient and information-dense with genuinely non-obvious protocol content, but a few explanatory asides (the unused-clone cleanup note, Codex-native mirror, trust-boundary philosophy prose) could be trimmed; not the level-5 lean ideal but well above the level-3 'could be tightened' band.

4 / 5

Actionability

Provides concrete, executable bash blocks with real commands and exit codes (bootstrap, evaluate, resolve/waive), but key invocations still contain placeholders ($PAPER_DIR, $GATE_HELPER, <id>, <this pipeline's executor>) the agent must resolve, leaving minor gaps short of fully copy-paste-ready.

4 / 5

Workflow Clarity

Steps 0-3 are clearly sequenced with explicit validation checkpoints (pristine-tree checks, eval-gate marker, fail-closed FATAL exits), a feedback loop (re-sweep after fixes), and a maintainer checklist, matching the level-5 anchor for clear sequence with explicit validation and error-recovery loops.

5 / 5

Progressive Disclosure

Section headers give decent internal navigation, but no bundle files (references/scripts/assets) exist despite the ~280-line body, and detail that could live in separate files (pin-bump maintainer checklist, Codex-native note, gate semantics) is inlined; it sits above the level-2 'minimal structure' anchor but below level-4 due to inlined bulk and absence of offloaded reference files.

3 / 5

Total

16

/

20

Passed

Description

100%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 exemplary: it states concrete capabilities, gives rich natural trigger terms (including multilingual synonyms and slash commands), and explicitly covers both what the skill does and when to invoke it. It occupies a distinct niche with minimal overlap risk.

DimensionReasoningScore

Specificity

Names multiple concrete actions — 'Run the Anti-Autoresearch integrity-forensics sweep', 'convert the verdict into a typed policy gate (BLOCK/WARN/NO_NEW_BLOCKER)', 'append-only obligations ledger' — covering the full pipeline comprehensively, matching the level-5 anchor for multiple specific concrete actions.

5 / 5

Completeness

Explicitly answers both what (the sweep, policy gate, obligations ledger) and when ('Use when user says ...'), with concrete trigger phrases, matching the level-5 anchor.

5 / 5

Trigger Term Quality

Comprehensive natural triggers including synonyms and multilingual phrases — 'integrity forensics', 'forensic audit this paper', '投稿前自查诚信', '审这篇论文的诚信', 'anti-autoresearch' — plus slash-command invocations, matching the level-5 anchor for broad coverage including synonyms.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (paper integrity forensics via a SHA-pinned launcher) with highly specific triggers unlikely to collide with other skills, matching the level-5 anchor for a distinct niche with minimal conflict risk.

5 / 5

Total

20

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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

Total

14

/

16

Passed

Repository

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

Path

skills/integrity-forensics/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.