Best use case
corpus-health is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
It is a strong fit for teams already working in Codex.
Report on research corpus health, completeness, and integrity
Teams using corpus-health should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/corpus-health/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How corpus-health Compares
| Feature / Agent | corpus-health | Standard Approach |
|---|---|---|
| Platform Support | Codex | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Report on research corpus health, completeness, and integrity
Which AI agents support this skill?
This skill is designed for Codex.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
Cursor vs Codex for AI Workflows
Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.
AI Agents for Startups
Explore AI agent skills for startup validation, product research, growth experiments, documentation, and fast execution with small teams.
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
SKILL.md Source
# Corpus Health Command Assess the health and completeness of the research corpus at `.aiwg/research/`. ## Kernel Delegation > As of ADR-021, `corpus-health` delegates structural lint to the semantic memory kernel. **Delegation pattern**: 1. `corpus-health` retains its research-specific health-check UX 2. Delegates to `memory-lint --consumer research-complete --severity warning` 3. Research-specific layers remain in this wrapper: - GRADE coverage check - Citation completeness validation - Research corpus-specific metrics **Backward compatibility**: No UX changes. @agentic/code/addons/semantic-memory/skills/memory-lint/SKILL.md ## Instructions When invoked, analyze the research corpus and report on its health: 1. **Scan Corpus Structure** - Count sources in `.aiwg/research/sources/` - Count findings in `.aiwg/research/findings/` - Count quality assessments in `.aiwg/research/quality-assessments/` - Count provenance records in `.aiwg/research/provenance/records/` 2. **Frontmatter Completeness** - Check each source for required frontmatter per @$AIWG_ROOT/agentic/code/frameworks/sdlc-complete/schemas/research/frontmatter-schema.yaml - Report sources missing: ref_id, title, authors, year, DOI, key_findings - Calculate completeness percentage 3. **PDF Integrity** - Check `.aiwg/research/pdfs/` for downloaded papers - Verify SHA-256 checksums against frontmatter `pdf_hash` values - Report missing PDFs and checksum mismatches 4. **Cross-Reference Integrity** - Verify all REF-XXX in findings reference valid sources - Check for orphaned findings (no source reference) - Check for orphaned sources (never cited in any artifact) 5. **Staleness Check** - Flag sources with `last_verified` > 90 days old - Flag DOIs that haven't been re-verified - Report sources needing refresh 6. **Evidence Gaps** - Load `.aiwg/research/TODO.md` for planned research - Count unresolved evidence gaps - Report gap severity distribution 7. **Generate Health Report** - Summary dashboard with pass/warn/fail indicators - Detailed findings per category - Action items prioritized by severity ## Arguments - `--brief` - Show summary only - `--fix` - Attempt to fix frontmatter gaps and regenerate checksums - `--report` - Save report to `.aiwg/reports/corpus-health.md` ## References - @$AIWG_ROOT/agentic/code/frameworks/sdlc-complete/schemas/research/frontmatter-schema.yaml - Frontmatter requirements - @$AIWG_ROOT/agentic/code/frameworks/sdlc-complete/schemas/research/fixity-manifest.yaml - Fixity verification - @$AIWG_ROOT/agentic/code/frameworks/sdlc-complete/rules/research-metadata.md - Research metadata rules - @$AIWG_ROOT/agentic/code/frameworks/sdlc-complete/agents/citation-verifier.md - Citation Verifier agent
Related Skills
workspace-health
Assess workspace alignment and recommend cleanup or realignment actions at key lifecycle transition points
project-health-check
Analyze overall project health and metrics
kb-health
Lint and health-check the knowledge base. Finds orphan pages, missing cross-references, stale claims, broken wiki-links, and regenerates the index.
corpus-snapshot
Generate a comprehensive corpus snapshot report from template, computing all metrics (dimensions, topology, degree distribution, delta from previous) and assisting with analysis sections (clusters, chains, gaps).
corpus-index-build
Build graph indices (by-topic, by-year, authors, citation-network) from corpus state using definitions in .aiwg/config.yaml. Replaces manual 3-agent dispatch with a single command.
corpus-export
Package corpus subsets as distribution archives. Select papers by cluster, topic, REF range, or custom filter; bundle PDFs, analysis docs, citation sidecars, web sources, and BibTeX into a tar.gz with manifest.
codebase-health
Scan source code and report agent-readiness metrics with actionable recommendations
aiwg-orchestrate
Route structured artifact work to AIWG workflows via MCP with zero parent context cost
venv-manager
Create, manage, and validate Python virtual environments. Use for project isolation and dependency management.
pytest-runner
Execute Python tests with pytest, supporting fixtures, markers, coverage, and parallel execution. Use for Python test automation.
vitest-runner
Execute JavaScript/TypeScript tests with Vitest, supporting coverage, watch mode, and parallel execution. Use for JS/TS test automation.
eslint-checker
Run ESLint for JavaScript/TypeScript code quality and style enforcement. Use for static analysis and auto-fixing.