codex/skills/research-software/SKILL.md
Research software tools via source code, GitHub, web. Use when creating skills, learning new tools, finding undocumented features, or bleeding-edge patterns.
npx skillsauth add tkersey/dotfiles research-softwareInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Rules: Latest STABLE tag (not main). Filter to 2025-2026. Code > Docs. Skip Stack Overflow.
Every research produces this structure:
## [Tool] vX.Y.Z (YYYY-MM-DD)
**Repo:** github.com/org/repo @ abc123
### Commands
| Task | Command | Notes |
|------|---------|-------|
### Config
| Option | Default | Notes |
|--------|---------|-------|
### Env Vars
| Variable | Purpose |
|----------|---------|
### Gotchas
- [problem]: [fix]. Source: [PR/issue/code]
### Sources
- Code: [file:line]
- PRs: #123, #456
- Posts: [url]
Research [TOOL] for [PURPOSE].
Clone to /tmp, checkout latest stable tag.
Spawn Explore agent on source. Find: CLI, config, hidden flags, env vars.
Parallel: GitHub PRs/issues, web search "[tool] 2025".
Output: skill-ready markdown.
# 0. Detect context (if in a project)
# Check package.json, Cargo.toml, pyproject.toml for existing versions
# 1. Clone + stable tag
git clone --depth 1 https://github.com/[org]/[repo] /tmp/[repo]-research
cd /tmp/[repo]-research && git fetch --tags && git checkout $(git describe --tags --abbrev=0)
# 2. Spawn Explore agent (parallel with step 3-4)
# → "Find all CLI commands, config options, hidden flags, env vars in /tmp/[repo]-research"
# 3. GitHub activity
gh pr list -R [org]/[repo] --state merged --limit 30 --json title,mergedAt
gh issue list -R [org]/[repo] --label question --limit 20
# 4. Web search
# → "[tool] 2025" "[tool] 2026" "[tool] tutorial"
# 5. Synthesize → Output structure above
# 6. Cleanup
rm -rf /tmp/[repo]-research
rm -rf /tmp/[repo]-research1. Source code (actual behavior)
2. Recent PRs (features being added)
3. GitHub issues (real problems)
4. Blog posts 2025-2026 (practical patterns)
5. Official docs (baseline, often outdated)
Skip: Stack Overflow, anything pre-2025, basic tutorials
| Mistake | Fix |
|---------|-----|
| Using beta/canary | Checkout latest stable TAG, not main |
| Old content (pre-2025) | Always add year to search queries |
| Trusting docs over code | Code wins: check actual defaults in source |
| Missing env vars | Search process.env, std::env, os.environ |
| Forgetting cleanup | rm -rf /tmp/[repo]-research when done |
# Hidden/experimental flags
rg "hidden|experimental|unstable" /tmp/[repo]-research
# Environment variables by language
rg "process\.env\." /tmp/[repo]-research --type ts # TypeScript
rg "std::env::" /tmp/[repo]-research --type rust # Rust
rg "os\.environ" /tmp/[repo]-research --type py # Python
rg "os\.Getenv" /tmp/[repo]-research --type go # Go
# Recent changes
git log --oneline --since="2025-06-01" | head -30
What are you researching?
│
├─ CLI tool (wrangler, cargo, bun)
│ Focus: src/cli/, commands, flags, env vars
│
├─ Library/Framework (React, Next.js)
│ Focus: packages/*/src/, exported APIs, deprecations
│
├─ Runtime (Bun, Deno, Node)
│ Focus: built-ins, runtime flags, compat layers
│
└─ Database/Service (D1, R2, Postgres)
Focus: query syntax, config, limits, gotchas
| Type | Where to look | Key searches |
|------|---------------|--------------|
| CLI | src/cli/, bin/ | hidden.*true, #[arg(, process.env |
| Library | packages/*/src/, index.ts | export , deprecated, experimental |
| Runtime | src/, built-ins | flag, --, compat |
| Database | queries, limits | limit, max, error |
Deep strategies: STRATEGIES.md
Investigate /tmp/[repo]-research for [TOOL].
Find: CLI commands, config options, hidden/experimental flags, env vars.
Check git log --oneline -30 for recent changes.
Output as markdown tables.
Use model: sonnet (balance of speed + depth)
Search "[TOOL] 2025" and "[TOOL] 2026".
Find 5-10 recent tutorials, blog posts, announcements.
Extract: patterns, gotchas, tips.
Skip: Stack Overflow, anything pre-2025, basic tutorials.
Use model: haiku (fast, web-focused)
| Need | File | |------|------| | Output templates by tool type | OUTPUT-TEMPLATES.md | | Example research sessions | EXAMPLES.md | | Tool-specific deep strategies | STRATEGIES.md |
tools
Invokes Apple's macOS 27 fm command-line tool from a local Mac to use the on-device system model or Private Cloud Compute, including instructions, image prompts, schema-constrained JSON, and noninteractive automation. Use when the user asks to run Apple Foundation Models through fm, compare system versus pcc, generate structured output, or automate fm without Swift or an app.
development
Compile historical Codex sessions into governed counterfactual evidence, evaluate an existing owner-applied candidate through blinded paired HCTP trials, and fold observable evidence into RUN, OBSERVE, or STOP. Use for `$hylo`, CRF extraction, counterfactual replay, source-governed direct or historical trials, sealed evidence, paired baseline/candidate evaluation, causal frontiers, or evidence-governed improvement.
testing
Ensure a `ledger` command is available on PATH; materialize, validate, record, replay, and project requested Actuating artifacts without taking semantic or execution authority; coordinate the shared Learnings/Synesthesia/Negative Ledger lifecycle checkpoint and repo-local source-memory reconciliation; address Universalist plans and receipts; and perform pure artifact validation.
testing
Classify and quotient review findings, failing tests, incidents, bug reports, migration failures, and other witnessed falsifiers against accepted intent and the current Construction. Author counterexample-set/v1 without selecting repairs, counting review credit, or granting mutation.