Agent skill

lp-do-fact-find

Thin orchestrator for discovery, intake routing, and evidence-first fact-finding. Routes to specialized modules and emits analysis-ready artifacts for /lp-do-analysis. For understanding-only briefings, use /lp-do-briefing.

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill lp-do-fact-find --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 18 KB
Bundled scripts: none
Path: skills/analysis/lp-do-fact-find/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Fact Find Orchestrator `/lp-do-fact-find` is the intake and routing layer. Keep this file thin. This orchestrator does five things: 1. Discovery and selection (topic) 2. Sufficiency gate 3. Classification (track, deliverable) 4. Module routing (load only one relevant module, plus mixed-track add-on when needed) 5. Artifact persistence using shared templates + automatic critique Do not embed long templates, long checklists, or API payload blocks here. ## Global Invariants ### Operating mode **FACT-FIND ONLY** ### Repo actions (allowed) - Read/search files and docs. - Run non-destructive commands (for example `rg`, targeted tests, targeted lint/typecheck) when needed for evidence. - Inspect targeted git history. ### Prohibited actions - Code changes, refactors, migrations, or production data writes. - Destructive shell/git commands. - Analysis/planning/build execution (this skill ends at fact-find output). ### Evidence and quality rules - Evidence first: non-trivial claims require explicit pointers. - Unknowns must include a concrete verification path. - Omit sections with no evidence, or collapse to a one-line `Not investigated: <reason>`. - Process-affecting work must capture the

What's inside
Steps it walks through
  1. Global Invariants
  2. Operating mode
  3. Repo actions (allowed)
  4. Prohibited actions
  5. Evidence and quality rules
  6. Required Inputs
  7. Phase 0: Queue Check Gate
  8. Phase 1: Discovery and Selection
  9. Phase 2: Context Hydration
  10. Optional CASS Retrieval (Pilot, recommended)
  11. Access Declarations
  12. Phase 3: Sufficiency Gate
  13. Phase 4: Classification
  14. Phase 5: Route to a Single Module
Ships with 1 file
  • metadata.json
Commands it runs
pnpm startup-loop:cass-retrieve -- --mode fact-find --slug <feature-slug> --topic "<topic>"
scripts/validate-fact-find.sh docs/plans/<feature-slug>/fact-find.md docs/plans/<feature-slug>/critique-history.md
scripts/validate-engineering-coverage.sh docs/plans/<feature-slug>/fact-find.md
scripts/generate-stage-handoff-packet.sh docs/plans/<feature-slug>/fact-find.md
pnpm --filter scripts tsx scripts/src/startup-loop/write-skill-observation.ts -- \
More from claude-skill-registry
All skills →
About this skill
What does the lp-do-fact-find skill do?

Thin orchestrator for discovery, intake routing, and evidence-first fact-finding. Routes to specialized modules and emits analysis-ready artifacts for /lp-do-analysis. For understanding-only briefings, use /lp-do-briefing.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill lp-do-fact-find --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going