.claude/skills/joycraft-add-fact/SKILL.md
Capture a project fact and route it to the correct context document -- production map, dangerous assumptions, decision log, institutional knowledge, or troubleshooting
npx skillsauth add maksutovic/joycraft joycraft-add-factInstall 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.
The user has a fact to capture. Your job is to classify it, route it to the correct context document, append it in the right format, and optionally add a CLAUDE.md boundary rule.
If the user already provided the fact (e.g., /joycraft-add-fact the staging DB resets every Sunday), use it directly.
If not, ask: "What fact do you want to capture?" -- then wait for their response.
If the user provides multiple facts at once, process each one separately through all the steps below, then give a combined confirmation at the end.
Route the fact to one of these 5 context documents based on its content:
docs/context/production-map.mdThe fact is about infrastructure, services, environments, URLs, endpoints, credentials, or what is safe/unsafe to touch.
docs/context/dangerous-assumptions.mdThe fact is about something an AI agent might get wrong -- a false assumption that leads to bad outcomes.
users table looks like a test table but it's production", "Deleting a workspace doesn't delete the billing subscription"docs/context/decision-log.mdThe fact is about an architectural or tooling choice and why it was made.
docs/context/institutional-knowledge.mdThe fact is about team conventions, unwritten rules, organizational context, or who owns what.
docs/context/troubleshooting.mdThe fact is about diagnostic knowledge -- when X happens, do Y (or don't do Z).
If the fact fits multiple categories, pick the best fit based on the primary intent. You will mention the alternative in your confirmation message so the user can correct you.
docs/context/ does not exist, create the directory.docs/templates/ for the matching template. If no template exists, use this minimal structure:For production-map.md:
# Production Map
> What's real, what's staging, what's safe to touch.
## Services
| Service | Environment | URL/Endpoint | Impact if Corrupted |
|---------|-------------|-------------|-------------------|
For dangerous-assumptions.md:
# Dangerous Assumptions
> Things the AI agent might assume that are wrong in this project.
## Assumptions
| Agent Might Assume | But Actually | Impact If Wrong |
|-------------------|-------------|----------------|
For decision-log.md:
# Decision Log
> Why choices were made, not just what was chosen.
## Decisions
| Date | Decision | Why | Alternatives Rejected | Revisit When |
|------|----------|-----|----------------------|-------------|
For institutional-knowledge.md:
# Institutional Knowledge
> Unwritten rules, team conventions, and organizational context.
## Team Conventions
- (none yet)
For troubleshooting.md:
# Troubleshooting
> What to do when things go wrong for non-code reasons.
## Common Failures
| When This Happens | Do This | Don't Do This |
|-------------------|---------|---------------|
Read the target document to understand its current structure. Note:
Add the fact to the appropriate section of the target document. Match the existing format exactly:
- ) to the most appropriate section.Remove any italic example rows (rows where all cells start with _) before appending, so the document transitions from template to real content. Only remove examples from the specific table you are appending to.
Append only. Never modify or remove existing real content.
Decide whether the fact also warrants a rule in CLAUDE.md's behavioral boundaries:
Add a CLAUDE.md rule if the fact:
Do NOT add a CLAUDE.md rule if the fact is:
If a rule is warranted, read CLAUDE.md, find the appropriate section (ALWAYS, ASK FIRST, or NEVER under Behavioral Boundaries), and append the rule. If no Behavioral Boundaries section exists, append one.
Report what you did in this format:
Added to [document name]:
[summary of what was added]
[If CLAUDE.md was also updated:]
Added CLAUDE.md rule:
[ALWAYS/ASK FIRST/NEVER]: [rule text]
[If the fact was ambiguous:]
Routed to [chosen doc] -- move to [alternative doc] if this is more about [alternative category description].
development
Spawn an independent verifier subagent to check an implementation against its spec -- read-only, no code edits, structured pass/fail verdict
development
Assess and upgrade your project's AI development harness — score 7 dimensions, apply fixes, show path to Level 5
testing
Wrap up a session — capture discoveries, verify, prepare for PR or next session
development
Produce objective codebase research by isolating question generation from fact-gathering — subagent sees only questions, never the brief