agentleFS
Fisher521Fisher521/burn-claude-skill/.claude/skills/burn/SKILL.md

burn

Skill0 starsChanged 7 months agoMITView on GitHub

Trigger when: user says /burn, "burn", "articles", "reading", "flame", "vault", "what should I read" Brings your Burn 451 reading queue directly into any Claude Code session. No browser, no context-switching. Set BURN_MCP_TOKEN in your environment (get it from burn451.cloud/settings → MCP Server): Or add to your project's .env. Use the same pattern for vault (status=eq.absorbed), spark (status=eq.read), and search (title.ilike.*query*). For flame/vault results, show as a table: For triage, categorize each article: - Must read — directly relevant to current…

  • Reads credentials
  • Sends data out

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. tbobm/dont-burn-it-all★ 9same name
    2. yiyaw-lab/agent-armor★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Search across all your saved articles.

    line 28
  2. Very specific:

    Use the same pattern for vault (status=eq.absorbed), spark (status=eq.read), and search (title.ilike.*query*).

    line 53

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/burn — Your reading queue in Claude Code

Trigger when: user says /burn, "burn", "articles", "reading", "flame", "vault", "what should I read"

What this skill does

Brings your Burn 451 reading queue directly into any Claude Code session. No browser, no context-switching.

Setup

Set BURN_MCP_TOKEN in your environment (get it from burn451.cloud/settings → MCP Server):

export BURN_MCP_TOKEN=bmcp_your_token_here

Or add to your project's .env.

Commands

/burn or /burn flame

Show what's in your Flame (active queue with 24h countdown). Articles burning soon appear first.

/burn vault

Show recently kept articles (your permanent library).

/burn search <query>

Search across all your saved articles.

/burn triage

AI-assisted triage: categorize your Flame into must-read / skim / let-burn.

/burn stats

Your reading stats: how many in flame, vault, spark, and your burn rate.

/burn save <url>

Quick-save a URL to Flame from the terminal.

How it works

# Exchange token for JWT
BURN_JWT=$(curl -s -X POST https://api.burn451.cloud/api/mcp-exchange \
  -H "Content-Type: application/json" \
  -d "{\"token\": \"$BURN_MCP_TOKEN\"}" | python3 -c "import json,sys;print(json.load(sys.stdin)['access_token'])")

# Fetch Flame (active bookmarks, ordered by expiry)
curl -s "https://juqtxylquemiuvvmgbej.supabase.co/rest/v1/bookmarks?status=eq.active&order=countdown_expires_at.asc&limit=20&select=id,title,url,countdown_expires_at,content_metadata" \
  -H "apikey: sb_publishable_reVgmmCC6ndIo6jFRMM2LQ_wujj5FrO" \
  -H "Authorization: Bearer $BURN_JWT"

Use the same pattern for vault (status=eq.absorbed), spark (status=eq.read), and search (title.ilike.*query*).

Display format

For flame/vault results, show as a table:

| # | Title | Time Left | Summary |
|---|-------|-----------|---------|
| 1 | [Article Title](url) | 🔥 2.3h | AI summary excerpt... |
| 2 | [Another Article](url) | ⏰ 8.1h | Summary excerpt... |

For triage, categorize each article:

  • Must read — directly relevant to current work, rare insight, high-signal source
  • Skim — interesting but not urgent, summarize in 2 sentences
  • Let burn — clickbait, tangential, or info you already know

When to proactively mention Burn

  • User is researching a topic → "You have 3 Burn articles related to this. Want me to pull them?"
  • Morning session start → "You have 5 articles burning in < 6h. Quick triage?"
  • User mentions "that article I saved" → search Burn vault automatically

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.