agentleFS
Sign inStart free
tanishq286tanishq286/tq-forge/skills/tq-forge-list/SKILL.md

tq-forge-list

Skill8 starsChanged 5 months agoMITView on GitHub

List every forged skill and agent (sandbox + promoted) with quality scores color-coded green/yellow/red. Reads $TQ_FORGE_HOME/sandbox and skill-log.json. Use when asked for "/tq-forge-list", "show forged skills", "what's in the sandbox", or "which skills have I forged".

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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. Very specific:

    Don't list pre-existing skills from $CLAUDE_SKILLS_DIR that tq-forge didn't create — only show items present in skill-log.json or the …

    line 74

≈ “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

/tq-forge-list — inventory of forged items

When to use

You want a quick overview of everything /tq-forge has built — what's still in the sandbox awaiting promote, what's already live, and which scored low enough to need a refresh.

Procedure

export TQ_FORGE_HOME="${TQ_FORGE_HOME:-$HOME/.tq-forge}"
S="${CLAUDE_PLUGIN_ROOT:-${TQ_FORGE_HOME:-$HOME/.tq-forge}/install}/scripts"
source "$S/common.sh" && tq_ensure_home
  1. Read the skill log.
    cat "$TQ_FORGE_HOME/skill-log.json"
    Each entry has {slug, kind, score, at, intent, status}. status is one of sandbox, promoted, needs_manual_review.
  2. Walk the sandbox.
    ls -1 "$SANDBOX_SKILLS" 2>/dev/null
ls -1 "$SANDBOX_AGENTS" 2>/dev/null
    A directory in the sandbox but not in skill-log.json is an orphan — include it with score ? and a flag.
  3. Walk promoted items.
    ls -1 "$CLAUDE_SKILLS_DIR/agents" 2>/dev/null
    Plus any slug from skill-log.json with status: promoted.
  4. Render two tables — Skills first, Agents second:
    📚 SKILLS (sandbox: <N>, promoted: <M>)
Slug                    Score   Status     Forged
notion-daily-summary    🟢 8.5  promoted   2d ago
inventory-snapshot      🟡 6.8  sandbox    1h ago

🤖 AGENTS (sandbox: <N>, promoted: <M>)
Slug                Kind        Score   Status
market-research     researcher  🟢 8.9  promoted
  5. Color code by score: 🟢 >= 8.0, 🟡 6.0-7.9, 🔴 < 6.0.
  6. Footer line with quick commands:
    Promote: /tq-forge-promote <slug>   Improve: /tq-forge-improve <slug>   Test: /tq-forge-test <slug>

Pitfalls

  • Entries with score: null are pending a score. Show them but flag with ?.
  • The orphan check (sandbox dir with no log entry) catches manually-created scaffolds. Treat as ?, suggest /tq-forge-test to score them.
  • Don't list pre-existing skills from $CLAUDE_SKILLS_DIR that tq-forge didn't create — only show items present in skill-log.json or the sandbox.

Verification

  • The two header counts (sandbox + promoted) equal ls | wc -l of the corresponding directories.

Tags

tq-forge inventory read-only

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.

Check your setup, free