agentleFS
jamie8johnsonjamie8johnson/cqs/.claude/skills/troubleshoot/SKILL.md

troubleshoot

Skill18 starsChanged 5 months agoMITView on GitHub

Diagnose common cqs issues — stale index, model download, schema mismatch, connection issues.

  • Reads credentials
  • Installs packages

29 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use ecosystem-reference, fractal-delegation and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • naman10parikhSkill

    ecosystem-reference

    Quick-access directory of Claude Code ecosystem repos, skills, plugins, MCPs, and patterns. Use when improving the harness.

    Also in 5 projects that use this

  • naman10parikhSkill

    fractal-delegation

    Also in 5 projects that use this

  • roronoazoroshao369Skill

    memory-compression

    Also in 5 projects that use this

  • MicrosoftSkill

    act-on-feedback

    Act on user feedback attached to the current session. Use when the user submits feedback on the session's changes via the Submit Feedback button.

    Also in 4 projects that use this

  • MicrosoftSkill

    generate-run-commands

    Generate or modify run commands for the current session. Use when the user wants to set up or update run commands that appear in the session's Run button.

    Also in 4 projects that use this

  • KirchliveSkill

    skill-routing

    Decides which of the installed skills a task needs and loads them before the work starts. This skill should be used at the beginning of any multi-step task — build, fix, refactor, migrate, review, plan, release, research, write, design, video — and again at every phase change, after context compaction, and when work moves into a different part of the codebase. Use it for requests like "let's build X", "fix this bug", "refactor Y", "plan the migration", "review this", and also when the user asks which skill applies, why a skill did not fire, or asks to check what is available.

    Also in 5 projects that use this

  • +5 more from naman10parikh

The file

We split this skill into the rules it gives an agent

10 rules. 0 are common, 4 are distinctive, and 6 are very specific to this project.

  • 0

    Common

    Most of the 23 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 6

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If not found: cargo install --path .

    line 20
  2. Very specific:

    If empty: cqs index to rebuild.

    line 38
  3. Distinctive:

    If you see "SchemaMismatch" or "SchemaNewerThanCq":

    line 46
  4. Very specific:

    Older schema: Run /migrate to upgrade

    line 47
  5. Distinctive:

    Newer schema: Update cqs binary to latest version

    line 48
  6. Very specific:

    Default model is EmbeddingGemma-300m (since v1.35.0).

    line 59
  7. Distinctive:

    If corrupted: delete the directory and let cqs re-download (blake3 checksums verify integrity).

    line 60
  8. Very specific:

    Check that source paths still exist and chunk counts are > 0.

    line 86
  9. Very specific:

    If source moved: cqs ref remove <name> and re-add with new path.

    line 87
  10. Distinctive:

    After running checks, summarize:

    line 91

“Common” is measured: kept by at least 6 in 10 of the 23 edited versions of this file we could read. “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

Troubleshoot

Guided diagnosis of common cqs issues. Run through checks in order, stop at first problem found.

Checklist

1. Is cqs installed and working?

cqs --version

If not found: cargo install --path . (from source) or check ~/.cargo/bin/ is in PATH.

2. Is the project initialized?

ls -la .cqs/ && cat .cqs/active_slot 2>/dev/null
ls -la .cqs/slots/$(cat .cqs/active_slot 2>/dev/null || echo default)/ 2>/dev/null

The index lives in the active slot: .cqs/slots/<name>/index.db plus HNSW sidecars (index.hnsw*; legacy pre-slot layouts kept files at .cqs/ top level). If missing: cqs init && cqs index.

3. Is the index populated?

Run cqs stats. Check:

  • Chunk count > 0
  • Last update is recent
  • Expected languages are present

If empty: cqs index to rebuild.

4. Schema version mismatch?

cqs stats 2>&1

If you see "SchemaMismatch" or "SchemaNewerThanCq":

  • Older schema: Run /migrate to upgrade
  • Newer schema: Update cqs binary to latest version

Current schema version: check src/store/helpers/mod.rs for CURRENT_SCHEMA_VERSION.

5. Model downloaded?

cqs doctor   # checks model, index, hardware in one pass
ls -la ~/.cache/huggingface/hub/models--onnx-community--embeddinggemma-300m-ONNX/

Default model is EmbeddingGemma-300m (since v1.35.0); alternative presets via CQS_EMBEDDING_MODEL / --model live under their own models--* dirs. If missing or incomplete, cqs downloads on first use. Check network access to huggingface.co. If corrupted: delete the directory and let cqs re-download (blake3 checksums verify integrity).

6. Daemon mode working?

cqs ping
systemctl --user status cqs-watch

cqs ping should report a connected daemon and a sub-100ms round-trip. Common issues:

  • Daemon not running: systemctl --user start cqs-watch (or cqs watch --serve ad hoc)
  • Stale socket from a crash: systemctl --user restart cqs-watch
  • Want to bypass the daemon for one command: CQS_NO_DAEMON=1 cqs <cmd>
  • LLM enrichment failing: check ANTHROPIC_API_KEY is set (see SECURITY.md)

7. Index stale?

Compare cqs stats last update time vs recent file modifications. Fix: cqs index (one-time) or cqs watch (continuous).

8. References broken?

cqs ref list

Check that source paths still exist and chunk counts are > 0. If source moved: cqs ref remove <name> and re-add with new path.

Report

After running checks, summarize:

  • What was checked
  • What failed (if anything)
  • What was fixed or needs fixing

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.