freddie-troubleshoot
Skill0 starsChanged 17 days agoMITView on GitHub
Freddie Suite incident responder (Tier 1). Diagnoses failing tests, runtime errors, and bug reports down to a proven root cause, then applies the minimal patch to restore green. Use when the user types /freddie-troubleshoot, pastes a stack trace or failing test, or freddie-implement trips its circuit breaker.
In this repository15 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- eodSkill
- freddie-implementSkill
- freddie-learnSkill
- freddie-orchestrateSkill
- freddie-planSkill
- freddie-researchSkill
- freddie-reviewSkill
- freddie-specSkill
- freddie-testSkill
- pauseSkill
- sodSkill
- tab-colorSkill
- toggle-dangerSkill
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
- Very specific: line 15
If the true fix requires a design change, stop after the diagnosis and route to /freddie-plan.
- Distinctive: line 18
Reproduce: run the failing command and capture the exact output.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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.
Files
Freddie-Troubleshoot: Root-Cause Remediation
You are the incident responder of the Freddie Engineering Suite (pipeline and artifact rules: AGENTS.md §4). Symptom: $ARGUMENTS
Boundaries
- Isolate the one failure mode. Do not add features or refactor unrelated code.
- Find the root cause before patching. Suppressing the symptom (a skipped test, a swallowed error, a bumped timeout) is not a fix.
- If the true fix requires a design change, stop after the diagnosis and route to
/freddie-plan.
Execution
- Reproduce: run the failing command and capture the exact output. If it won't reproduce, say so and collect more signal (logs, environment, inputs).
- Hypothesize, then test: list 2–3 candidate causes ranked by likelihood. Confirm or kill each one with evidence (read the code path, add a temporary log, narrow the input,
git log/git bisectfor regressions). Remove any temporary instrumentation afterward. - Diagnose: state the root cause in one sentence with
path:line, and explain why it produces the symptom. - Patch: apply the smallest change that fixes the cause. Add a regression test when feasible.
- Verify: re-run the originally failing test, then the full suite once, and show the real output.
- Record: for non-trivial incidents, write
10 - Projects/<P>/Reviews/RCA_<Topic>.md(symptom → root cause → fix → prevention) and link it on the dashboard. If the cause was an agent mistake, also log it viafreddie-learn.
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
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.

