Agent skill

Pilot Failure Triage

by qf-studio in qf-studio/pilot

Checks a failing Pilot executor against four known failure patterns from the v2.149.x fixes before the agent explores anything else.

Custom licenceAuto-check: notesDevelopment

Install Pilot Failure Triage

skills CLI
$ npx skills add qf-studio/pilot --skill pilot-debug -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install qf-studio/pilot pilot-debug --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/qf-studio/pilot.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/pilot-debug .claude/skills/pilot-debug && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
pilot-debug
GitHub stars
722
Token cost
~548 tokens
SKILL.md length
206 words
Files
1
Skills in repo
2
Repo updated
First seen
Licence
Custom licence

At a glance

Checks a failing Pilot executor against four known failure patterns from the v2.149.x fixes before the agent explores anything else.

  • Works in 4 steps: Silent autopilot gate (v2.149.1, commit… → Worktree path equality (v2.149.2, commit… → Vacuous-truth empty children (v2.149.3,… → …
  • A Pilot executor run has failed or hung
  • SKILL.md covers Triage order, Output, Anti-patterns and Related memories
  • Calls git

What it does

When someone reports that pilot failed, an executor or epic is stuck, or autopilot did not fire, the agent states a hypothesis first, in a fixed order, before running any investigation tool. The four patterns each have a diagnostic and a code location: a silent autopilot gate, worktree path equality, vacuous truth for epics with no children, and a missing IsEpic guard that marks epic parents with empty commit or PR fields as failed.

The agent ends with either a match, naming the pattern and following its diagnostic, or a novel result with a one-line reason none fit, in which case it writes a failing regression test first and then escalates. The skill warns against wandering into session directories, daemon config, queue state or the database until all four patterns are ruled out, and it lists memory files that describe each pitfall.

When your agent uses it

  • A Pilot executor run has failed or hung
  • An epic is stuck and its children look finished
  • Autopilot did not start after startup

Example prompts

  • “The pilot executor is stuck on this epic. Triage it against the known patterns.”
  • “Autopilot didn't fire after the last restart; check the startup logs first.”
  • “Pilot failed on a task whose worktree is under /tmp. Check whether it matches a known pattern.”

Requirements

  • The Pilot codebase and its startup logs
  • Pre-approved tools (allowed-tools): Read, Grep, Bash

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Silent autopilot gate (v2.149.1, commit f032689b)
  2. Worktree path equality (v2.149.2, commit aac6de5f, TASK-286)
  3. Vacuous-truth empty children (v2.149.3, commit fd0f7b69)
  4. Missing IsEpic guard (v2.149.3, commit fd0f7b69)

What it can do on your machine

Read from SKILL.md and the folder at commit 6f9b629. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Grep
    • Bash

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Pilot Failure Triage loads about 548 tokens when it runs. Until then it costs about 59 tokens; SKILL.md has 206 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~59
When it runs · the whole SKILL.md, loaded when a task matches
~548

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Read, Grep, Bash

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 206 words (~548 tokens).

“When invoked, state the hypothesis FIRST in this exact order before running any investigation tool. Each pattern was patched in v2.149.1–.3 and has high prior probability of recurring.”

— opening of SKILL.md by qf-studio, Custom licence
name
pilot-debug
allowed-tools
Read, Grep, Bash

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .claude/skills/pilot-debug of qf-studio/pilot.

Open the folder on GitHubat commit 6f9b629

Compare with similar skills

Pilot Failure Triage next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Pilot Failure Triage compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Pilot Failure Triage this skillqf-studio/pilot722—~548Automated safety check: NotesCustom licence
OpenLogi macOS Permissions TriageAprilNEA/OpenLogi23k—~2.5kAutomated safety check: NotesApache-2.0
Bug Finder for daisyUIsaadeghi/daisyui43k—~2.3kAutomated safety check: PassMIT
Root Cause Debugginggarrytan/gstack136k—~1.4kAutomated safety check: PassMIT
Graph-Based Bug Tracingtirth8205/code-review-graph32k1 repos~287Automated safety check: PassMIT
Systematic DebuggingChrisWiles/claude-code-showcase6.1k3 repos~1.2kAutomated safety check: PassNone

Similar skills

  • Decides whether an OpenLogi device problem on macOS is a privacy-permission (TCC) problem, using agent log lines, and says which identity needs which grant.

    23k GitHub stars~2.5k tokensUpdated 3 days ago
    DevelopmentAuto-check: notes
  • Bug Finder for daisyUI

    saadeghi/daisyui

    Investigates suspected bugs in the daisyUI monorepo through read-only analysis, then writes a decision-ready fix plan in tmp/bugs without changing any product code.

    43k GitHub stars~2.3k tokensUpdated 7 days ago
    DevelopmentAuto-check passed
  • Root Cause Debugging

    garrytan/gstack

    Investigates bugs, errors and stack traces in phases and requires a root-cause hypothesis to be confirmed before any fix is written.

    136k GitHub stars~1.4k tokensUpdated today
    DevelopmentAuto-check passed
  • Graph-Based Bug Tracing

    tirth8205/code-review-graph

    Traces a bug through a code knowledge graph, following callers, callees and execution flow before opening source files, within a small token budget.

    32k GitHub starsUsed in 1 repo~287 tokens
    DevelopmentAuto-check passed
  • Systematic Debugging

    ChrisWiles/claude-code-showcase

    Applies a four-phase debugging routine that finds the root cause of a bug or failing test before any fix is written.

    6.1k GitHub starsUsed in 3 repos~1.2k tokens
    DevelopmentAuto-check passed
  • Debugging and Error Recovery

    addyosmani/agent-skills

    Applies a stop-the-line rule and a step-by-step triage when tests fail, builds break or something stops working, aiming at the root cause instead of guesses.

    102k GitHub starsUsed in 1 repo~2.6k tokens
    DevelopmentAuto-check passed

More from qf-studio/pilot

  • Checks status, tails logs, queries the task queue, and starts, stops or restarts the Pilot daemon running on a specific AWS EC2 instance over SSM.

    722 GitHub stars~3k tokensUpdated yesterday
    Auto-check: notes

Categories

Questions about Pilot Failure Triage

What does Pilot Failure Triage do?

Checks a failing Pilot executor against four known failure patterns from the v2.149.x fixes before the agent explores anything else. When someone reports that pilot failed, an executor or epic is stuck, or autopilot did not fire, the agent states a hypothesis first, in a fixed order, before running any investigation tool. The four patterns each have a diagnostic and a code location: a silent autopilot gate, worktree path equality, vacuous truth for epics with no children, and a missing IsEpic guard that marks epic parents with empty commit or PR fields as failed.

When should I use Pilot Failure Triage?

Pilot Failure Triage fits situations like: A Pilot executor run has failed or hung; an epic is stuck and its children look finished; autopilot did not start after startup.

How do I install Pilot Failure Triage in Claude Code?

Run `npx skills add qf-studio/pilot --skill pilot-debug -a claude-code`. Or copy the skill folder (.claude/skills/pilot-debug in qf-studio/pilot) into .claude/skills/pilot-debug in your project. Claude Code loads it when a task matches its description.

How do I install Pilot Failure Triage in Codex?

Run `npx skills add qf-studio/pilot --skill pilot-debug -a codex`. Or copy the skill folder (.claude/skills/pilot-debug in qf-studio/pilot) into .agents/skills/pilot-debug in your project. Codex loads it when a task matches its description.

Can I use Pilot Failure Triage in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add qf-studio/pilot --skill pilot-debug -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pilot-debug, .gemini/skills/pilot-debug, .github/skills/pilot-debug and .opencode/skills/pilot-debug in your project.

What does Pilot Failure Triage need to run?

Going by SKILL.md and its folder, Pilot Failure Triage needs the command-line tools its instructions call (git). Our summary lists: The Pilot codebase and its startup logs. Its frontmatter pre-approves these tools: Read, Grep, Bash.

Does Pilot Failure Triage access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Pilot Failure Triage safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Pilot Failure Triage use?

Pilot Failure Triage has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Pilot Failure Triage use?

About 548 tokens (SKILL.md is roughly 2.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Pilot Failure Triage?

Skills that share tags, products or a category with Pilot Failure Triage: OpenLogi macOS Permissions Triage (AprilNEA/OpenLogi, 23k stars), Bug Finder for daisyUI (saadeghi/daisyui, 43k stars), Root Cause Debugging (garrytan/gstack, 136k stars) and Graph-Based Bug Tracing (tirth8205/code-review-graph, 32k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Pilot Failure Triage?

qf-studio (a GitHub organization) maintains it in qf-studio/pilot, which has 722 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 6, 2026.

Source: qf-studio/pilot on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.