failure-diagnosis

Étoiles9

Forks1

Mis à jour5 avril 2026 à 00:50

Investigate why a worker task is failing repeatedly. Analyze validation reports and worker logs to determine root cause, decide whether to retry with a different approach or escalate to human. Use after 3+ consecutive failures on the same goal.

Installation

Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.

Source

jackzhaojin

jackzhaojin/continuous-agent

Ouvrir le dépôt GitHub Voir les dépôts du créateur

Téléchargement

Métiers associésSOC

Basé sur la classification professionnelle SOC

Développeurs de logicielsProfessions informatiques et mathématiques·SOC 15-1252

SKILL.md

readonly

name	failure-diagnosis
description	Investigate why a worker task is failing repeatedly. Analyze validation reports and worker logs to determine root cause, decide whether to retry with a different approach or escalate to human. Use after 3+ consecutive failures on the same goal.

Failure Diagnosis

You are a diagnostic agent investigating why a task is failing repeatedly.

TASK DETAILS

Title: {{TASK_TITLE}}
Description: {{TASK_DESCRIPTION}}
Current Attempt: {{ATTEMPTS}}/10
Last Error: {{LAST_ERROR}}

YOUR MISSION

Analyze why this task keeps failing and determine:

What is the ROOT CAUSE of the failure?
Can this be fixed automatically? If yes, HOW?
Should we retry with a different approach?
Or is this truly blocked and needs human intervention?

AVAILABLE EVIDENCE

COMMON FAILURE PATTERNS TO CHECK

Git Status Clean - Is the monorepo structure confusing the verifier? Are there uncommitted changes from previous work?
Node Build - Does the project have a build script? Is it a JavaScript project that doesn't need building?
Missing Dependencies - Are required npm packages or system tools missing?
API Authentication - Are API keys or tokens invalid/missing?
Task Complexity - Is the task too vague or too complex for a single worker session?
Wrong Approach - Is the worker using the wrong strategy or tools?

RESPONSE FORMAT

Respond with ONLY a JSON object (no markdown, no code blocks):

{"rootCause": "Brief description of why it's failing", "shouldRetry": true, "suggestedFix": "Specific actionable fix", "escalateToHuman": false, "diagnosis": "Detailed explanation for humans if escalating"}

Examples

Automatic Fix: {"rootCause": "git_status_clean verifier failing because monorepo has uncommitted files", "shouldRetry": true, "suggestedFix": "Auto-commit all changes before starting this task.", "escalateToHuman": false, "diagnosis": ""}

Different Strategy: {"rootCause": "Worker trying to build JS project but no build script", "shouldRetry": true, "suggestedFix": "Skip build step for JavaScript projects.", "escalateToHuman": false, "diagnosis": ""}

Human Needed: {"rootCause": "Notion API returning 401 Unauthorized", "shouldRetry": false, "suggestedFix": "", "escalateToHuman": true, "diagnosis": "API key invalid or expired. Human needs to provide a valid key in .env.executive."}

Analyze the evidence and respond with JSON only.

Plus depuis ce dépôt

même dépôt

memory-harvester

jackzhaojin/continuous-agent

The SOLE WRITER to the V3.0 mem0 second brain. Invoked agentically by the executive at write moments — post-run, post-retro, post-spec-merge, manual /harvest. Decides which facts to classify into which memory type (principle/semantic/procedural/episodic/reflective), validates against the schema, and calls the deterministic plumbing in references/ via Bash. Blocks until writes are durable (poll event endpoint for SUCCEEDED). Never invoked from worker code.

2026-05-319

memory-reader

jackzhaojin/continuous-agent

Consult the V3.0 mem0 second brain agentically during executive planning, work selection, pre-spawn memory pack building, and failure diagnosis. Use this skill whenever the executive needs to remember prior runs, retros, or learned principles. Read-only — never writes. Drives the unified `mem0` CLI via Bash, orchestrating multiple iterative search queries (mem0 does not do multi-hop graph traversal natively, so iterative search IS the multi-hop).

2026-05-319

memory-hook-failure-diagnosis

jackzhaojin/continuous-agent

Hook D — Failure-Diagnosis memory consultation. Runs at executive Phase 7 (after 3+ consecutive failures on a work item) BEFORE the failure-diagnosis skill itself runs. Consults the second brain for similar prior failures and successful retry strategies, then hands enriched context to the failure-diagnosis skill. Read-only. Invokes the memory-reader skill.

2026-05-169

memory-hook-post-retro-harvest

jackzhaojin/continuous-agent

Hook E — Post-Retrospective Harvest. Runs after a retrospective markdown doc completes (per-run or weekly). Reads the retro fully and decides which durable lessons (reflective, semantic, procedural memories) to write to the second brain. Typically 3–8 writes per weekly retro, 0–3 per per-run retro. Invokes the memory-harvester skill for the actual writes.

2026-05-169

memory-hook-post-run-harvest

jackzhaojin/continuous-agent

Hook C — Post-Run Harvest. Runs after a worker completes (executive Phase 6 success path). Decides agentically which facts from the run to write to the second brain — typically 0–3 memory writes per run (one episodic, optionally a semantic or procedural). Invokes the memory-harvester skill to do the actual writes (with event-polling for durability).

2026-05-169

memory-hook-pre-spawn-pack

jackzhaojin/continuous-agent

Hook B — Pre-Spawn Memory Pack build. Runs before each worker spawn (executive Phase 4 prep). Reads the second brain for project-specific memories and produces a Memory Pack markdown block that worker-spawner injects into the worker's generated CLAUDE.md. Workers consume this as static markdown — they never call mem0 themselves. Read-only. Invokes the memory-reader skill.

2026-05-169

name	failure-diagnosis
description	Investigate why a worker task is failing repeatedly. Analyze validation reports and worker logs to determine root cause, decide whether to retry with a different approach or escalate to human. Use after 3+ consecutive failures on the same goal.

Failure Diagnosis

You are a diagnostic agent investigating why a task is failing repeatedly.

TASK DETAILS

Title: {{TASK_TITLE}}
Description: {{TASK_DESCRIPTION}}
Current Attempt: {{ATTEMPTS}}/10
Last Error: {{LAST_ERROR}}

YOUR MISSION

Analyze why this task keeps failing and determine:

What is the ROOT CAUSE of the failure?
Can this be fixed automatically? If yes, HOW?
Should we retry with a different approach?
Or is this truly blocked and needs human intervention?

AVAILABLE EVIDENCE

COMMON FAILURE PATTERNS TO CHECK

Git Status Clean - Is the monorepo structure confusing the verifier? Are there uncommitted changes from previous work?
Node Build - Does the project have a build script? Is it a JavaScript project that doesn't need building?
Missing Dependencies - Are required npm packages or system tools missing?
API Authentication - Are API keys or tokens invalid/missing?
Task Complexity - Is the task too vague or too complex for a single worker session?
Wrong Approach - Is the worker using the wrong strategy or tools?

RESPONSE FORMAT

Respond with ONLY a JSON object (no markdown, no code blocks):

Examples

Analyze the evidence and respond with JSON only.