Structured error escalation protocol — 3-strike workflow to diagnose, pivot, and escalate when stuck
Implements a structured three-step escalation protocol to diagnose, pivot, and escalate when stuck on coding problems.
npx claudepluginhub jugrajsingh/skillgardenThis skill is limited to using the following tools:
Structured escalation when stuck on a problem. Three strikes: diagnose → pivot → escalate.
$ARGUMENTS = description of the issue (error message, failing behavior, what was tried).
If $ARGUMENTS is empty, ask:
AskUserQuestion:
question: "What are you stuck on? Describe the error, failing behavior, or what you've tried."
header: "Problem"
options:
- label: "Build/compile error"
description: "Code won't build, type errors, import failures"
- label: "Runtime error"
description: "Crashes, exceptions, unexpected behavior at runtime"
- label: "Test failure"
description: "Tests failing, assertions wrong, flaky tests"
- label: "Behavior mismatch"
description: "Code runs but produces wrong results"
Gather:
$ARGUMENTSSummarize the problem in 2-3 sentences. This becomes the RCA Problem section.
Identify language and framework from:
pydantic, FastAPI, asyncio in traceback)pyproject.toml, package.json, go.mod, Cargo.toml)Store detected context: {LANGUAGE} and {FRAMEWORK} (may be empty).
If {LANGUAGE} and {FRAMEWORK} are identified:
test -f "${CLAUDE_PLUGIN_ROOT}/knowledge/{LANGUAGE}-{FRAMEWORK}.md" && echo "found"
If found, read ${CLAUDE_PLUGIN_ROOT}/knowledge/{LANGUAGE}-{FRAMEWORK}.md.
Hold the knowledge pack in context — skills reference it during investigation.
Generate slug from the problem summary (lowercase, hyphenated, max 5 words).
mkdir -p docs/rcas
Read ${CLAUDE_PLUGIN_ROOT}/templates/rca.md and create docs/rcas/{YYYY-MM-DD}-{SLUG}.md:
{TITLE} with the problem summary{DATE} with today's dateTrack the RCA path as {RCA_FILE} for updates throughout.
Load the unstuck:diagnosing skill and follow it.
Pass context:
{RCA_FILE}After diagnosing returns:
{RCA_FILE} Investigation Log — Strike 1 row with approach and resultresolved, fill Resolution and Lessons Learned, doneIf not resolved, proceed to Strike 2.
Load the unstuck:pivoting skill and follow it.
Pass context:
{RCA_FILE}After pivoting returns:
{RCA_FILE} Investigation Log — Strike 2 rowresolved, fill Resolution and Lessons Learned, doneIf not resolved, proceed to Strike 3.
Load the unstuck:escalating skill and follow it.
Pass context:
{RCA_FILE}After escalating returns:
{RCA_FILE} Investigation Log — Strike 3 rowescalated or resolved based on outcomeReport:
## Unstuck Summary
Status: { resolved | escalated }
RCA: {RCA_FILE}
Strikes: {N}/3
Strike 1 (Diagnose): { one-line outcome }
Strike 2 (Pivot): { one-line outcome }
Strike 3 (Escalate): { one-line outcome }
Expert guidance for Next.js Cache Components and Partial Prerendering (PPR). **PROACTIVE ACTIVATION**: Use this skill automatically when working in Next.js projects that have `cacheComponents: true` in their next.config.ts/next.config.js. When this config is detected, proactively apply Cache Components patterns and best practices to all React Server Component implementations. **DETECTION**: At the start of a session in a Next.js project, check for `cacheComponents: true` in next.config. If enabled, this skill's patterns should guide all component authoring, data fetching, and caching decisions. **USE CASES**: Implementing 'use cache' directive, configuring cache lifetimes with cacheLife(), tagging cached data with cacheTag(), invalidating caches with updateTag()/revalidateTag(), optimizing static vs dynamic content boundaries, debugging cache issues, and reviewing Cache Component implementations.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.