diff --git a/.changeset/error-recovery-skill.md b/.changeset/error-recovery-skill.md
new file mode 100644
index 000000000..ec48a85a3
--- /dev/null
+++ b/.changeset/error-recovery-skill.md
@@ -0,0 +1,5 @@
+---
+"@bradygaster/squad-cli": minor
+"@bradygaster/squad-sdk": minor
+---
+feat: add error-recovery skill for standard agent failure recovery patterns
\ No newline at end of file
diff --git a/docs/proposals/error-recovery.md b/docs/proposals/error-recovery.md
new file mode 100644
index 000000000..9661c6ea5
--- /dev/null
+++ b/docs/proposals/error-recovery.md
@@ -0,0 +1,69 @@
+# Proposal: Error Recovery Skill
+
+**Issue:** bradygaster/squad#623
+**Author:** tamirdresher
+**Date:** 2026-03-26
+**Status:** Proposal
+
+---
+
+## Problem Statement
+
+When a Squad agent fails (model timeout, tool error, invalid output, context overflow), there is
+no standardized recovery pattern. Individual coordinators implement ad-hoc retry logic or simply
+fail the task. This causes inconsistent user experience and missed opportunities for graceful
+degradation across the squad.
+
+---
+
+## Proposed Approach
+
+A skill library providing five recovery patterns an agent can apply when it encounters a failure:
+
+| Pattern | When to use |
+|---------|-------------|
+| **retry** | Transient errors (rate limit, timeout) — wait and retry same approach |
+| **fallback** | Primary approach consistently fails — switch to alternative method |
+| **diagnose** | Unclear failure cause — gather diagnostics before deciding |
+| **escalate** | Blocked beyond agent capability — surface to coordinator/human |
+| **degrade** | Full functionality unavailable — deliver partial result with caveat |
+
+The skill provides a selection guide table mapping error symptoms to the appropriate pattern,
+plus prompt templates for each pattern that agents can use in their reasoning.
+
+---
+
+## Fit with Existing Architecture
+
+- **Complements** existing gent-conduct skill (which covers behavior) — this skill covers failure states
+- **No code changes** — template-only, agents apply this via their prompt reasoning
+- **Coordinator-agnostic** — works with any existing coordinator style
+- **Consistent with** the 3-cycle protocol from iterative-retrieval skill
+
+---
+
+## What Changes
+
+- New skill: packages/squad-cli/templates/skills/error-recovery/SKILL.md
+- New skill: packages/squad-sdk/templates/skills/error-recovery/SKILL.md
+- New changeset: .changeset/error-recovery-skill.md
+
+## What Stays the Same
+
+- No existing skills modified
+- No CLI or SDK runtime code changed
+
+---
+
+## Risks and Mitigations
+
+| Risk | Likelihood | Impact | Mitigation |
+|------|-----------|--------|------------|
+| Agents over-apply retry (masking root causes) | Low | Medium | Skill explicitly limits retry to 3 attempts max |
+| Conflicts with future built-in error handling | Low | Low | Template-only — superseded naturally if runtime handles it |
+
+---
+
+## References
+
+- Issue: bradygaster/squad#623
diff --git a/packages/squad-cli/templates/skills/error-recovery/SKILL.md b/packages/squad-cli/templates/skills/error-recovery/SKILL.md
new file mode 100644
index 000000000..ebf38825c
--- /dev/null
+++ b/packages/squad-cli/templates/skills/error-recovery/SKILL.md
@@ -0,0 +1,99 @@
+---
+name: "error-recovery"
+description: "Standard recovery patterns for all squad agents. When something fails, adapt — don't just report the failure."
+domain: "reliability, agent-coordination"
+confidence: "high"
+license: MIT
+---
+
+# Error Recovery Patterns
+
+Standard recovery patterns for all squad agents. When something fails, **adapt** — don't just report the failure.
+
+---
+
+## 1. Retry with Backoff
+
+**When:** Transient failures — API timeouts, rate limits, network errors, temporary service unavailability.
+
+**Pattern:**
+1. Wait briefly, then retry (start at 2s, double each attempt)
+2. Maximum 3 retries before escalating
+3. Log each attempt with the error received
+
+**Example:** API call returns 429 Too Many Requests → wait 2s → retry → wait 4s → retry → wait 8s → retry → escalate if still failing.
+
+---
+
+## 2. Fallback Alternatives
+
+**When:** Primary tool or approach fails and an alternative exists.
+
+**Pattern:**
+1. Attempt primary approach
+2. On failure, identify alternative tool/method
+3. Try the alternative with the same intent
+4. Document which alternative was used and why
+
+**Example:** Primary CLI tool fails → fall back to direct API call for the same operation.
+
+---
+
+## 3. Diagnose-and-Fix
+
+**When:** Build failures, test failures, linting errors — structured errors with actionable output.
+
+**Pattern:**
+1. Read the full error output carefully
+2. Identify the root cause from error messages
+3. Attempt a targeted fix
+4. Re-run to verify the fix
+5. Maximum 3 fix-retry cycles before escalating
+
+**Example:** Build fails with a type error → check for missing import → add it → rebuild.
+
+---
+
+## 4. Escalate with Context
+
+**When:** Recovery attempts have been exhausted, or the failure requires human judgment.
+
+**Pattern:**
+1. Summarize what was attempted and what failed
+2. Include the exact error messages
+3. State what you believe the root cause is
+4. Suggest next steps or who might be able to help
+5. Hand off to the coordinator or the appropriate specialist
+
+**Example:** After 3 failed build attempts → "Build fails on line 42 with null reference. Tried X, Y, Z. Likely a design issue in the Foo module. Recommend the code owner review."
+
+---
+
+## 5. Graceful Degradation
+
+**When:** A non-critical step fails but the overall task can still deliver value.
+
+**Pattern:**
+1. Determine if the failed step is critical to the task outcome
+2. If non-critical, log the failure and continue
+3. Deliver partial results with a clear note of what was skipped
+4. Offer to retry the skipped step separately
+
+**Example:** Generating a report with 5 sections — section 3 data source is unavailable → produce the report with 4 sections, note that section 3 was skipped and why.
+
+---
+
+## Applying These Patterns
+
+Each agent should reference these patterns in their charter's `## Error Recovery` section, tailored to their domain. The charter should list the agent's most common failure modes and map each to the appropriate pattern above.
+
+**Selection guide:**
+
+| Failure Type | Primary Pattern | Fallback Pattern |
+|---|---|---|
+| Network/API transient | Retry with Backoff | Escalate with Context |
+| Tool/dependency missing | Fallback Alternatives | Escalate with Context |
+| Build/test error | Diagnose-and-Fix | Escalate with Context |
+| Auth/permissions | Retry with Backoff | Escalate with Context |
+| Non-critical data missing | Graceful Degradation | — |
+| Unknown/novel error | Escalate with Context | — |
diff --git a/packages/squad-sdk/templates/skills/error-recovery/SKILL.md b/packages/squad-sdk/templates/skills/error-recovery/SKILL.md
new file mode 100644
index 000000000..ebf38825c
--- /dev/null
+++ b/packages/squad-sdk/templates/skills/error-recovery/SKILL.md
@@ -0,0 +1,99 @@
+---
+name: "error-recovery"
+description: "Standard recovery patterns for all squad agents. When something fails, adapt — don't just report the failure."
+domain: "reliability, agent-coordination"
+confidence: "high"
+license: MIT
+---
+
+# Error Recovery Patterns
+
+Standard recovery patterns for all squad agents. When something fails, **adapt** — don't just report the failure.
+
+---
+
+## 1. Retry with Backoff
+
+**When:** Transient failures — API timeouts, rate limits, network errors, temporary service unavailability.
+
+**Pattern:**
+1. Wait briefly, then retry (start at 2s, double each attempt)
+2. Maximum 3 retries before escalating
+3. Log each attempt with the error received
+
+**Example:** API call returns 429 Too Many Requests → wait 2s → retry → wait 4s → retry → wait 8s → retry → escalate if still failing.
+
+---
+
+## 2. Fallback Alternatives
+
+**When:** Primary tool or approach fails and an alternative exists.
+
+**Pattern:**
+1. Attempt primary approach
+2. On failure, identify alternative tool/method
+3. Try the alternative with the same intent
+4. Document which alternative was used and why
+
+**Example:** Primary CLI tool fails → fall back to direct API call for the same operation.
+
+---
+
+## 3. Diagnose-and-Fix
+
+**When:** Build failures, test failures, linting errors — structured errors with actionable output.
+
+**Pattern:**
+1. Read the full error output carefully
+2. Identify the root cause from error messages
+3. Attempt a targeted fix
+4. Re-run to verify the fix
+5. Maximum 3 fix-retry cycles before escalating
+
+**Example:** Build fails with a type error → check for missing import → add it → rebuild.
+
+---
+
+## 4. Escalate with Context
+
+**When:** Recovery attempts have been exhausted, or the failure requires human judgment.
+
+**Pattern:**
+1. Summarize what was attempted and what failed
+2. Include the exact error messages
+3. State what you believe the root cause is
+4. Suggest next steps or who might be able to help
+5. Hand off to the coordinator or the appropriate specialist
+
+**Example:** After 3 failed build attempts → "Build fails on line 42 with null reference. Tried X, Y, Z. Likely a design issue in the Foo module. Recommend the code owner review."
+
+---
+
+## 5. Graceful Degradation
+
+**When:** A non-critical step fails but the overall task can still deliver value.
+
+**Pattern:**
+1. Determine if the failed step is critical to the task outcome
+2. If non-critical, log the failure and continue
+3. Deliver partial results with a clear note of what was skipped
+4. Offer to retry the skipped step separately
+
+**Example:** Generating a report with 5 sections — section 3 data source is unavailable → produce the report with 4 sections, note that section 3 was skipped and why.
+
+---
+
+## Applying These Patterns
+
+Each agent should reference these patterns in their charter's `## Error Recovery` section, tailored to their domain. The charter should list the agent's most common failure modes and map each to the appropriate pattern above.
+
+**Selection guide:**
+
+| Failure Type | Primary Pattern | Fallback Pattern |
+|---|---|---|
+| Network/API transient | Retry with Backoff | Escalate with Context |
+| Tool/dependency missing | Fallback Alternatives | Escalate with Context |
+| Build/test error | Diagnose-and-Fix | Escalate with Context |
+| Auth/permissions | Retry with Backoff | Escalate with Context |
+| Non-critical data missing | Graceful Degradation | — |
+| Unknown/novel error | Escalate with Context | — |