smart-retry

Included with Lifetime

$97 forever

Use when retrying a failed operation — but with a different strategy, not the same one. "Try again differently", "retry with another approach". Memory-aware so it doesn't repeat strategies that already failed.

General

What this skill does


# smart-retry

Retry with a different strategy. Memory-aware — refuses to repeat what already failed.

## When this differs from naive retry

- Network blip → naive retry works
- Test failure → smart-retry needs *different angle*
- Build error → likely needs config change, not re-run
- Rate-limit → wait, then naive retry

Smart-retry classifies the failure first.

## Method

1. **Failure capture.** What failed? Full error + context.
2. **Memory pass.** `mem_search { query: "<error signature>", k: 5 }`. Has this been hit before? What was tried?
3. **Classify.**
   - **Transient** (network, rate-limit, race) → wait + naive retry, max 3 attempts
   - **Definitive** (test failure, type error, missing dep) → strategy switch needed
   - **Configuration** (env var, missing file, permission) → fix-then-retry
4. **Generate strategies.** For definitive failures, list 3 distinct approaches. **Distinct** means: different file, different angle, different abstraction.
5. **Apply strategy 1.** If success → log to memory + done. If fail → strategy 2. Cap at 3.
6. **Escalate** to user if all 3 fail with rich context.

## Output shape

```
Failure:        <quoted error>
Classification: <transient | definitive | config>
Memory hits:    <prior failures matching this error>

Strategies (definitive only):

  S1:  <strategy>  — based on memory item <id> (worked then, similar context)
       Apply? [auto / manual]

  S2:  <distinct strategy>  — different angle: <what>

  S3:  <distinct strategy>  — different abstraction: <what>

Cycle 1: applied S1
  Result: <pass | fail with new error>

Cycle 2: applied S2 (S1 failed with same error, switching)
  Result: ✓ pass

Final: green after S2.
Captured: this strategy works for <error class>; future smart-retry will rank S2 first.
```

## Rules

- **Strategies must be distinct.** Re-running the same fix with retries = naive retry.
- **Memory cited per strategy.** "Tried S1 because memory says it worked for similar X."
- **Cap at 3 strategies.** No infinite loops.
- **Escalate richly.** When 3 strategies fail, hand back full diagnosis to user.
- **Capture outcomes.** Successful strategy raises rank for future similar errors.

## Anti-patterns

- Same strategy with cosmetic variation
- Retrying without classifying first (treats all failures as transient)
- Bypassing the cap (3 max)
- Silent retries (no log of what was tried)

## When NOT to use

- Single transient failure — naive retry once
- Definitive error with single obvious fix — just fix
- Heal workflow already running — `/heal` skill is the parent here

## Subagent dispatch

- `general-purpose` per strategy attempt
- Memory MCP for prior-failure lookup

## Value over native CC

CC retries on errors but tends to retry the same approach. Smart-retry forces strategy-distinctness + memory-grounding. The discipline IS the value.

Files: 1

Size: 3.1 KB

Complexity: 7/100

Category: General

Source: https://github.com/ialameh/sift-coder/tree/main/skills/workflow/smart-retry

Related in General

modeling-omnistudio-epc-catalog

Included

Salesforce Industries CME EPC product-modeling skill for Product2-based catalog creation. Use when creating EPC products, configuring product attributes, building offer bundles with Product Child Items, or reviewing EPC DataPack JSON metadata for product catalog changes. TRIGGER when: user creates or updates Product2 EPC records, AttributeAssignment payloads, AttributeMetadata/AttributeDefaultValues, Offer bundles, or ProductChildItem relationships. DO NOT TRIGGER when: designing OmniScripts/FlexCards/Integration Procedures (use building-omnistudio-omniscript, building-omnistudio-flexcard, or building-omnistudio-integration-procedure), implementing Apex business logic (use generating-apex), or troubleshooting deployment pipelines (use deploying-metadata).

Generalscripts

relationship-science-coach

Included

Use this skill for direct, practical adult relationship coaching: couples conflict, repair, trust, marriage, dating, flirting, attachment patterns, emotional connection, sex, desire differences, eroticism, kink negotiation, affection, love languages, breakups, and long-term passion. Draw on Gottman, EFT and Hold Me Tight, attachment science, modern sex research, Perel, Nagoski, Kerner, Schnarch, Love and Stosny, and flexible love-language tools. Be concrete and low-hedge. Redirect only for imminent danger, abuse, coercive control, minors, non-consent, self-harm, stalking, or medical/legal/psychiatric decisions.

Generalscripts

building-sf-integrations

Included

Salesforce integration architecture and runtime plumbing with 120-point scoring. Use this skill to set up Named Credentials, External Credentials, External Services, REST/SOAP callout patterns, Platform Events, and Change Data Capture. TRIGGER when: user sets up Named Credentials, External Services, REST/SOAP callouts, Platform Events, CDC, or touches .namedCredential-meta.xml files. DO NOT TRIGGER when: Connected App/OAuth config (use configuring-connected-apps), Apex-only logic (use generating-apex), or data import/export (use handling-sf-data).

Generalscripts

venue-templates

Included

Access comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.

Generalscripts

let-fate-decide

Included

Draws the 12 Houses of the Zodiac Tarot spread to inject entropy into planning when prompts are vague, ambiguous, or casually delegated. Interprets the spread to guide next steps. Use when the user says 'let fate decide', 'YOLO', 'whatever', 'idk', or other nonchalant phrases, makes Yu-Gi-Oh references, or when you are about to arbitrarily pick between multiple reasonable approaches. Prefer over ask-questions-if-underspecified when the user's tone is casual or playful rather than precision-seeking.

Generalscripts

net-ops

Included

Cross-platform network troubleshooting (Windows, macOS, Linux) via local or remote shell. Use for: DNS broken, can't resolve hostnames, nslookup/dig works but apps fail, NRPT, WFP, scutil, /etc/resolver, systemd-resolved, /etc/resolv.conf, NetworkManager, VPN DNS leak residue (ProtonVPN/Mullvad/WireGuard/AnyConnect), AV/firewall blocking DNS or DoH, Tailscale DNS interaction, intermittent connectivity, remote diagnostics over SSH.

Generalscripts