Skill1.3k repo starsupdated today

spk-run-blocked-recovery

The spk-run-blocked-recovery skill diagnoses and resolves blockers that interrupt Spec Kitty workflow commands like next, review, accept, merge, sync, and dashboard operations. It classifies issues into categories such as missing artifacts, invalid states, guard failures, git problems, or authentication errors, then applies targeted specialist skills to repair each blocker type. Use this skill when workflow commands fail and require systematic troubleshooting before escalating to user intervention.

View source Repository: spec-kitty

Install in Claude Code

Copy

git clone --depth 1 https://github.com/Priivacy-ai/spec-kitty /tmp/spk-run-blocked-recovery && cp -r /tmp/spk-run-blocked-recovery/src/doctrine/skills/spk-run-blocked-recovery ~/.claude/skills/spk-run-blocked-recovery

Then start a new Claude Code session; the skill loads automatically.

Definition

SKILL.md

# spk-run-blocked-recovery

Use this skill when `next`, review, accept, merge, sync, or dashboard output
shows a blocker.

## Flow

1. Capture the exact command and blocker output.
2. Classify the blocker: missing artifact, invalid state, guard failure,
   worktree/git issue, sync issue, auth issue, or user decision required.
3. Use the nearest specialist skill: setup doctor, git workflow, team sync,
   review, accept, or merge.
4. Make one repair, rerun the same command, and compare output.
5. Escalate to the user only when the command requires a product decision or
   external credential.

## Rule

Do not bypass a guard. Resolve the reason the guard exists.