CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

recovery

Plan PsychSift restore, rollback, queue recovery, reconciliation, backup validation, and disaster-recovery proof without modifying live systems automatically. Use for failed jobs, corrupted state, rollback planning, or continuity exercises.

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

86%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A lean, well-sequenced planning skill whose guardrails (approval-required live operations, unproven-assumption identification) are exemplary. Its main gaps are the lack of pointers to where recovery artifacts live and no modeled feedback loop for validation failures.

Suggestions

Add concrete pointers or paths for step 2 (e.g., where local recovery scripts, migrations, and backups documentation are found) so 'Inspect local recovery scripts' is directly executable.

Include a brief feedback-loop directive in step 4, such as 're-verify counts and integrity after each recovery step; stop and roll back on mismatch', to model validate-fix-retry behavior for destructive operations.

Optionally name the deliverable format explicitly (e.g., a runbook template with sections per step) to make the step-6 output reproducible.

DimensionReasoningScore

Conciseness

Ten lines with zero padding: every step adds directives Claude would not infer on its own (approval gating on live systems, acceptable loss window, unproven assumptions). No concept explanations at all.

5 / 5

Actionability

Steps are directive and name concrete artifacts ("manifests, counts", "stop conditions, checkpoints", "ordered recovery runbook"), but "Inspect local recovery scripts, migrations, queue state models" gives no paths or commands for locating them. Mostly actionable with minor gaps; not 3 because the guidance is concrete rather than abstract.

4 / 5

Workflow Clarity

Steps 1-6 are clearly sequenced and step 4 mandates validation content ("stop conditions, checkpoints, rollback, post-recovery integrity, and audit evidence"), satisfying the destructive-operation validation requirement. Not 5 because the skill itself models no validate-fix-retry feedback loop.

4 / 5

Progressive Disclosure

Under 50 lines, self-contained planning skill with no external references needed; the numbered list is well-organized and easy to navigate, matching the simple-skill guideline for a top score.

5 / 5

Total

18

/

20

Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: third-person voice, specific action list, an explicit 'Use for' trigger clause, and a distinctive system-scoped niche. The only weakness is modest synonym coverage in its trigger terms.

DimensionReasoningScore

Specificity

Lists six concrete actions ("restore, rollback, queue recovery, reconciliation, backup validation, and disaster-recovery proof") with comprehensive coverage of the recovery domain; not 4 because there are no minor gaps in coverage.

5 / 5

Completeness

Explicitly answers both what ("Plan PsychSift restore, rollback, queue recovery...") and when ("Use for failed jobs, corrupted state, rollback planning, or continuity exercises") with concrete trigger phrases. Not 4 because the 'when' clause is fully explicit, not merely present.

5 / 5

Trigger Term Quality

"failed jobs, corrupted state, rollback planning, continuity exercises" are natural phrases a user would say, but common variations like "outage", "data loss", or "restore failure" are absent. Not 5 because a few natural synonyms are missing.

4 / 5

Distinctiveness Conflict Risk

The system-specific name "PsychSift" plus a distinct recovery-planning niche (restore/rollback/reconciliation) gives clear triggers with minimal conflict risk against generic skills.

5 / 5

Total

19

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

BigSimmo/PsychSift

Path

.agents/skills/recovery/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.