CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

fix-data-repair

Repair data damaged by a bug — duplicates, wrong grants, orphans, unowned records, stale caches — with dry-run counts, backups, idempotent reversible scripts, and human approval for production. Use when root-cause analysis shows a bug may have written bad data.

75

Quality

94%

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

92%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.

An exemplary lean, safety-first workflow: every step is sequenced with explicit validation (dry-run counts, idempotency proof, approval gate, zero-row verification) and the exit criteria make completion unambiguous. The single improvement area is actionability — one small concrete pattern (e.g., how to back up rows) would make the script step fully copy-paste ready.

DimensionReasoningScore

Conciseness

Roughly 19 lines with zero padding: every step adds non-obvious instruction ('sanitized sample (no personal data)', 'idempotent (safe to rerun)') and no concepts Claude already knows are re-explained.

5 / 5

Actionability

Each step carries specific, executable guidance ('dry run: counts and a sanitized sample', 'back up affected rows first', 'rerun to prove idempotency'), but no concrete code or command patterns (e.g., a backup-table snippet or SQL skeleton) are given — minor gaps for an instruction-only skill.

4 / 5

Workflow Clarity

Seven clearly sequenced steps with explicit validation checkpoints: dry-run counts, before/after count comparison, a rerun-to-prove-idempotency feedback loop, a production approval gate, and a final zero-row damage-query verification.

5 / 5

Progressive Disclosure

Under 50 lines with no need for external references; well-organized into Procedure, Exit criteria, and a counterpart note, which satisfies the simple-skill exception for a top score.

5 / 5

Total

19

/

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: specific, third-person, and complete with an explicit 'Use when' trigger clause tied to root-cause analysis. The only gap is that a few natural synonyms (e.g., 'clean up', 'backfill', 'data corruption') are absent from the trigger vocabulary.

DimensionReasoningScore

Specificity

Lists multiple concrete repair targets ('duplicates, wrong grants, orphans, unowned records, stale caches') plus concrete safeguards ('dry-run counts, backups, idempotent reversible scripts, and human approval for production') — comprehensive coverage in third-person voice.

5 / 5

Completeness

Explicitly answers both what ('Repair data damaged by a bug... with dry-run counts, backups, idempotent reversible scripts, and human approval for production') and when ('Use when root-cause analysis shows a bug may have written bad data') with a concrete trigger phrase.

5 / 5

Trigger Term Quality

Good coverage of natural terms users would say ('duplicates', 'orphans', 'stale caches', 'bad data', 'repair'), but misses common variations like 'clean up data', 'backfill', or 'data corruption'.

4 / 5

Distinctiveness Conflict Risk

Clear niche (post-bug data repair) with a distinct trigger ('root-cause analysis shows a bug may have written bad data'); minimal overlap risk with generic data-analysis or QA 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

itsablabla/qa-bug-agent-skills

Path

skills/fix-data-repair/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.