CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

fix-handoff-gate

Hand a fix to the independent verifier with a complete fix claim, honest status, deployed fingerprint, rollback plan, and a Done-Gate–compliant report, then react to the verdict. Use after the regression proof passes, and whenever reporting fix status to anyone.

71

Quality

89%

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

85%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 procedural skill with genuine validation checkpoints and error-recovery loops — workflow clarity is exemplary for an instruction-only skill. Its main defects are the dangling reference to templates/fix-claim.json and unspecified invocation details for the claim auditor and recipe library.

Suggestions

Bundle the actual templates/fix-claim.json (or inline its field schema) so the referenced primary artifact exists in the skill directory.

Specify how to run the claim auditor (command or script path) and where the recipe library and ledger live, so steps 4 and 6 are executable without guessing.

Clarify how qa-release-gate relates operationally (e.g., a one-line note on what the verifier will do with the claim) to make the counterpart reference actionable.

DimensionReasoningScore

Conciseness

Roughly 15 lines with zero padding: every line is dense instruction (field lists, exact status strings, verdict-to-action mappings) and nothing explains concepts Claude already knows. Fully matches the "lean and efficient; every token earns its place" anchor.

5 / 5

Actionability

Concrete, executable guidance for an instruction-only skill — step 1 enumerates the exact fields of templates/fix-claim.json, step 2 gives exact status strings, step 6 gives verdict-specific actions. Minor gaps keep it below 5: how to invoke the "claim auditor", where the recipe library and ledger live, and the location of the referenced template are unspecified.

4 / 5

Workflow Clarity

A clear 6-step sequence with an explicit validation checkpoint ("Run the claim auditor on the report; zero flags required") and per-verdict feedback loops (NOT FIXED → root cause; PARTIALLY FIXED → extend sweep; regression → revert first), plus an exit-criteria section. Matches the 5 anchor's explicit validation and error-recovery loops.

5 / 5

Progressive Disclosure

The body is short and well-sectioned, but its primary artifact — "Fill `templates/fix-claim.json`" — is referenced yet absent from the bundle (no templates/, references/, scripts/, or assets/ exist), so navigation to the key referenced material fails. Better than the inlined-content problem of 2, but the dangling core reference prevents a 4.

3 / 5

Total

17

/

20

Passed

Description

87%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: it states concrete artifacts, an explicit two-part trigger clause, and a well-delineated niche in third-person/declarative style. The only weakness is that its top-level action coverage is slightly narrower than its enumerated payload list suggests.

DimensionReasoningScore

Specificity

Enumerates concrete payload items ("complete fix claim, honest status, deployed fingerprint, rollback plan, and a Done-Gate–compliant report") plus the follow-on action "react to the verdict" — several specific actions with minor gaps (e.g., running the claim auditor is not mentioned). It exceeds the 3 anchor (only 1-2 concrete actions) but is essentially two top-level verbs with an enumerated payload, short of the comprehensive multi-action coverage of the 5 anchor.

4 / 5

Completeness

Explicitly answers both what ("Hand a fix to the independent verifier with a complete fix claim... then react to the verdict") and when ("Use after the regression proof passes, and whenever reporting fix status to anyone") with concrete trigger conditions. Both halves are explicit and specific, matching the 5 anchor.

5 / 5

Trigger Term Quality

Includes natural phrases a user would say in this workflow — "fix", "regression proof passes", "reporting fix status" — but misses common variations such as "handoff", "deployed", or "QA verdict". Good coverage, not comprehensive, so it sits at 4 rather than 5 and clearly above the sparse keyword coverage of 3.

4 / 5

Distinctiveness Conflict Risk

A clear niche — fix handoff to an independent verifier in Done-Gate form — with distinct trigger conditions (regression proof passed, reporting fix status) and an explicit counterpart skill (qa-release-gate), so conflict risk is minimal.

5 / 5

Total

18

/

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-handoff-gate/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.