CtrlK
BlogDocsLog inGet started
Tessl Logo

engineer-system-change

Evaluate and carry out non-trivial software-system changes from first principles. Use when assessing RFCs, issues, designs, features, refactors, migrations, dependency changes, or proposed fields, events, APIs, modules, and services whose need, consumers, system fit, validation, or rollback require scrutiny. Read the actual system, identify the concrete problem and named semantic consumers, choose the smallest sufficient solution, reject pseudo-requirements and speculative abstractions, and require evidence proportional to risk. Do not use for mechanical edits, source-code explanation, or a dedicated review of an already-complete diff.

80

Quality

100%

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

100%

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

A tightly written instruction-only skill: dense, non-padded, with a concrete gated workflow, explicit verdicts, and validation/feedback checkpoints. The single-file structure is well organized with no nested references, appropriate given no bundle files exist.

DimensionReasoningScore

Conciseness

The body is dense and assumes Claude's competence — no elementary explanations, no fluff; every line ('Minimize concepts, states, interfaces, irreversible decisions...', 'A verdict records the decision gate and never expands authorization') earns its place, matching the lean-and-efficient anchor.

3 / 3

Actionability

Concrete executable guidance throughout: a named decision-gate sequence, a consumer-question table, an ordered solution-preference list, evidence labels ('VERIFIED', 'INFERENCE', 'UNKNOWN'), and explicit verdicts ('STOP', 'REDUCE', 'REVISE', 'PROCEED', 'NEEDS_EVIDENCE') that map conditions to actions, matching the fully-actionable anchor for an instruction-only skill.

3 / 3

Workflow Clarity

The six numbered gates form a clear sequence with explicit validation checkpoints — 'Reproduce the baseline first', 'Map each important result claim to observed evidence', 'Verify negative boundaries and failure behavior' — plus feedback loops (re-validate, NEEDS_EVIDENCE) satisfying the clear-sequence-with-validation anchor.

3 / 3

Progressive Disclosure

No bundle files exist, so the single SKILL.md is appropriately self-contained; content is well-organized under clear section headings (Preserve the Task Boundary, Apply the Decision Gates, Use Explicit Verdicts, Keep the Output Proportional) with no nested-reference indirection, matching the well-organized-structure allowance for skills needing no external references.

3 / 3

Total

12

/

12

Passed

Description

100%

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, third-person description with explicit 'Use when' triggers, broad concrete action coverage, and a sharp exclusion clause that minimizes conflict with adjacent skills. It answers both what and when without padding.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'assessing RFCs, issues, designs, features, refactors, migrations, dependency changes' plus 'proposed fields, events, APIs, modules, and services' — matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly answers both 'what' ('Evaluate and carry out non-trivial software-system changes from first principles') and 'when' via the 'Use when assessing...' clause, satisfying the explicit-trigger anchor and avoiding the cap at 2.

3 / 3

Trigger Term Quality

Natural user terms are well covered: 'RFCs, issues, designs, features, refactors, migrations, dependency changes' are the vocabulary users actually invoke this skill with, matching the 'good coverage of natural terms' anchor.

3 / 3

Distinctiveness Conflict Risk

Niche is clearly delimited — 'whose need, consumers, system fit, validation, or rollback require scrutiny' and the exclusion 'Do not use for mechanical edits, source-code explanation, or a dedicated review of an already-complete diff' sharply separates it from overlapping skills.

3 / 3

Total

12

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
bytedance/deer-flow
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.