CtrlK
BlogDocsLog inGet started
Tessl Logo

delegated-file-edit-verification

Verify delegated file-edit results directly in the target workspace before accepting success, and rerun with absolute paths if the delegate's report conflicts with reality.

59

Quality

67%

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

Fix and improve this skill with Tessl

tessl review fix ./benchmarks/gdpval/skills/delegated-file-edit-verification/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

The content is highly actionable with executable verification code and a well-sequenced, validated workflow, but it is monolithic and somewhat verbose with redundant restatements of its core principle across multiple sections.

Suggestions

Consolidate the repeated 'never accept a done message' guidance so it appears once (Core principle) rather than being restated in Procedure step 4, Anti-patterns, and Why this works.

Consider moving the longer worked examples and the response template into a separate reference file (e.g. examples.md) and linking to it from a concise overview, to reduce the inline bulk.

Trim narrative explanation in the procedure steps where the checklist and code examples already convey the required actions.

DimensionReasoningScore

Conciseness

The body is mostly efficient and skill-specific, but ~270 lines with recurring restatements of the same 'never trust a done message' idea across the Core principle, Procedure step 4, Anti-patterns, and Why this works sections means it could be tightened, matching 'mostly efficient but includes some unnecessary explanation'.

2 / 3

Actionability

It provides fully executable, copy-paste-ready checks including shell commands (ls, stat, find, test -f, head) and runnable Python snippets for CSV and openpyxl verification, matching the 'fully executable code/commands' anchor.

3 / 3

Workflow Clarity

A clearly sequenced 7-step procedure with explicit validation checkpoints ('Verify immediately after the delegate reports success', 'Re-verify after the rerun'), feedback loops on conflict, and a verification checklist matches the 'clear sequence with explicit validation steps' anchor.

3 / 3

Progressive Disclosure

Sections are well-organized with clear headers and no broken references, but at ~270 lines the skill is monolithic with examples and templates inline and no overview pointing to separate reference files, fitting 'some structure but content that should be separate is inline'.

2 / 3

Total

10

/

12

Passed

Description

57%

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

The description is concrete and occupies a distinct niche, but it lacks an explicit 'Use when...' trigger clause and relies on somewhat technical phrasing rather than natural user keywords, which limits its trigger quality and completeness.

Suggestions

Add an explicit 'Use when...' clause naming natural user phrasings, e.g. 'Use when another agent or sub-task claims it edited a file and you need to confirm the edit actually landed.'

Soften jargon like 'target workspace' and 'delegate's report' toward terms users actually say ('the agent says it saved the file', 'the output location').

Enumerate a few more concrete capabilities (verify existence, check structure, confirm counts/headers) to lift specificity from a partial list to a comprehensive one.

DimensionReasoningScore

Specificity

The description names the domain and concrete actions ('Verify delegated file-edit results directly in the target workspace', 'rerun with absolute paths'), but enumerates only two actions rather than a comprehensive list of capabilities, matching the 'names domain and some actions' anchor.

2 / 3

Completeness

It clearly states what the skill does, but the 'when' is only implied ('before accepting success', 'if the delegate's report conflicts') with no explicit 'Use when...' trigger clause, which per the guidelines caps completeness at 2.

2 / 3

Trigger Term Quality

Relevant keywords like 'file-edit', 'target workspace', and 'absolute paths' appear, but the phrasing is technical rather than natural user speech and lacks common variations a user would say, fitting the 'some relevant keywords but missing common variations' anchor.

2 / 3

Distinctiveness Conflict Risk

'Delegated file-edit verification' is a narrow, clearly defined niche with triggers tied to delegation scenarios, making it unlikely to fire for the wrong skill, matching the 'clear niche with distinct triggers' anchor.

3 / 3

Total

9

/

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
HKUDS/OpenSpace
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.