file-sync

Sync files with centralized storage. Use when your coordinator or another Worker notifies you of file updates (config changes, task files, shared data, collaboration artifacts).

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./manager/agent/openhuman-worker-agent/skills/file-sync/SKILL.md

Quality

Content

80%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, highly actionable skill body with copy-paste-ready commands and a real backing script, well-structured for a simple single-purpose skill. The main gap is the absence of an explicit validation/verification step around the destructive `--overwrite` push, which caps workflow clarity.

Suggestions

Add an explicit validation checkpoint after the push (e.g., verify the pushed files landed in MinIO with `mc ls` or check the script's OK output) before confirming to the coordinator, since `mc mirror --overwrite` is a destructive/batch remote operation.

Reduce redundancy between the inline command examples and the 'Example workflow' section, or collapse the standalone commands into the workflow to tighten the body.

Consider noting that `push-shared.sh` fails fast (set -euo pipefail) so a non-zero exit means the push did not complete, making the implicit validation path explicit.

Dimension	Reasoning	Score
Conciseness	The body is efficient with no over-explanation of concepts Claude already knows, using direct commands and brief caveats. Below 5 because the 'Example workflow' section repeats the mc mirror and push-shared.sh commands already shown above, adding mild redundancy; above 3 because the rest is tight and purposeful.	4 / 5
Actionability	Provides fully executable, copy-paste-ready commands (mc mirror, cat, bash push-shared.sh) plus a concrete end-to-end example with a real task id (st-01), and the referenced push-shared.sh script exists and is complete. Matches the top anchor for copy-paste-ready guidance covering common cases.	5 / 5
Workflow Clarity	The pull -> read -> work -> push -> confirm sequence is clearly laid out, but the destructive `--overwrite` push to centralized storage has no explicit validation/verification checkpoint before or after, so per the batch/destructive cap workflow clarity cannot exceed 3. It is above 2 because the sequence is well-defined rather than rough.	3 / 5
Progressive Disclosure	Content is well-organized into clear sections with operational detail kept in SKILL.md and a single one-level-deep bundle reference (scripts/push-shared.sh) that is real and naturally signaled via the invoking command. Matches the top anchor for a simple, well-structured skill with easy navigation; no nesting or buried references.	5 / 5
	Total	17 / 20 Passed

Description

78%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 well-constructed description that clearly states both capability and trigger conditions with concrete, natural trigger terms. Minor room to improve by enumerating specific sync actions and adding synonyms/file extensions for richer trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('Sync files with centralized storage') and one concrete action (sync), matching the anchor for 1-2 concrete actions without being comprehensive. It is above score 2 (which requires only minimal/generic actions) because 'sync' is a concrete named action, but below 4 because only a single action is given with no enumeration of sub-actions.	3 / 5
Completeness	Explicitly answers both what ('Sync files with centralized storage') and when ('Use when your coordinator or another Worker notifies you of file updates...') with concrete trigger phrases, matching the top anchor exactly. Not below 4 because the 'when' clause is explicit and specific rather than weakly implied.	5 / 5
Trigger Term Quality	Includes natural trigger phrases a coordinator would say ('file updates', 'config changes', 'task files', 'shared data', 'collaboration artifacts') giving good keyword coverage. Below 5 because it lacks synonyms and file extensions, but clearly above 3's 'some relevant keywords' bar.	4 / 5
Distinctiveness Conflict Risk	The coordinator/Worker notification framing gives it a distinct niche with low conflict risk versus general file skills. Below 5 because the verb 'sync files' is still somewhat broad and could overlap with related storage skills, but above 3 because the trigger context is clearly specialized.	4 / 5
	Total	16 / 20 Passed

Validation

100%

Warnings & errors only

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: agentscope-ai/AgentTeams
Path: manager/agent/openhuman-worker-agent/skills/file-sync/SKILL.md
Commit: 69c5849

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.