task-progress

Use when executing a task (progress logging, plan updates), when resuming a task after session reset, or when managing task history. Covers progress log format, task-history.json, and resume flow.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

83%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 tight, actionable skill body with concrete paths, commands, and formats that assumes Claude's competence. Its main weakness is the absence of validation/verification steps around the batch `mc mirror --overwrite` sync and history writes, which caps workflow clarity.

Suggestions

Add a verification step after the `mc mirror` push (e.g., confirm the synced files exist remotely or check the command's exit status) to satisfy the validation requirement for batch/overwrite operations.

Include a brief validation check in the resume flow (e.g., verify `task_dir` exists and `spec.md`/`plan.md` are readable before proceeding) so failures surface early.

Validate `task-history.json` shape before writing (e.g., ensure `recent_tasks` stays ≤10 after an insert) to guard the LRU overflow logic against corruption.

Dimension	Reasoning	Score
Conciseness	Lean and efficient: gives file paths, formats, and commands directly with no padding or explanation of concepts Claude already knows; the Gotchas add only non-obvious operational details.	5 / 5
Actionability	Fully executable guidance — concrete paths (~/shared/tasks/{task-id}/progress/YYYY-MM-DD.md), a copy-paste push command (mc mirror ... --overwrite), a complete JSON schema, and explicit rules for each operation.	5 / 5
Workflow Clarity	The resume flow is a clear numbered sequence, but the batch/overwrite `mc mirror ... --overwrite` operation and JSON writes have no validation or verification checkpoints, which caps this dimension at 3 per the destructive/batch guideline.	3 / 5
Progressive Disclosure	Well-organized into clear sections (Gotchas, Progress Log, Task History, Resume Flow) with no nested references; the skill is self-contained, though at ~71 lines it slightly exceeds the under-50-line simple-skill threshold for a top score.	4 / 5
	Total	17 / 20 Passed

Description

83%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, third-person description that pairs a clear capability statement with explicit "Use when..." triggers and concrete named artifacts. It is concise without being vague and clearly signals when to invoke the skill.

Dimension	Reasoning	Score
Specificity	Names several concrete artifacts and actions — "progress logging", "plan updates", "task-history.json", "progress log format", and "resume flow" — rather than vague abstractions, with only minor coverage gaps.	4 / 5
Completeness	Explicitly answers both what ("Covers progress log format, task-history.json, and resume flow") and when ("Use when executing a task... when resuming... or when managing task history") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural trigger phrases like "executing a task", "resuming a task after session reset", and "managing task history" are present and likely user-spoken, though it leans slightly technical (task-history.json) and misses some synonyms.	4 / 5
Distinctiveness Conflict Risk	The session-reset resume and progress-log/history specifics carve a clear niche, though "executing a task" is broad enough to create minor overlap with general task-management skills.	4 / 5
	Total	17 / 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/hermes-worker-agent/skills/task-progress/SKILL.md
Commit: 223ddc2

Reviewed: 13 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.